{"as_of":"2026-08-04T03:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:83f292089cadae1c039ec50f653c19ff9479f7d431954ba9b64288a03777a4c6","coverage":[{"denominator":207,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-24T06:41:15.508744Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-03T06:30:56.289259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T19:08:36.655886Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-06-28T19:12:34.724099Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"cited_work":{"arxiv_id":"2309.17257","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.17257","snapshot_observed_at":"2026-06-28T19:12:34.724099Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","venue":"cs.CV","work_id":"a3c2d502-558c-4296-b6f1-5f85d34c2da3","year":2023},"citing_paper":{"arxiv_id":"2606.00620","last_updated":"2026-05-30T08:51:28Z","snapshot_observed_at":"2026-07-06T23:41:19.955034Z","submitted_at":"2026-05-30T08:51:28Z","title":"FlowNar: Scalable Streaming Narration for Long-Form Videos","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T19:08:36.655886Z"},"links":{"cited_paper":"/paper/2309.17257","citing_paper":"/paper/2606.00620"},"observation_digest":"sha256:922b72079c56a317bd5b28dc016d19c5278def3a52499fe2ca66ed7dd3a32b54","observation_id":"7bb88481-8851-4576-a1b4-451c9119724e","resolution":{"observed_at":"2026-06-28T19:12:34.725222Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.17257/citation-record","integrity":"/paper/2309.17257/integrity","json":"/paper/2309.17257/citation-record.json","paper":"/paper/2309.17257"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Slowfast networks for video recognition","venue":null,"work_id":"53650608-25e0-4fe0-a4cd-29250689c0e7","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:c99a05af643ec71b9d6baf7fd9bc5c7aa5b692e7903f05a885a2ca574ee691c8","observation_id":"5cc12138-b01a-4a6a-8088-8b233b337fc8","resolution":{"observed_at":"2026-05-24T06:44:03.841227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Video swin transformer","venue":null,"work_id":"f6023625-7742-48ab-b0c1-a995399cb2cb","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:90ce2f647f4a3f7c49c2c4c80dbde8069ce06bebd6d38553a7b39280fe83b96a","observation_id":"2142e81c-35d0-46b1-8859-60dc4c77d23c","resolution":{"observed_at":"2026-05-24T06:44:03.838116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Philipp, ¨Uber die Formalisierung und Analyse medizinischer Prozesse im Kontext von Expertenwissen und k¨ unstlicher Intelligenz","venue":null,"work_id":"61431868-c331-49a1-8b7f-ef7ad0bb131f","year":2023},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:b0ba33e239ef544f8abf33639660127d0edae1c4033e41c80d3bfb3ce6743612","observation_id":"dab96e10-ef32-4e99-bf58-9b9dcc190f9b","resolution":{"observed_at":"2026-05-24T06:44:03.832420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anticipating visual representations from unlabeled video","venue":null,"work_id":"ff2a33ac-85da-4176-8097-9a8c56fcc7c3","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:978fbe2d49bc9102ec3b059e26d05f0591db1a571e20d65e3959c0150bed564b","observation_id":"a9eb470f-0c66-41b1-9ad1-4152e5981a9f","resolution":{"observed_at":"2026-05-24T06:44:03.829245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Temporal Aggregate Repre- sentations for Long-Range Video Understanding","venue":null,"work_id":"f6f7aa52-bb5b-476b-9192-ce236d218387","year":2020},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:bc4f8c969566020576a09a23a8f334fd07444aadc58c1754e7514d405e65b429","observation_id":"5f835a5d-588a-4167-bbbf-fb9c807b6815","resolution":{"observed_at":"2026-05-24T06:44:03.826236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"MeMViT: Memory-Augmented Multiscale Vi- sion Transformer for Efficient Long-Term Video Recognition","venue":null,"work_id":"b3c52054-39ae-4ff6-889f-92e2d4550b70","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:62d7f3d09e4451e599a839859bf3d4897661d05c98e8d04cde7cdecb093f971d","observation_id":"f322564c-99bb-46dd-a3b4-792b55dc8156","resolution":{"observed_at":"2026-05-24T06:44:03.861175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling egocentric vision: The epic-kitchens dataset","venue":null,"work_id":"461ce118-1a71-406b-81f5-a3c64befbdab","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:7979ebcb4b8cc62c6ab56f2921489b16e89ef451c62ea76930f2428fbc55ea90","observation_id":"5507089b-a6dd-496d-813d-f98c43add257","resolution":{"observed_at":"2026-05-24T06:44:03.819760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.10352","last_updated":"2023-10-21T04:57:29Z","snapshot_observed_at":"2026-07-06T14:07:35.137233Z","submitted_at":"2022-10-19T07:40:47Z","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","version":5},"cited_work":{"arxiv_id":"2210.10352","doi":"10.48550/arxiv.2210.10352","metadata_source":"arxiv_reference","pith_arxiv_id":"2210.10352","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Temporal action segmentation: An analysis of modern technique","venue":null,"work_id":"19e3238b-653c-4de2-a74b-6f561293dd87","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"cited_paper":"/paper/2210.10352","citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:6f6a901deab707d8d684fc9fb41d7829a3da4644e532cb9a451e92d491531146","observation_id":"6e26cdda-d609-431a-aecc-bd8aad4155ea","resolution":{"observed_at":"2026-05-24T06:44:02.294717Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep learning-based action detection in untrimmed videos: A survey","venue":null,"work_id":"72dd8245-633a-41d0-8a99-a8af925d21b7","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:9bb50caf334b530d4ae017c4ba8c3ff9f8716b7663f08aa2dd584f253791204b","observation_id":"7850f9d9-8c99-4c23-8a1a-ce4c07e8e857","resolution":{"observed_at":"2026-05-24T06:44:03.816516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A Review on Deep Learning Techniques for Video Prediction","venue":null,"work_id":"d01e5e26-3c70-45e8-ba17-74103cc617d6","year":2020},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:832bd32faa9dcfdcea52093830aa02d6a2588d5b1d12858ed2e5053477b95366","observation_id":"66679975-1c27-49a3-8d51-75188167fb63","resolution":{"observed_at":"2026-05-24T06:44:03.876265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Human motion trajectory prediction: A sur- vey","venue":null,"work_id":"87fa4e09-d817-40d4-ab8d-45bccedef8c3","year":2020},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:fa90249882d2a23e7cd84a4d0c90b2732d3e4000bfa9421ea74933ee357f05d3","observation_id":"01689e0a-51aa-4231-9251-e6ea45d784f6","resolution":{"observed_at":"2026-05-24T06:44:03.810131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3d human motion prediction: A survey","venue":null,"work_id":"cfe571d1-2eb9-4b06-b477-d2e10d80a653","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:8cc42094fc89c06f8db28604e4c29d46f087c19e9f5a7b80a5741288f6194c59","observation_id":"99257441-692c-48a5-a918-74cb0a4409b8","resolution":{"observed_at":"2026-05-24T06:44:03.807183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Convolutional lstm network: A machine learning ap- proach for precipitation nowcasting","venue":null,"work_id":"f3ecd246-d53b-4c08-85bc-c7d5f76f6ffb","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:b79e2371e2d901aa4d4df65f73e1325560288025be6516daf9f9c4cf5a017e05","observation_id":"f1d32c07-bc2a-4461-b76a-2f8fb97a6edf","resolution":{"observed_at":"2026-05-24T06:44:03.801204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Price prediction strategies for market-based scheduling","venue":null,"work_id":"bfcb1b7d-6aca-4bc0-aac4-628ded2f6d52","year":2004},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:9b06e70431294d03ce15a0e2d5b38f8e48eadcce39245e83b00ab14f69656fbf","observation_id":"ae27dce6-2716-4b4a-b8c2-cbb139ce667c","resolution":{"observed_at":"2026-05-24T06:44:03.888860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Human In- tention Estimation based on Hidden Markov Model Motion Validation for Safe Flexible Robotized Warehouses","venue":null,"work_id":"4fcb4967-0aef-4a61-98f5-06532fb146a2","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:be4243c5b89ea7ade5d59cb63e1794093413536f2ef1c3040d863b2c6b861271","observation_id":"3bc9d1c3-4ca6-4e28-84c9-bba538d0d1e0","resolution":{"observed_at":"2026-05-24T06:44:03.795176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anticipating Human Activi- ties Using Object Affordances for Reactive Robotic Response","venue":null,"work_id":"3d8562ec-6635-48d9-aaf9-6b01764edcb3","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:3fe8f5b606eafc1aaa9225045e10a6740e7b7163d800b547a0405f2b1c0881f1","observation_id":"99fb848f-bcb0-465c-a65c-050024d585e5","resolution":{"observed_at":"2026-05-24T06:44:03.895664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models","venue":null,"work_id":"8adcb7fa-4d28-4dfa-a1b8-366aebb17050","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cf731016b04971baae0838bb92e80e722418c9f5f7d915a925c0bb79d49a0a46","observation_id":"50494c8c-d91a-4185-a778-83b3befc8103","resolution":{"observed_at":"2026-05-24T06:46:04.747709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs","venue":null,"work_id":"2876d11c-1301-4a06-bc2a-f7606e016a77","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:76a8713a8c228a37fa95ae71b6bc26ac8f1211a6540c4923d49d40e8b2dbd7f7","observation_id":"2d6486f1-3168-4a25-be8a-36da93be5b26","resolution":{"observed_at":"2026-05-24T06:46:04.751323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Help by predicting what to do","venue":null,"work_id":"a5eecc93-c991-443e-bf6c-19c04607ed73","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:049492dc9bea0e0db3ca48c4508a0496c042974e47aca37361b27f3a83040a81","observation_id":"e9da2c74-6c06-4cb2-b340-e9f4f860ed03","resolution":{"observed_at":"2026-05-24T06:46:04.755154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anticipating the Start of User Interaction for Service Robot in the Wild","venue":null,"work_id":"c051b548-1958-424b-be80-6b69a818d08b","year":2020},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cb05f16ebd316804f1ff29f937dd26ff41019273dc8c517c1b59304fa41dca97","observation_id":"5f500138-5caf-4f3c-b730-eaf11dcd2ca7","resolution":{"observed_at":"2026-05-24T06:46:04.759106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Antici- pation in human-robot cooperation: A recurrent neural network approach for multiple action sequences prediction","venue":null,"work_id":"5f4a10b7-1c0b-429b-82ba-bc741fded50f","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:d4afe7d9943468d185e03f45e0cf291b9dd6e23c6d4c72d65daf88cf94f80aea","observation_id":"b8582bd2-d1ed-47e5-82dc-3801456fa7f2","resolution":{"observed_at":"2026-05-24T06:46:04.732086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Using gaze patterns to predict task intent in collaboration","venue":null,"work_id":"097d83e7-d3fd-4fdd-879e-d5fbf901365d","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:eab4f67dd79344a9f8ca6c2451e2e8df40d2c664fe6d4039ae89954fb934bcd8","observation_id":"b48294f6-c5a6-4235-9fc5-05c06d74be68","resolution":{"observed_at":"2026-05-24T06:46:04.736277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Generating notifications for missing actions: Don’t forget to turn the lights off!","venue":null,"work_id":"283a1430-82ca-4293-a3ca-67a4586c05df","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:96bf5eac42f866aadb9d37d6c01d3dc067ae6d136c14dc1a01fde0c0e3de98f5","observation_id":"c58806d5-0dcd-41c7-af9e-f73d997f0575","resolution":{"observed_at":"2026-05-24T06:46:04.744117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization","venue":null,"work_id":"4158df38-03c4-4f71-87ba-cda541d73ad2","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:9c314998b07efc10403bbe473e9392589d2b54b082b6a6cb8d0277c7583b9a97","observation_id":"60ac5d71-a6e2-4b28-b312-87c4f6f44087","resolution":{"observed_at":"2026-05-24T06:46:04.724307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anticipating traffic accidents with adaptive loss and large-scale incident db","venue":null,"work_id":"9b6bd2fc-bd07-4ea1-87e9-53606c293e52","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:acea1bbf6ef160b5f5210053334a4c49383416b79ffcc86dae9b9d9db048ee23","observation_id":"70c64cd7-6d09-48dc-bdb1-b33b4bbce84b","resolution":{"observed_at":"2026-05-24T06:46:04.717524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A comprehensive survey on human activity prediction","venue":null,"work_id":"82139bee-888a-44b0-8411-7a28bac121a6","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cf89c31b27a171cb3ca2e0132312a3b6253e54b7b8e6ff85573a45af5e54f192","observation_id":"31ef8c01-bd67-4ebe-81da-ab08d08791ad","resolution":{"observed_at":"2026-05-24T06:46:04.721083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.00095","last_updated":"2020-07-22T15:33:06Z","snapshot_observed_at":"2026-07-06T09:34:15.665695Z","submitted_at":"2020-06-30T20:26:46Z","title":"Deep Learning for Vision-based Prediction: A Survey","version":2},"cited_work":{"arxiv_id":"2007.00095","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.00095","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep learning for vision-based prediction: A sur- vey","venue":null,"work_id":"ec9794be-f8b3-429d-be7f-914d0ec4f9ae","year":2007},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"cited_paper":"/paper/2007.00095","citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:dd0ce91fcb9532b7a7481843a66b56e4d45b85b363b0e792682c44b7a6764676","observation_id":"092e0c3d-6468-4880-a748-b4f73f971041","resolution":{"observed_at":"2026-05-24T06:44:02.312821Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Human action recognition and prediction: A survey","venue":null,"work_id":"2ca45b75-6b47-4b84-bd04-e66a201d4ab4","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:00a3c72cafda220573700137199146b55a0ec9b44d5754b4e3bb81f79e5c6eea","observation_id":"2d38e59b-eb94-455a-9504-3f21efeecde9","resolution":{"observed_at":"2026-05-24T06:44:03.937116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pre- dicting the future from first person (egocentric) vision: A survey","venue":null,"work_id":"af4cabfb-cda1-49c4-89ae-dc64d326f057","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:4249d627950bf78e7dceae45273441e2efd2faa12c28131252a171c361c5cb40","observation_id":"159691d6-f1c9-4545-97d4-eb07384954c5","resolution":{"observed_at":"2026-05-24T06:44:03.930331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Online human action detection and anticipation in videos: A survey","venue":null,"work_id":"e1a98002-aa00-42bb-b593-44e7ba560e7d","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:137b1b0f5597fced730bc3c7fdc24f86054d39266ee9f5c868eb0a600a74f8ab","observation_id":"1baa58b6-9ebb-4704-857b-882026800c3c","resolution":{"observed_at":"2026-05-24T06:44:03.933842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.07123","last_updated":"2024-02-07T14:37:42Z","snapshot_observed_at":"2026-07-06T16:05:58.986548Z","submitted_at":"2023-08-14T13:10:48Z","title":"An Outlook into the Future of Egocentric Vision","version":2},"cited_work":{"arxiv_id":"2308.07123","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.07123","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An outlook into the future of egocentric vision","venue":null,"work_id":"28a54482-c015-4f97-b9c6-0d22fa99f62b","year":2023},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"cited_paper":"/paper/2308.07123","citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:76180a87590013610d20767c1c4ea340218a909c6984e83b3a9dd4ac56bf64e6","observation_id":"63b86801-93c8-400e-87cb-89b10800d9b5","resolution":{"observed_at":"2026-05-24T06:44:02.374681Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Modeling Complex Temporal Compo- sition of Actionlets for Activity Prediction","venue":null,"work_id":"c547c5a8-a0e4-43fa-a67b-3937af2cab02","year":2012},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cd129f26b80807ffe1a0a3dacd24c577f40a87f4311434b491e37151f8ec65f0","observation_id":"e178e962-4689-411b-aa54-8f87f97909e0","resolution":{"observed_at":"2026-05-24T06:44:03.940547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Prediction of Human Activity by Discovering Temporal Sequence Patterns","venue":null,"work_id":"749f3ee4-56fe-480f-ad61-d4de740a496e","year":2014},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:117a75a1d6e8a1b6301f8de0eaead6f3f304ff99acaec65c3d1325ef6c9dce83","observation_id":"3fe9154d-000c-4fbd-af0d-c651a7381854","resolution":{"observed_at":"2026-05-24T06:44:03.882432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"First-person activity forecasting with online inverse reinforcement learning","venue":null,"work_id":"480aa736-e987-4d86-aff9-876d4af024a9","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:106ca3dc1e5673e1d1a57a7044540843fc2954b715859833506870ca573d4211","observation_id":"4b2a144b-cf6b-4976-a295-c2ce7f1f940a","resolution":{"observed_at":"2026-05-24T06:44:03.885528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A poisson process model for activity forecasting","venue":null,"work_id":"7698e106-2867-4100-9243-239608dd8d7f","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:daca9f4f4c8d93e794dc099d21cd71ac3efe5f4e4b6cd23a1792f148667bb1bc","observation_id":"a67611ff-b687-48d0-8d47-a20303c8bce8","resolution":{"observed_at":"2026-05-24T06:44:03.909464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Predicting Human Activities Using Stochastic Grammar","venue":null,"work_id":"778de2dd-0b63-4e55-8194-42366f7ccdca","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:8cde5055359c0ddf01b5d35f2d3f88a3719ab68572643536ae9902cd190e6454","observation_id":"4a3ac75d-de88-403f-bc70-a2742d4cc400","resolution":{"observed_at":"2026-05-24T06:44:03.872846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Very deep convolutional net- works for large-scale image recognition","venue":null,"work_id":"4672fd32-1bd7-4120-831d-15226b2b9d97","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:1e914d6ddb45cbd3b591406ecbb6dc6368f2635fff38cfcb90a4077d5e9c9dcd","observation_id":"b67e6aea-f1b3-45d5-8701-b1e576ba801e","resolution":{"observed_at":"2026-05-24T06:44:03.864378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"562319b1-ce6a-4465-94ec-4af6b9229866","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:d38317046cd0a9f310485f73fc7feccd0918e902052e6619e3c79f11defb7da0","observation_id":"35907217-fc0f-4ece-bc24-800ac283decd","resolution":{"observed_at":"2026-05-24T06:44:03.869516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Temporal Segment Networks: Towards Good Prac- tices for Deep Action Recognition","venue":null,"work_id":"7c6cf2c4-8cf8-42b3-ad03-bd994d5cad0b","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cdd5fe49505e263638a790c9ba28f53b20b5b5265dce32376615bf62ecaef4c3","observation_id":"69c84691-5aff-4d68-a5c6-65af0a4c70da","resolution":{"observed_at":"2026-05-24T06:44:03.879440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","venue":null,"work_id":"496352d0-af26-45d5-8d20-922647ec4662","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:a6bf0a3d51050c4f4dd63f482d1975655c514ddc363d2725c206b8ae3441217f","observation_id":"61444025-640c-43d8-9654-08b0792ecf3e","resolution":{"observed_at":"2026-05-24T06:44:03.892240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","venue":null,"work_id":"c57d9f08-ef20-497c-bf4c-4326786e3a5c","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:2c0e04be6984d6eeae76e2bb2f77f5a7297c184614afcbf7513d777808848bf7","observation_id":"559a1d1d-c44b-41f4-adfe-615d677618fc","resolution":{"observed_at":"2026-05-24T06:44:03.954842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Two-stream convolutional net- works for action recognition in videos","venue":null,"work_id":"a6d1f1b6-8a25-424a-b2ec-efdec841950d","year":2014},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cd32e09a008f175b88a3fae15c01beede8ac793b9193ea55e04cbbd33019bb66","observation_id":"eab1fd8f-9cb5-418b-a1e6-3423ec2e700f","resolution":{"observed_at":"2026-05-24T06:44:03.847956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A closer look at spatiotemporal convolutions for action recogni- tion","venue":null,"work_id":"65ee8f85-2d44-4c0f-9fb3-9e47856133d3","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:45f2bb05b9f2417129257e2eaa2c512f787342e5564d75fbde636ea28f3fa190","observation_id":"87ab9945-61eb-4e66-89e3-8871d3246301","resolution":{"observed_at":"2026-05-24T06:44:03.855264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mvitv2: Improved multiscale vision trans- formers for classification and detection","venue":null,"work_id":"ed59b128-52d7-4d1d-93b4-236aa3b976db","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:3291bf81bf25253771ef33fdf4d8efcb23da4640bd95be565f9e8a560d865965","observation_id":"4ffc4c77-41c1-47c8-ace2-e66ab4d88b41","resolution":{"observed_at":"2026-05-24T06:44:03.844363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"RED: Reinforced Encoder- Decoder Networks for Action Anticipation","venue":null,"work_id":"37817422-6d6b-4478-b545-ee3eca28562c","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:2bf4f857e8f707cb9aa23c57c9f6f90a85c0a0fbd29d71741c73e0968e182c9b","observation_id":"5b34b0f8-bc71-4ed6-b930-532d87a2e609","resolution":{"observed_at":"2026-05-24T06:44:03.852183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","venue":null,"work_id":"e0afb650-863d-447d-80bb-2781a573e73e","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:0dcd10f26702523ae007154de2cb102038a2c2b5b0e7d2a57433879f6bcd3e67","observation_id":"6e4b3720-a349-4d73-9ab3-05144c1c20c4","resolution":{"observed_at":"2026-05-24T06:44:03.905690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","venue":null,"work_id":"65369e60-474a-4723-933c-cb3f86db642c","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:0da65e201f312d4aaf0d082b4706ff02ba231ddd1681403ee73f4c7215523933","observation_id":"fc58f94b-6d20-492d-8046-8154a1392acc","resolution":{"observed_at":"2026-05-24T06:44:03.917818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Uncertainty-Aware Anticipation of Activities","venue":null,"work_id":"4f5432d6-72eb-4a83-89a3-f916dbae6e0d","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:d745ca161ee8717f125fc00d4e52b8485920baa392d33a06feb23d06fe0182d2","observation_id":"7f016363-d730-4ccf-8590-af775b5c11a4","resolution":{"observed_at":"2026-05-24T06:44:03.914215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On diverse asynchronous activity anticipation","venue":null,"work_id":"175c75f4-9d83-4173-a9c5-33d0d0b23a70","year":2020},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:12c80f6b1c5780fc5a560b6cd3717f61155066c1aa4e3ae9b933f18415028442","observation_id":"10fced87-d5ee-4529-aca8-908356f365bb","resolution":{"observed_at":"2026-05-24T06:46:04.876132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Weakly supervised action learning with rnn based fine-to-coarse modeling","venue":null,"work_id":"2cb11e38-cab9-4bb6-8901-9142e6f6821e","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:43923c651c372a1314835a025f2731c077b0924e153fa1c4096832f5c7f7b82c","observation_id":"d907a457-1e9d-48a6-bcf3-91a5b40ae480","resolution":{"observed_at":"2026-05-24T06:46:04.843076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ms-tcn: Multi-stage temporal convo- lutional network for action segmentation","venue":null,"work_id":"b09c6fa1-e62d-4b99-ad81-117b9b13eb8b","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:84e15dddcfdcf531dd69094c30a5196a94316579eefe82801276c5981d905b6f","observation_id":"38f77a66-9371-496c-9dcf-614f6771565b","resolution":{"observed_at":"2026-05-24T06:46:04.727853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Weakly-supervised dense action anticipation","venue":null,"work_id":"c2731e6c-01b0-4286-ac91-8ce51106fd12","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:ef4c284e5cf1a2b28de9fe47915e8ddc782873ffd3f0fa698e6a1ec70f0eca52","observation_id":"4cb2dbc1-cd47-453c-8c10-d187c949baf7","resolution":{"observed_at":"2026-05-24T06:46:04.740596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A Variational Auto-Encoder Model for Stochastic Point Pro- cesses","venue":null,"work_id":"df2399ff-b926-4229-ab7e-43251337d979","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:d7d1021bff2b0c667b8f50fb289cea9aa57cc4cfe0d4551d16a5e08e306a9084","observation_id":"747f1008-a1e0-4899-b34d-33611c3503cc","resolution":{"observed_at":"2026-05-24T06:46:04.762891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Faster r-cnn: Towards real- time object detection with region proposal networks","venue":null,"work_id":"5ec3cc96-394a-4a20-a136-918e494bd267","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:b67e194ef03860a5c964788e2cd89869764d2150e86a07ae40f564fd87597b89","observation_id":"fd74d8bb-a5e9-4636-b7e2-a87eea90b730","resolution":{"observed_at":"2026-05-24T06:46:04.827804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mask r-cnn","venue":null,"work_id":"d262d113-400c-4cb7-b525-6282f022c41f","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:c749ecd90650958eefbc20e742244f6b37316a0e7119c7386738c9392bfb8572","observation_id":"afb14458-ee1a-45a3-82c5-509e8c1925e1","resolution":{"observed_at":"2026-05-24T06:46:04.452047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Imagenet classi- fication with deep convolutional neural networks","venue":null,"work_id":"6bbcd6bb-f11e-4c9a-b335-0cb982725237","year":2012},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:b9b35d596bbbbab87df35500bf54f4d96d7ca57b8c3e60b3df9eb4162091fc5e","observation_id":"cfb6a165-8933-49f3-a4ab-881023c53e43","resolution":{"observed_at":"2026-05-24T06:46:04.525462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"High five: Recognising human interactions in tv shows","venue":null,"work_id":"b8fa8ba2-ecc1-4dfd-abff-2247f84d61ee","year":2010},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:6de094c1703b72d9ff63c92a208e21120f508b6e9fb474e2654ffc86c4f1ef09","observation_id":"9accb991-fb6f-4ae5-b11b-e01272ca0401","resolution":{"observed_at":"2026-05-24T06:46:04.529305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Detecting activities of daily living in first-person camera views","venue":null,"work_id":"10d96691-b6ec-4ece-ab3e-6d120a4d8513","year":2012},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:17259d9d62b8c36f97357b2a2ea8b220a4c274865bbdbf6694513940d078adab","observation_id":"042dff29-fb3d-460b-b109-b38b9380d037","resolution":{"observed_at":"2026-05-24T06:46:04.559271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Thumos challenge: Action recognition with a large number of classes","venue":null,"work_id":"f3e6f153-bd17-47f4-8e3c-a05c2a496e80","year":2014},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:b168a41bd9f8e7d95e4a7ba7dde348de075e81ca675441c904380a888419858e","observation_id":"53fcfd84-1365-48ee-9b3d-8b6501ebf5fb","resolution":{"observed_at":"2026-05-24T06:46:04.492514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Visual forecasting by imitating dynamics in natural sequences","venue":null,"work_id":"b676700b-7983-44d9-a759-3967bb15b894","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:13d36359a3224ac8feff72be35dc4fff400d0eef0b5ad59ce30a845b16b37c4c","observation_id":"4ea745e5-b940-451a-86d8-a2f813c8af3b","resolution":{"observed_at":"2026-05-24T06:44:03.788450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.00797","last_updated":"2016-08-02T12:58:30Z","snapshot_observed_at":"2026-07-06T05:05:43.383925Z","submitted_at":"2016-08-02T12:58:30Z","title":"CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016","version":1},"cited_work":{"arxiv_id":"1608.00797","doi":null,"metadata_source":"pith","pith_arxiv_id":"1608.00797","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016","venue":"cs.CV","work_id":"04e71980-0bc7-40b2-b5b3-997150ba1392","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"cited_paper":"/paper/1608.00797","citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:373412c9a312b6e634e189a85aa423dc917767e092b25b82a1eddf0cc63d6a2b","observation_id":"da612db1-8215-4870-8920-6786bf2fa876","resolution":{"observed_at":"2026-05-24T06:44:02.369509Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Online action detection","venue":null,"work_id":"d07abd3a-11f5-452c-8a57-eb99af8389f1","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:e1d83ddb0fa5aedeeeab91e36192fb5e2e637561896269d4d577ee3582492fb2","observation_id":"9fe71379-c8f8-4d94-beb0-10acb66c4c06","resolution":{"observed_at":"2026-05-24T06:44:03.770963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unsupervised learning for forecast- ing action representations","venue":null,"work_id":"10a179cf-2d1e-411d-95ab-82b392cca771","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:6a9a5f8643b757b4f6954cd61bfb693a587ba6040c45e4b0f0921b5256acf2ce","observation_id":"fe66f6a8-c06d-4a31-b050-0c4ab4fd66b1","resolution":{"observed_at":"2026-05-24T06:44:03.780943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Knowledge distillation for human action anticipation","venue":null,"work_id":"e2a61b3e-3512-4aaa-9c97-686067ce3129","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:9d94c49206776f041f5da327c11122baeea05eac7b4c622064845028ccd4e75d","observation_id":"de4f3130-5af1-4646-ba3f-33d3996f0dab","resolution":{"observed_at":"2026-05-24T06:44:03.898657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anticipating human actions by cor- relating past with the future with Jaccard similarity measures","venue":null,"work_id":"b798e355-8858-46d4-9b34-0388d1387a40","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:292bddd3dcba5c9c88a3155781907ca52d9d33817a65a9e82f78f0268bc41abc","observation_id":"7b208524-25f3-4018-96f0-5e2af0625313","resolution":{"observed_at":"2026-05-24T06:44:03.804306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities","venue":null,"work_id":"14b3674d-9b16-444f-918d-aa12230c4156","year":2014},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:5440fe04b095324d0353e02d441fbf1e1e40fe82a6830743f87f83a872866ddb","observation_id":"300b796f-74d0-4c93-86bb-7b90bc3d4c1e","resolution":{"observed_at":"2026-05-24T06:46:04.477016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anticipative Video Transformer","venue":null,"work_id":"cdcf9f22-ce58-4a15-bf51-cf70cd678717","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:3c277dbbbb46fd79d965135a9c9ea4cc8069578cf77c79f512aab2ae3b9ca51d","observation_id":"c8497ea2-9272-4d9f-ad28-ad1984c3499c","resolution":{"observed_at":"2026-05-24T06:46:04.481264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rescaling egocentric vision: Collection, pipeline and challenges for epic- kitchens-100","venue":null,"work_id":"a02a265b-bed3-4e92-ae46-4a6e35433ec4","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:c6b2464662d1d4d0216e09aaab832872a53e12b65315a8d85e1ac8e5e1bd0888","observation_id":"43af0d8f-fbe4-488c-9ba1-dfe6f620f5a4","resolution":{"observed_at":"2026-05-24T06:46:04.496327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"In the eye of beholder: Joint learning of gaze and actions in first person video","venue":null,"work_id":"35e31575-acb5-46c0-9234-a9eadc825440","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:1c2abfe934bba4fadf5b277f74d5039a772dc3bb167b7fd6b7d0344959807296","observation_id":"33f486ef-198a-4376-b11c-db384399edd3","resolution":{"observed_at":"2026-05-24T06:46:04.542519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Combining embedded accelerom- eters with computer vision for recognizing food preparation activities","venue":null,"work_id":"7ff09314-901b-4a90-a923-07c9d38f4075","year":2013},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:0b8f03b0170ad3b330bc7adf45e74510b86be483482efec0b44ffc83e02874e9","observation_id":"21a2c370-08ab-47a1-9647-647631b69e05","resolution":{"observed_at":"2026-05-24T06:46:04.426822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning To Anticipate Future With Dynamic Context Removal","venue":null,"work_id":"ffb929d3-8020-4ce4-b2a1-2b4268700a89","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:0d816f5000b4cbf2b48a37c0a3e390e5870c37bb9fb62415d20322bb211aa948","observation_id":"46ca353c-56c1-4a72-a456-831ae035f573","resolution":{"observed_at":"2026-05-24T06:46:04.430173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tsm: Temporal shift module for efficient video understanding","venue":null,"work_id":"60488e4f-aba1-4643-8823-2752b18d646f","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:50ad815855d39737beafa8d3917d94233f4eb122957af6f67d5f44c1a4098bff","observation_id":"bfacdaf6-a6de-40f6-a8e4-9c4eb7ef6974","resolution":{"observed_at":"2026-05-24T06:46:04.461865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Latency mat- ters: Real-time action forecasting transformer","venue":null,"work_id":"10f237d6-968d-4f32-9ca3-42583263d4fd","year":2023},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:b99a59461de466e1ecd345dfffcbf7e816b35818e2f442d97d54e4e62aa0211a","observation_id":"676c7395-4006-4dc5-bee1-18ecaf373bf0","resolution":{"observed_at":"2026-05-24T06:46:04.412592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fore- casting future action sequences with neural memory networks","venue":null,"work_id":"57f01d65-846a-4e25-a3d5-f4fc1438cc0e","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:f958cd01b8b61977818f70410b4a0d7c3a7395bf9b09e8e37180428ec9a30038","observation_id":"4e78fc35-2e7e-4e4e-96c9-58af12ce263a","resolution":{"observed_at":"2026-05-24T06:46:04.444107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Temporal recurrent networks for online action detection","venue":null,"work_id":"58619ad9-b160-4129-b6d1-9718d5555539","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:9b40b0a9af47a4bf3e52d8ed3f8966a5497494b278b7b661cef8bd82ea1d8557","observation_id":"d5501bac-b97b-4714-a590-0ae668657568","resolution":{"observed_at":"2026-05-24T06:46:04.545997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"TTPP: Tempo- ral Transformer with Progressive Prediction for Efficient Action Anticipation","venue":null,"work_id":"3d93ae53-0b39-40ff-a2fd-e4fda7f419e7","year":2020},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:b88b9933cf1f71a71ed7f802b91ce4b94f7e7df2ad4bc249b7d13fe994e7468b","observation_id":"fea4452f-7e1e-4648-865d-c79cfcbf5378","resolution":{"observed_at":"2026-05-24T06:46:04.831665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.07915","last_updated":"2020-11-16T13:08:47Z","snapshot_observed_at":"2026-07-06T10:14:55.883487Z","submitted_at":"2020-11-16T13:08:47Z","title":"LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection","version":1},"cited_work":{"arxiv_id":"2011.07915","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.07915","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lap-net: Adaptive features sampling via learning action progression for online action detection","venue":null,"work_id":"3e3b1b04-54f0-4f48-a3e3-72c14d2944f2","year":2011},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"cited_paper":"/paper/2011.07915","citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:e4731626d8578fad117f9db88539985b53f2b3bd0a96cce623da7b9c5f77d5ee","observation_id":"78f05e98-2cbe-42d4-8284-fb50c14b4f4b","resolution":{"observed_at":"2026-05-24T06:44:02.332249Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to Anticipate Egocentric Actions by Imagination","venue":null,"work_id":"1c63f685-39fc-4e34-a923-115db8707c31","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:2e9aaec483b2b534665997598ce74d895acc534fbc171403a061aa4827629c42","observation_id":"fa775662-7538-4c8d-9388-dfb8eaf0d390","resolution":{"observed_at":"2026-05-24T06:46:04.846553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Long short-term transformer for online action detection","venue":null,"work_id":"f2f02afc-48dc-4c4d-aac9-ce009219b726","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:762a0fa3fc820620b35334f1a047be9a7f3d06c241623731078c8e56f33fb9cb","observation_id":"a88dc5bd-ea1c-4044-9a5e-aac436e4f127","resolution":{"observed_at":"2026-05-24T06:46:04.864950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Oadtr: Online action detection with transformers","venue":null,"work_id":"8dc4bda5-e4b8-49ca-a467-fd9533755f60","year":2021},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:ab3149b140b865687094858fafc298e1fee507366a9acd5e532e93bbb8736fa6","observation_id":"37d4259b-7ea5-4ee9-b1cc-3a1d63d9e59a","resolution":{"observed_at":"2026-05-24T06:46:04.812531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A Hybrid Egocentric Activity Antici- pation Framework via Memory-Augmented Recurrent and One- shot Representation Forecasting","venue":null,"work_id":"2037d612-3527-4fd3-9d8c-8014d0e529aa","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:7c96cb194d697db1f063a0a8a5aab4af56783fd4c9c7eb2edd31d5f1b9e513d3","observation_id":"5b7c096a-dedd-44cb-9129-35e1f16e496d","resolution":{"observed_at":"2026-05-24T06:46:04.816453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Future Trans- former for Long-term Action Anticipation","venue":null,"work_id":"e295f54a-1e87-487f-a9da-3308fad57a38","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:14a416835ec0063cc5137fd5704d8cc5f62c0a71d740208b5485852ab7ba6b04","observation_id":"fb24917b-66b5-4f89-b845-45fdace287b0","resolution":{"observed_at":"2026-05-24T06:46:04.824036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Real-time online video detection with temporal smoothing transformers","venue":null,"work_id":"97e641b8-db8f-4e4e-b2d7-58ef9ef87902","year":2022},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:700ef3cf7911768f7eefdd0634ed7ab51867b96b7c91d08e2f8cdc7d224388db","observation_id":"2908d0fe-e1be-4012-bbdc-c7f60ee1af11","resolution":{"observed_at":"2026-05-24T06:46:04.809024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Temporal perception and prediction in ego-centric video","venue":null,"work_id":"5ede9d0e-3345-450b-a336-db8ad1a5a9d4","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:ccc0fa77965251d84cb64825853929f0a4bdec4ca8c19914a0787a7b8b302e7d","observation_id":"6e43bac4-f27b-4463-b36e-4864c511ec55","resolution":{"observed_at":"2026-05-24T06:46:04.798500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-07-06T03:01:10.229407Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":"1212.0402","doi":"10.48550/arxiv.1212.0402","metadata_source":"pith","pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-07-11T03:07:53.363433Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","venue":"cs.CV","work_id":"5dfb46e7-e952-409d-a3c7-ba7f20aebad6","year":2012},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:0f74e27bcdb97e8787d1a5c7637df9e0e92b2daed6b3d20b43637817e6f84103","observation_id":"c12a1842-e1e5-4312-b769-d17d5c092673","resolution":{"observed_at":"2026-05-24T06:44:02.320377Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Joint predic- tion of activity labels and starting times in untrimmed videos","venue":null,"work_id":"eb3600d9-71b5-448d-a6c7-97ee40b8454d","year":2017},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:9bf6aa5ef2ba576686ef77287450e3649926b3f6dff7c9bab7416fc77afcfe45","observation_id":"f01d008d-8816-416c-96af-44dc3e851685","resolution":{"observed_at":"2026-05-24T06:44:03.823041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning spatiotemporal features with 3d convolutional net- works","venue":null,"work_id":"90fc38b4-a884-4204-a000-22b031f6b7fa","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:50d84b875dd3434496f22382ac444bfc74701ec112ccb71bc03f07b23ec77614","observation_id":"ef716ce1-a61d-4315-a565-46e0d13f0a78","resolution":{"observed_at":"2026-05-24T06:44:03.858167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A large-scale benchmark dataset for event recognition in surveillance video","venue":null,"work_id":"f7c38a6e-618e-45a3-80cb-7a7d6e5abd9d","year":2011},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:8ad57482ceb31bed6c5004e54acfb2cc2690b3178ac45eba75b4d8a1bcf3d177","observation_id":"542487f0-e75a-4f78-883f-8a4fbd9f8d98","resolution":{"observed_at":"2026-05-24T06:44:03.951411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A database for fine grained activity detection of cooking activities","venue":null,"work_id":"a9c3c4d5-638d-40d6-a7ff-afcfb8ab46b9","year":2012},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:be428fc3ac7c2f8927b84721d44ebf6949f1338e840ce6e42b5208f9b7816224","observation_id":"b9ac334f-47dd-41e5-805d-50e291efb234","resolution":{"observed_at":"2026-05-24T06:44:03.774220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Egocentric activity predic- tion via event modulated attention","venue":null,"work_id":"1bdea937-9878-4cca-be79-839478c4d2a6","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cb04ba0d579d76837b94cfa0201c0bd821cec9a89b3f498a369dbc3e41e0a6a0","observation_id":"b41125b6-6249-4c53-a01c-057c40e402d4","resolution":{"observed_at":"2026-05-24T06:44:03.785018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pixel-level hand detection with shape-aware structured forests","venue":null,"work_id":"3e2d6ec5-7897-40bf-80ee-a3abb811ee48","year":2015},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:0ccc0e9e585a1ac2ea0f1185d01637c4429801d4e24975180809ad2fbc20e932","observation_id":"e998b234-29b1-4c82-b114-1cb081dc6a32","resolution":{"observed_at":"2026-05-24T06:44:03.901924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ssd: Single shot multibox detector","venue":null,"work_id":"622c4abf-84af-4dfa-ad1f-da6bcd1c2250","year":2016},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:6b1da3a356d6615955984ebde3954c538182447ac9040216abdbae66104cda8c","observation_id":"411a5a9d-f7c0-453d-80ba-6490bbc41ddb","resolution":{"observed_at":"2026-05-24T06:44:03.944026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to recognize objects in egocentric activities","venue":null,"work_id":"520d99fc-104d-4b7b-b906-d8f713152ac9","year":2011},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:cfdd45e42832e7b3a728f67eefbb298a04d699df8924a16af2a3c2433787362b","observation_id":"6edd2f4c-00a9-4143-8bab-18ede39f470f","resolution":{"observed_at":"2026-05-24T06:44:03.760381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to recognize daily actions using gaze","venue":null,"work_id":"2509737e-aa46-45b0-9fd0-81e72f9aba7d","year":2012},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:481a95156968a5dc2714f1d6fec691cd9da9898a9fd6f8ed752f3b272ba2542f","observation_id":"e350771d-e7cf-4f07-96df-b682d2dfc3d4","resolution":{"observed_at":"2026-05-24T06:44:03.751018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Peeking Into the Future: Predicting Future Person Activities and Locations in Videos","venue":null,"work_id":"edafcf4c-03a5-4db7-9734-a6d8683528fe","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:6a234ae11974f85643148b5bcea2757959b5f066e6197cf059f6153a73034a8d","observation_id":"f6c21559-1ca9-490d-93bf-e49acbf14ae1","resolution":{"observed_at":"2026-05-24T06:44:03.754133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Encoder-decoder with atrous separable convolution for seman- tic image segmentation","venue":null,"work_id":"39c1e9c2-2726-4417-8c7e-09723d55894c","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:7804d021e57a48e2dc1567c682a43c02620c720f306c75fd5598be33753a9a0c","observation_id":"539872e4-933a-4ca4-ab18-b034189690e6","resolution":{"observed_at":"2026-05-24T06:44:03.947768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Trecvid 2018: Benchmarking video activity detection, video captioning and matching, video storytelling linking and video search","venue":null,"work_id":"c05dec30-1531-42b5-94b1-1764bb51f6b2","year":2018},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:a2c2f1ca2e9c1a728fe500fb6af2638a0bb870a2fe3971bd1f4600544e6d5ee2","observation_id":"0adf070d-130c-4051-87d3-06ed1a855b67","resolution":{"observed_at":"2026-05-24T06:44:03.764294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"What Would You Expect? Antic- ipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention","venue":null,"work_id":"45d77d1b-7617-420f-aa0b-39f1480a11b9","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:67a92ad3edf9d4ce6af33a8d8629a62b23017515c97d13bd7e6518822b0c5524","observation_id":"e1c61884-31d4-44a3-806f-17a502b47405","resolution":{"observed_at":"2026-05-24T06:44:03.813260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video","venue":null,"work_id":"6fa0cb99-1a53-4c02-ae52-e360e880f102","year":2020},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:69f648c1492f9fd30321635f30070774c1edfd17c8da3f738db8534230c6afac","observation_id":"b51a8173-8c96-4769-8f0f-6bb9fca3387e","resolution":{"observed_at":"2026-05-24T06:44:03.923090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Video classifica- tion with channel-separated convolutional networks","venue":null,"work_id":"76052578-4596-40b5-9aed-a372bb8fee20","year":2019},"citing_paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-05-24T06:41:15.508744Z"},"links":{"citing_paper":"/paper/2309.17257"},"observation_digest":"sha256:6baa3cb77590c7160c267cf2d46fd89946a478d8978a64b55072a83dad95c723","observation_id":"27d2da05-28bd-4dbd-86df-84e74d131e80","resolution":{"observed_at":"2026-05-24T06:46:04.801857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2309.17257","last_updated":"2026-04-12T21:40:57Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:25:29.858870Z","submitted_at":"2023-09-29T14:07:56Z","title":"A Survey on Deep Learning Techniques for Action Anticipation"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":6,"verified_fuzzy":94},"total_outbound_references":207},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 100 of 207 outbound references and 1 inbound Pith citation observation for arXiv:2309.17257."}