{"as_of":"2026-08-16T14:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5d6f49923c3b13296f3d2f8baf9f6210e3b550573e5ac675690739dcc7f1c736","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:17:08.029962Z","state":"measured"},{"denominator":74,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":74,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.09445/citation-record","integrity":"/paper/1908.09445/integrity","json":"/paper/1908.09445/citation-record.json","paper":"/paper/1908.09445"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:09.363877Z","title":"Sparse representation for crowd attributes recognition,","venue":null,"work_id":"8895c04d-340f-4677-a7a3-4a128ffc65dc","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.635132Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:842b6cc2b9f62b936ec877c7c33a38ad074a541e3e9d8bf29e1e122b29104e2e","observation_id":"87dc72cb-08a0-4c84-82e4-859635e6bcce","resolution":{"observed_at":"2026-08-14T11:17:09.368870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.349033Z","title":"Research on automatic parking systems based on parking scene recognition,","venue":null,"work_id":"c0b6a646-0049-4d76-9a84-16cb2259e235","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.640460Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:cfad36044a6594dee39ca1f8649bc7fac0a66735ffa67b7158c25f3f54bb382b","observation_id":"20d2518f-e000-4161-b815-7c491f421d85","resolution":{"observed_at":"2026-08-14T11:17:09.353944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.05593","last_updated":"2019-08-15T15:42:57Z","snapshot_observed_at":"2026-08-16T12:21:18.732739Z","submitted_at":"2019-08-15T15:42:57Z","title":"FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.05593","snapshot_observed_at":"2026-08-14T11:17:07.645826Z","title":"Fastpose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.645826Z"},"links":{"cited_paper":"/paper/1908.05593","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:6855f9adbc3c325b883f4993eb8ef3c479cf0971c88d19c39aee3d37d1beb6ff","observation_id":"c6183c24-6565-4203-b43c-9b3bd6af0c17","resolution":{"observed_at":"2026-08-14T11:17:07.645826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.01344","last_updated":"2019-06-04T11:05:24Z","snapshot_observed_at":"2026-08-14T16:21:14.550053Z","submitted_at":"2019-06-04T11:05:24Z","title":"Exploiting Offset-guided Network for Pose Estimation and Tracking","version":1},"cited_work":{"arxiv_id":"1906.01344","doi":null,"metadata_source":"pith","pith_arxiv_id":"1906.01344","snapshot_observed_at":"2026-08-14T11:17:08.310531Z","title":"Exploiting Offset-guided Network for Pose Estimation and Tracking","venue":"cs.CV","work_id":"ef5d7ddf-5680-4b7c-bdf7-f36b38af4eda","year":2019},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.651448Z"},"links":{"cited_paper":"/paper/1906.01344","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:de33208337481b3ec6335263f128eaa2f01c6d522627b724a0a29e2b6ab4e94c","observation_id":"47025c46-861c-4583-a4df-5e9198e3a48a","resolution":{"observed_at":"2026-08-14T11:17:08.317181Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.334336Z","title":"State-aware re-identification feature for multi-target multi-camera tracking,","venue":null,"work_id":"b65382c5-118c-4d93-bcb7-1bf23640c359","year":2019},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.656999Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:5f7ffa0ea0929ed52f9a4e520276a47005c9e70a9e9e9b49bc92bca13e2c82c4","observation_id":"91b9b435-4e14-4bdf-922a-5d60658753c5","resolution":{"observed_at":"2026-08-14T11:17:09.339149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.318060Z","title":"Selection of observation position and orientation in visual servoing with eye-in-vehicle configuration for manipulator,","venue":null,"work_id":"2bf3efe7-967d-4248-a11b-ac2e4d47313d","year":null},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.662106Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:24b8d30d5b87c22005790ac1517250ef28da1eedb40de9cbc372bdec6755da0b","observation_id":"7919de92-26c8-47bc-be3f-91d198c53631","resolution":{"observed_at":"2026-08-14T11:17:09.323369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.302017Z","title":"Adaptive tra- jectory tracking of wheeled mobile robots based on a fish-eye camera,","venue":null,"work_id":"c2853cd6-aede-4698-93b0-c07f9042732e","year":null},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.667240Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:9127c1bbd95bd2e6480157bd293e64bd0f8523121b9d2a136c168c84dec5e14e","observation_id":"a7acd3d5-c318-4316-9ed9-26925e1372f5","resolution":{"observed_at":"2026-08-14T11:17:09.307412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.286105Z","title":"A velocity compensation visual servo method for oculomotor con- trol of bionic eyes,","venue":null,"work_id":"207eb965-d5f9-4a38-b19e-6ca8d58a8657","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.672351Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:a501cbe0385b632fa06f26c037ace16e02efb66461bdeebae64c43764bb50ae7","observation_id":"e3953693-da33-493d-a578-4fdf7e34b253","resolution":{"observed_at":"2026-08-14T11:17:09.291262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.268455Z","title":"Motion control in saccade and smooth pursuit for bionic eye based on three- dimensional coordinates,","venue":null,"work_id":"3aa21116-1e7f-42ba-a409-4097ccc2bac0","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.677829Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:fc28f44f47426e9c635845b19955bd271cb35a5c63d493f8f8d9f4c5fcdcaeb1","observation_id":"c9c406f5-8b45-429d-9476-70475acb0db1","resolution":{"observed_at":"2026-08-14T11:17:09.274310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.04890","last_updated":"2018-07-13T02:15:39Z","snapshot_observed_at":"2026-08-14T18:52:29.694747Z","submitted_at":"2018-07-13T02:15:39Z","title":"Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes","version":1},"cited_work":{"arxiv_id":"1807.04890","doi":null,"metadata_source":"pith","pith_arxiv_id":"1807.04890","snapshot_observed_at":"2026-08-14T11:17:08.286237Z","title":"Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes","venue":"cs.CV","work_id":"4c0475fe-9f37-40b2-a931-bca84274ece2","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.683091Z"},"links":{"cited_paper":"/paper/1807.04890","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:21c9b33b01ae17a59963184645c520602dd747b270a45d39caeb0564e0418a2c","observation_id":"0e75d2bd-e359-4887-895d-df3aaadd3840","resolution":{"observed_at":"2026-08-14T11:17:08.292092Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.07256","last_updated":"2018-11-18T01:59:28Z","snapshot_observed_at":"2026-08-14T17:57:20.704875Z","submitted_at":"2018-11-18T01:59:28Z","title":"Optical Flow Based Online Moving Foreground Analysis","version":1},"cited_work":{"arxiv_id":"1811.07256","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.07256","snapshot_observed_at":"2026-08-14T11:17:08.263503Z","title":"Optical Flow Based Online Moving Foreground Analysis","venue":"cs.CV","work_id":"6dfeb2f9-4ad6-4a46-bee5-f94cf8ff3076","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.689160Z"},"links":{"cited_paper":"/paper/1811.07256","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:7b28dbece2bd6957f7bd5aad6f96ba2363c53e29231601c3d7c1244d0728d618","observation_id":"4f9a07b4-85de-4da3-90d4-d4031cdd22d8","resolution":{"observed_at":"2026-08-14T11:17:08.269324Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.08290","last_updated":"2018-11-21T01:27:27Z","snapshot_observed_at":"2026-08-14T17:57:20.560438Z","submitted_at":"2018-11-18T01:57:44Z","title":"An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes","version":2},"cited_work":{"arxiv_id":"1811.08290","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.08290","snapshot_observed_at":"2026-08-14T11:17:08.237402Z","title":"An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes","venue":"cs.CV","work_id":"2e612009-5a3c-47fb-aec8-e67e8239fd08","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.694470Z"},"links":{"cited_paper":"/paper/1811.08290","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:27a9db59b905b8a58367e87acf1ab37e11a285b66488ecf4e1b420f0d9cd1eb9","observation_id":"7d5e4bde-e85f-4f50-9a79-a797c37f8497","resolution":{"observed_at":"2026-08-14T11:17:08.243766Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.251685Z","title":"Motion cue based instance-level moving object detection,","venue":null,"work_id":"94354073-2efa-4424-87ca-8a9aef7c5668","year":2019},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.700268Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:6063493d4719b4cf07a82a2dc28eb971a5462b813ee4671c0bbc5e3c99dc17ef","observation_id":"06d3cafe-3ec7-487a-b43e-bab80db6bde6","resolution":{"observed_at":"2026-08-14T11:17:09.257150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.235243Z","title":"Std: A stereo tracking dataset for evaluating binocular tracking algorithms,","venue":null,"work_id":"682d06b4-1fbd-41dd-81d1-b64803ad29c6","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.705035Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:a8d9854f6df068d4b253e6ace80a6df62ef3705aa2674c7b429f7d9f3aadfd33","observation_id":"158cf080-787a-4385-a2fe-fb02f628ca85","resolution":{"observed_at":"2026-08-14T11:17:09.240638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.219198Z","title":"Object tracking benchmark,","venue":null,"work_id":"8473c897-41dc-4272-8588-01ee57ce3adc","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.709919Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:219ea3b49f8e5244e02f99c417995acc48f024916d6b5a1dfffd946d86d305c3","observation_id":"4b2bd6df-fc70-47a9-a0fe-7b17d6f2dc0c","resolution":{"observed_at":"2026-08-14T11:17:09.224037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.201925Z","title":"Visual tracking: An exper- imental survey,","venue":null,"work_id":"ae617b76-68e3-41f6-b164-8044e2758201","year":2014},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.715709Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:e66aa626cecef44b5e2e743ec08173d737150be34c94bb6569ce771e97cb1437","observation_id":"0c018eed-2d76-420e-9e52-18203ec62069","resolution":{"observed_at":"2026-08-14T11:17:09.207490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.184359Z","title":"The sixth visual object tracking vot2018 challenge results,","venue":null,"work_id":"67027802-bbcf-408a-9c1c-20ee5689c6c2","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.720584Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:911ab3733c468186d0cc9fc09992017636b44563bcba3d6d72f829603d4f0183","observation_id":"525c7741-5105-45d0-9145-8361cb4cf6a6","resolution":{"observed_at":"2026-08-14T11:17:09.190241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.166941Z","title":"The visual object tracking vot2015 challenge results,","venue":null,"work_id":"71acb6a8-9d1b-4d95-b872-834dc857239e","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.725437Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:79f75fbbe3cadf02c21479dca515c3235059ad190caa48f7311ddc0d5ca29e43","observation_id":"d1b55746-5770-45a5-9cd9-211d560535ad","resolution":{"observed_at":"2026-08-14T11:17:09.172345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.149412Z","title":"Online object tracking with sparse prototypes,","venue":null,"work_id":"ca590f3d-72d0-4929-bfc9-24c8edcd2c36","year":2013},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.730455Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:dd9dd646d094b6e4fd5c6152adcbe247f332c677e4e8dfcaddf5b9d348c106c2","observation_id":"1fc7a8ce-02b7-4636-9c3e-be2c63c3355b","resolution":{"observed_at":"2026-08-14T11:17:09.155253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.133146Z","title":"Inverse sparse tracker with a locally weighted distance metric,","venue":null,"work_id":"484f0cfb-ede8-4362-99c2-219ba0946c39","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.736265Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:7f2c5b0f4d86e2218c4d91e28196a4ee7e90c5e64edcf8f03f8ae28ca7255f8a","observation_id":"117aefe4-78d9-4ff4-87fe-ff4d20779410","resolution":{"observed_at":"2026-08-14T11:17:09.138375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.117135Z","title":"Struck: Structured output tracking with kernels,","venue":null,"work_id":"1db2e0f2-39f4-41fe-a17c-88df493e64c7","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.740905Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:8aab024512ffdf3b07132259e8240f38e050b05d8f2ee12a1221d4e3d1bda02e","observation_id":"3594f549-7a50-4f6d-a811-025ef1389b56","resolution":{"observed_at":"2026-08-14T11:17:09.122112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.099658Z","title":"Real-time tracking via on-line boosting,","venue":null,"work_id":"16c65d9a-e78a-44f6-be89-e70e8412d791","year":2006},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.745811Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:ad42a8e10d9923d59cf5e7823210382b9d4a3b14df5fa7c1165e6cf21c54bf84","observation_id":"5bce6619-c19b-443c-ba46-0dc14f649b12","resolution":{"observed_at":"2026-08-14T11:17:09.105872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.083299Z","title":"Robust object tracking with online multiple instance learning,","venue":null,"work_id":"c24a5f18-d07a-49a0-98af-5df2e62b900a","year":2011},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.750648Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:5a07ac05efec42efbb0970ff402b35fe26581266bee8c7a98a4eaa8b68d21184","observation_id":"e321f8dc-f5c6-47d0-bc19-af9d7508dd28","resolution":{"observed_at":"2026-08-14T11:17:09.088469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.067651Z","title":"High-speed tracking with kernelized correlation filters,","venue":null,"work_id":"bce28e7b-3cf8-4f6d-b76f-8d09853b1d23","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.755546Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:6ae835ea0d47fa169823cded0b3b83be4ca4f672a2917c9c2cd10296dc196d06","observation_id":"69a653e1-065f-48f2-98fd-ba25adbbefc4","resolution":{"observed_at":"2026-08-14T11:17:09.072523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.051141Z","title":"Learning spatially regularized correlation filters for vi- sual tracking,","venue":null,"work_id":"a17dde7c-0442-44d7-86e2-0390d432644a","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.760534Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:b312dae20f797644f69645d94f5d6df635d75b35647b6932726900edfa09d84d","observation_id":"d3853206-34b1-45ad-8338-b863104e1dd6","resolution":{"observed_at":"2026-08-14T11:17:09.056341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.033698Z","title":"Long- term correlation tracking,","venue":null,"work_id":"5cd48ab6-53ba-4d2f-be3c-2a36cd88f820","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.765614Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:fc5be324e145983efdb5fc27ed8754460efda0b3d6e384cdb709049ae4511f41","observation_id":"2582b3f7-1300-404a-9d6d-f15cb7f08f0a","resolution":{"observed_at":"2026-08-14T11:17:09.039480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:09.015912Z","title":"A scale adaptive kernel correlation filter tracker with feature integration,","venue":null,"work_id":"cfa0f69d-fae9-46c3-aed3-06038a9d6f48","year":2014},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.771410Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:d3d7f02c37c3ef0c4d0b0ac4c61f2e1f9ed5b59cc94185b0d59020beaa8202aa","observation_id":"b91dde52-a88d-4fbf-a63c-0dcfc19ccc18","resolution":{"observed_at":"2026-08-14T11:17:09.021381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.999283Z","title":"Ex- ploiting the circulant structure of tracking-by-detection with kernels,","venue":null,"work_id":"226233e7-f401-4052-83a2-d31410c636b7","year":2012},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.777293Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:496aa8e85fc5617cf50cc3f4bada4c42da6939243f7ab11254fbc8a72581d4ca","observation_id":"dff9d339-d178-4edc-a1f6-082205d28fb3","resolution":{"observed_at":"2026-08-14T11:17:09.004501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.982482Z","title":"Discriminative scale space tracking,","venue":null,"work_id":"97594fd1-58d3-43da-8adf-16ef1b4cb1dd","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.783289Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:3d40b705d8dc7b4d23e30714525a6b9757c638584bf1ae48012fe42f1d53c7f7","observation_id":"598da227-3b51-4f44-a509-e50354d77173","resolution":{"observed_at":"2026-08-14T11:17:08.987592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.964577Z","title":"Learning background-aware correlation filters for visual tracking,","venue":null,"work_id":"da53fe4f-894f-4e0e-aadd-990abc2f0ebd","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.788680Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:067b62aafaba47d021557ddf44f58ba476d163a2cd16b92a3a1c991e77a31d1e","observation_id":"edb419b0-39b5-4b62-9739-7aa0b84ec67f","resolution":{"observed_at":"2026-08-14T11:17:08.970448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.947877Z","title":"Imagenet classification with deep convolutional neural networks,","venue":null,"work_id":"6aaf0ddb-f6e9-484d-808f-1ddd49156ffb","year":2012},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.793787Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:cf412ce0734887563128e7c6e14cd29ce94fe637889eac1362b2f027c4333a33","observation_id":"079640e9-feef-4286-a946-46589021d212","resolution":{"observed_at":"2026-08-14T11:17:08.953446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:07.798602Z","title":"Deep resid- ual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.798602Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:be6e8794069fe37e8dedbee815593a88aaf75ee9f0f451d6ef824b592ed20266","observation_id":"ece2480c-b43a-4f71-beb8-c1149564701a","resolution":{"observed_at":"2026-08-14T11:17:07.798602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.920317Z","title":"Faster r-cnn: towards real-time object detection with region proposal networks,","venue":null,"work_id":"a6edb468-2942-4fa9-a830-8970ca44c6cf","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.803852Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:0bf8d92b799b5353be4355ba45288a25dd0cd9afb88cccc0298033fe1f3ce6fe","observation_id":"b165e19c-e904-4311-ba21-23e3bf5c4ec8","resolution":{"observed_at":"2026-08-14T11:17:08.925448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.903787Z","title":"Fully convolu- tional networks for semantic segmentation,","venue":null,"work_id":"960bc130-994f-40b7-9b3e-3a7762a94f6f","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.808812Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:6e0f0fb04fbdb2779a3acf521c98300a5bbb331ca3f29fb0cb1794cb3539e31b","observation_id":"759d49eb-a29b-4c78-b17b-0bceeb8e8351","resolution":{"observed_at":"2026-08-14T11:17:08.909299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.886408Z","title":"Hi- erarchical convolutional features for visual tracking,","venue":null,"work_id":"a0f91bbd-d120-4d8d-aec5-d512c20fc813","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.813944Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:ca056465efdf6486189ffbaa10e2a0c578703655adca4e53990596650488f0eb","observation_id":"8e826822-3165-4480-ae53-393843f68501","resolution":{"observed_at":"2026-08-14T11:17:08.892910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.870214Z","title":"Hedged deep tracking,","venue":null,"work_id":"ecbcd944-1fb0-4196-8dea-46013618b401","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.819171Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:f2432e5ec0a80a5da90f4b3cb73ec6ed670ccc8e5f831b076b0aa1de67670a01","observation_id":"58e88c15-749f-4f3e-968a-4ca7b4053dc0","resolution":{"observed_at":"2026-08-14T11:17:08.875289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.853636Z","title":"Beyond correlation filters: Learning continuous convo- lution operators for visual tracking,","venue":null,"work_id":"102bb92b-4e6f-418f-a6db-5829299b4112","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.824230Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:0ff17f2816b2f24d84185ca77a5d7cc7056e2d8bd3814fd32b7987f7de702659","observation_id":"bfa5d6aa-6328-4bb8-b3b3-9099b9b3ef4d","resolution":{"observed_at":"2026-08-14T11:17:08.859523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.837681Z","title":"Convolutional features for correlation filter based visual tracking,","venue":null,"work_id":"c34db4ff-2484-47a7-9e0c-ad3443cafc78","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.828960Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:a7793debf39e935e94ed98ed3bc31d22716a3981332b9e7f339b10585051be53","observation_id":"739597ea-b92b-4d32-97dd-0a1336e94372","resolution":{"observed_at":"2026-08-14T11:17:08.842836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.822257Z","title":"Fully-convolutional siamese networks for object tracking,","venue":null,"work_id":"362917f9-ceea-4dfc-860b-aaa3b63f4f65","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.834746Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:444485817b79ef8d8b14e89499cc07e96a64e89258ce093bd2ab56599f7bbdc9","observation_id":"9a16c30e-9720-4ee1-ae50-f14fb7e618d1","resolution":{"observed_at":"2026-08-14T11:17:08.827365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.806822Z","title":"Visual track- ing with fully convolutional networks,","venue":null,"work_id":"2b837600-de00-49f1-a46b-45c2e8ca506a","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.840000Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:8eee653e9c162c7c5734db7121cdc22c97f272d50ef2fce79ee43cc9d0de6367","observation_id":"8a6a37b0-9c88-4045-ad0a-918c28865c0d","resolution":{"observed_at":"2026-08-14T11:17:08.811653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.789714Z","title":"The visual object tracking vot2016 challenge results,","venue":null,"work_id":"5f4e2b6e-e9c6-4b3a-b521-1fc532432095","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.845477Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:02a21c6f8493b375897e95c88276653d748bf8e08bf514cb8c30944d98384077","observation_id":"48a08e09-35f5-470a-bb66-bb26c2d491fa","resolution":{"observed_at":"2026-08-14T11:17:08.795131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.772601Z","title":"UCT: Learning unified convolutional networks for real-time visual tracking,","venue":null,"work_id":"c11cb32b-ec7b-4feb-82da-db86025b0cb0","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.850551Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:084993f2b2c7475eaa0d8777feddd3f6a636ef93b0eb2eee657b02c6e3662d4e","observation_id":"c9feeb1c-b3b6-41ab-977a-4382d2518d7e","resolution":{"observed_at":"2026-08-14T11:17:08.778025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.755484Z","title":"Two-stream gated fusion convnets for action recognition,","venue":null,"work_id":"b1694fe7-b511-44b3-aac6-3db5198d72db","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.856703Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:80a0364484afc8507e09096f4370d8ae1845e27060f5f0ee5213efca43850da5","observation_id":"84de5e56-0774-4b42-be42-c107f6219ab6","resolution":{"observed_at":"2026-08-14T11:17:08.760643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.738843Z","title":"Attention-guided unified network for panoptic segmentation,","venue":null,"work_id":"654a5a05-ecfd-41bd-823d-c3b4cd296a95","year":2019},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.861822Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:3775fb18e76ae909b1446bde780cab48147b9ad5409982659707b4be9b287306","observation_id":"fb4fcd4c-ddf7-4941-bf0e-e93adddd0c38","resolution":{"observed_at":"2026-08-14T11:17:08.744164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.05770","last_updated":"2018-12-17T08:12:06Z","snapshot_observed_at":"2026-08-14T17:43:48.614069Z","submitted_at":"2018-12-14T03:43:54Z","title":"Action Machine: Rethinking Action Recognition in Trimmed Videos","version":2},"cited_work":{"arxiv_id":"1812.05770","doi":null,"metadata_source":"pith","pith_arxiv_id":"1812.05770","snapshot_observed_at":"2026-08-14T11:17:08.212130Z","title":"Action Machine: Rethinking Action Recognition in Trimmed Videos","venue":"cs.CV","work_id":"51aff9db-f506-4ebf-81df-7c97e0929ed8","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.867387Z"},"links":{"cited_paper":"/paper/1812.05770","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:a59f752526b40eccdfff7f3f35fca8f36304706c57682f3cc0739b1049e376da","observation_id":"c2011070-9f42-496f-8d44-bbd205e4e1ee","resolution":{"observed_at":"2026-08-14T11:17:08.218197Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1709.03655","last_updated":"2017-09-13T09:13:31Z","snapshot_observed_at":"2026-08-14T20:34:09.467449Z","submitted_at":"2017-09-12T02:09:04Z","title":"Learning Gating ConvNet for Two-Stream based Methods in Action Recognition","version":2},"cited_work":{"arxiv_id":"1709.03655","doi":null,"metadata_source":"pith","pith_arxiv_id":"1709.03655","snapshot_observed_at":"2026-08-14T11:17:08.186305Z","title":"Learning Gating ConvNet for Two-Stream based Methods in Action Recognition","venue":"cs.CV","work_id":"9453a452-da59-4a79-a9c8-67a1a23b1cf3","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.874594Z"},"links":{"cited_paper":"/paper/1709.03655","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:d36a8ad4fad8a1c101a18fe19f8a4e9b06fc2068f8c25a2e6ca43353526dce0f","observation_id":"0bc6f8fe-bc0c-43d0-8cda-bb0a37023410","resolution":{"observed_at":"2026-08-14T11:17:08.192418Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1501.04587","last_updated":"2015-04-23T06:18:09Z","snapshot_observed_at":"2026-08-14T23:03:33.271250Z","submitted_at":"2015-01-19T18:54:34Z","title":"Transferring Rich Feature Hierarchies for Robust Visual Tracking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1501.04587","snapshot_observed_at":"2026-08-14T11:17:07.879815Z","title":"Transferring rich feature hierarchies for robust visual tracking,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.879815Z"},"links":{"cited_paper":"/paper/1501.04587","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:7445c6c01b40248e2d08c9086ee4ec5acfba75593bb430d3a7f9521c07256aa2","observation_id":"6247962e-d6a7-473f-b5af-c967d575ebd2","resolution":{"observed_at":"2026-08-14T11:17:07.879815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.722834Z","title":"Deeptrack: Learning dis- criminative feature representations online for robust vi- sual tracking,","venue":null,"work_id":"24ba3c13-8627-46ab-95e7-67a195e8452d","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.886392Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:26f613e785131b0f8bec9e94f64373774152b00648ca24ffca4a3d0568e6f84a","observation_id":"e08d70c3-93e7-4090-8288-c72e9b5de361","resolution":{"observed_at":"2026-08-14T11:17:08.728020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.10302","last_updated":"2018-11-27T16:39:58Z","snapshot_observed_at":"2026-08-14T17:53:49.216407Z","submitted_at":"2018-11-26T11:41:23Z","title":"Multi-hierarchical Independent Correlation Filters for Visual Tracking","version":2},"cited_work":{"arxiv_id":"1811.10302","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.10302","snapshot_observed_at":"2026-08-14T11:17:08.134700Z","title":"Multi-hierarchical Independent Correlation Filters for Visual Tracking","venue":"cs.CV","work_id":"23e403da-7e8e-4616-9aa6-3318a8b1a6dd","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.891937Z"},"links":{"cited_paper":"/paper/1811.10302","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:e7d4e63a0c652a2a80d49dd2688544e2c0dbcb573a5540d970b3389d40ce2e50","observation_id":"cdb80473-b21a-45d7-945c-49db82877881","resolution":{"observed_at":"2026-08-14T11:17:08.142609Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.705061Z","title":"Learning multi-domain convolu- tional neural networks for visual tracking,","venue":null,"work_id":"9d7f8da6-73a8-425a-87af-2f794a0d1784","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.897403Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:6c75ebdb23687ad8041933b237e4b2e867b1dd81d3c49ba7d62d0eb74c0cfcc0","observation_id":"381eeb05-b51f-490a-854f-8432390765df","resolution":{"observed_at":"2026-08-14T11:17:08.710872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.687783Z","title":"Template matching using fast normalized cross correlation,","venue":null,"work_id":"e7a38dc1-36a2-4174-bd99-810655f05033","year":2001},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.903539Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:726be772f04ec2941fd972a74e9e78f2be745876ce372576f29b5ed298a833e1","observation_id":"a78a8f58-6337-48f1-9447-26b2ce4ae1c9","resolution":{"observed_at":"2026-08-14T11:17:08.693155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.671746Z","title":"Real-time track- ing of non-rigid objects using mean shift,","venue":null,"work_id":"dcc507f9-e71f-45be-b5d4-ff6f6a4cacc2","year":2000},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.908849Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:604de2e5a71067a1e225e7deef524393b521d0ee815ac1117f2658d88e9fbe86","observation_id":"fb95a89c-28ce-4ccd-bf4f-37f12b0e89a8","resolution":{"observed_at":"2026-08-14T11:17:08.676935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.653930Z","title":"Visual object tracking using adaptive correlation filters,","venue":null,"work_id":"13a03c56-ae16-44cb-b497-d49c29eff4f0","year":2010},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.914911Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:3bb79632e65a1a84a5a1576c501f5e13129d93ba83428e91aff4ff471afbc657","observation_id":"d79c3d05-f987-40d3-b848-f8fa7237fa4b","resolution":{"observed_at":"2026-08-14T11:17:08.659147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.636780Z","title":"Staple: Complementary learners for real- time tracking,","venue":null,"work_id":"09d426da-6aa2-4b39-9bf7-18a645c9cbf0","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.920052Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:f871c95537873ba652f8d20498203e589b7c01a20121b87f9e33f4fbcd6cb603","observation_id":"5013d76e-0b68-44b7-850f-dacf3e48e415","resolution":{"observed_at":"2026-08-14T11:17:08.642551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.618304Z","title":"Correla- tion filters with limited boundaries,","venue":null,"work_id":"e7ab11df-0b25-48c5-a3f4-8ddb0bc02a0f","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.924981Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:f9541aaa95df36d2f8516f8960c1846995cca31c72d99edc14556a2426138235","observation_id":"c1e1e120-c642-47e8-866d-d64c4d0a622d","resolution":{"observed_at":"2026-08-14T11:17:08.623865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.600904Z","title":"Learning to track at 100 fps with deep regression networks,","venue":null,"work_id":"8e603d44-7516-4582-b117-b1dc239643b6","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.929933Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:9c593b2315120c53aecb9c64b42457c65e580c355af59e1b664f7c7056188cba","observation_id":"7bc83923-2d69-4c7c-9a43-6ba62fc9ca4d","resolution":{"observed_at":"2026-08-14T11:17:08.606372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.583853Z","title":"End-to-end representation learning for correlation filter based tracking,","venue":null,"work_id":"b8cf84fe-ef71-443d-8f18-8653f0b2e287","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.934819Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:b854e2f0e2034fb3a423665af1fe57986e27fc70a150ae052a3cd5f6b980bb33","observation_id":"7cd4197c-f051-46e9-b08e-98b58740eab3","resolution":{"observed_at":"2026-08-14T11:17:08.589204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04057","last_updated":"2017-04-13T10:08:14Z","snapshot_observed_at":"2026-08-16T14:43:09.152683Z","submitted_at":"2017-04-13T10:08:14Z","title":"DCFNet: Discriminant Correlation Filters Network for Visual Tracking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04057","snapshot_observed_at":"2026-08-14T11:17:07.939798Z","title":"Dcfnet: Discriminant correlation filters network for visual track- ing,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.939798Z"},"links":{"cited_paper":"/paper/1704.04057","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:c3527335df8841ac33b1e0be74e6139eb18b9cd0a1a4149661c2efd1a1b5cb8a","observation_id":"13b0742b-eedc-451d-adeb-9f81c497f0cd","resolution":{"observed_at":"2026-08-14T11:17:07.939798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.564720Z","title":"End-to-end flow correlation tracking with spatial-temporal attention,","venue":null,"work_id":"1f2d61a6-35ea-4699-9f5f-c438bd958987","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.946546Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:69069fc830eeb728aafb1f65d29f49ca25e3d70c90c974f98bdfa08dbf648a47","observation_id":"00f792ba-cb4d-4e04-999d-47d32be98a31","resolution":{"observed_at":"2026-08-14T11:17:08.571266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.547007Z","title":"End-to-end video-level representation learning for action recognition,","venue":null,"work_id":"2e5dac01-1bae-4075-bd10-26cfb45ca480","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.951952Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:55446c2c5958cf9fca3789076309ac95656e23371ddc05be015d7f956afecdc2","observation_id":"fd9a0de3-493c-47d4-b44b-086a0ab26ee9","resolution":{"observed_at":"2026-08-14T11:17:08.552105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:07.957083Z","title":"High performance visual tracking with siamese region proposal network,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.957083Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:c6fc11d167b764c830d7f7b8a1434328e689de377ba3b66de75dae944248dbf8","observation_id":"92f2473c-c0a6-4103-a3ac-18a2d0390494","resolution":{"observed_at":"2026-08-14T11:17:07.957083Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.517459Z","title":"Distractor-aware siamese networks for visual object tracking,","venue":null,"work_id":"d5c77c4c-b36f-4f1e-8003-78f933642645","year":2018},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.961774Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:fdf8203b02d8b483de6e934cf73c4c1118cee9b9c6b0a2d26792b7c0cefc9e5d","observation_id":"c3b2abea-a567-49ae-ac17-aeae9e194aec","resolution":{"observed_at":"2026-08-14T11:17:08.523405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1509.04874","last_updated":"2015-09-19T02:36:04Z","snapshot_observed_at":"2026-08-14T22:40:32.015602Z","submitted_at":"2015-09-16T10:30:37Z","title":"DenseBox: Unifying Landmark Localization with End to End Object Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1509.04874","snapshot_observed_at":"2026-08-14T11:17:07.966774Z","title":"Densebox: Unifying landmark localization with end to end object detection,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.966774Z"},"links":{"cited_paper":"/paper/1509.04874","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:aa4bf9d2ced31aca472500b55f9b1daec34f8b9d503859878a274f59cee61045","observation_id":"887c4d53-a424-49f9-8737-9bbf5e40114a","resolution":{"observed_at":"2026-08-14T11:17:07.966774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.500996Z","title":"Learning a deep compact im- age representation for visual tracking,","venue":null,"work_id":"1086ce0f-dddc-4ca2-bba8-ef65e8d8ef17","year":2013},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.973849Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:8b7cb5f190c06b76418cad74f43d623c7629ef7a0bb38190e68a6cff8956e6a9","observation_id":"7b19bb41-f9b4-4255-9c10-3c32629288ed","resolution":{"observed_at":"2026-08-14T11:17:08.506636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.483429Z","title":"Online object tracking: A benchmark,","venue":null,"work_id":"bc9c88a9-759c-4f4b-8ab9-024e1b399ed8","year":2013},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.979411Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:04c70601e4f7abd0cd5e090d6321b8849346662956ae07cd1d3cac6097338169","observation_id":"e4db4af5-dd26-4ca8-8efd-f608dd0eeb55","resolution":{"observed_at":"2026-08-14T11:17:08.489457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.465965Z","title":"The visual object tracking vot2015 challenge results,","venue":null,"work_id":"09f1cb42-960e-4a75-b23a-72ea6a996069","year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.984416Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:782899b2070a637458303c2cd2c95e6f7f498429d8e16d463b399ead8a5467a9","observation_id":"4edab244-8a2b-4685-8d26-0a5f1ee66768","resolution":{"observed_at":"2026-08-14T11:17:08.471986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-14T11:17:07.989372Z","title":"Very deep convolu- tional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.989372Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:9d9ce20dc1a7887e0aa8d377996322002f820d62b42a9043d5e0c71c68013fd8","observation_id":"ca3dfd43-e18b-442e-9fcc-d20bf87010ed","resolution":{"observed_at":"2026-08-14T11:17:07.989372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.448467Z","title":"Visualizing and under- standing convolutional networks,","venue":null,"work_id":"b1f66d7f-e4e3-4914-b5df-3fa6b0af684e","year":2014},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:07.995746Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:b0b847000cae2abe20b467425348310840be61d51162963ee6ae5cfebe1716c5","observation_id":"0db610fd-45c2-4fb2-b6e3-3be25ab0dae3","resolution":{"observed_at":"2026-08-14T11:17:08.453996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.001388Z","title":"ImageNet Large Scale Visual Recognition Challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:08.001388Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:98c6e1eeff155ed03b31e14a213820af34bfa265bc6d54064dab7769e6fd9941","observation_id":"c5b0470c-3b0a-4e0d-931c-183098b54b7a","resolution":{"observed_at":"2026-08-14T11:17:08.001388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:17:08.418987Z","title":"Caffe: Convolutional architecture for fast feature embedding,","venue":null,"work_id":"44599f85-40bd-4f3c-af9e-515cb444062b","year":2014},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:08.006525Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:3b61a121f31277fd296c3b94b0eb0b49360ac5bdc124864370c9fa384b08fd56","observation_id":"182d9cd6-168f-4a6f-8297-8492ce0171d3","resolution":{"observed_at":"2026-08-14T11:17:08.424373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.401818Z","title":"Parallel tracking and verifying: A framework for real-time and high accuracy visual tracking,","venue":null,"work_id":"ac127b93-6386-4d1a-be33-03f2b28ec307","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:08.011662Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:244915f10f786f7dff8ddaaaabfc1c39ebfd453d3d4f3f4ae33ef0efdbff0dbb","observation_id":"5d3783e9-1cc2-49e7-8e2c-7c10b24658b0","resolution":{"observed_at":"2026-08-14T11:17:08.407189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.384779Z","title":"Context-aware correlation filter tracking,","venue":null,"work_id":"a453ba89-07d9-41c8-a136-f0c09e489d2e","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:08.018405Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:81a5d69567adb4a0bd8c252dc70e3854dd9fa5a7036b864c47519f71b6c5453d","observation_id":"bc4fa692-eb39-4a0a-be0f-6160fba59790","resolution":{"observed_at":"2026-08-14T11:17:08.390072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.367846Z","title":"Discriminative correlation filter with channel and spatial reliability,","venue":null,"work_id":"ddc81f59-bfa4-4075-b127-eb9de7f7f2bd","year":2017},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:08.024618Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:cc527330bca621efe19a46524dd55271b4a673b52d8089ff51b8007d3a78af06","observation_id":"412f9d43-3d23-4d9a-abf4-779c304d3932","resolution":{"observed_at":"2026-08-14T11:17:08.373346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T11:17:08.348620Z","title":"Visual tracking using attention- modulated disintegration and integration,","venue":null,"work_id":"37a85978-54e9-4a92-b9a3-82e4c47e997d","year":2016},"citing_paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-14T11:17:08.029962Z"},"links":{"citing_paper":"/paper/1908.09445"},"observation_digest":"sha256:778a089aee25d8f60b30a56f4aeecc7c45275236d4bd1e9a0073f775e48f4aa0","observation_id":"8fa5bb61-502f-4c70-9749-888e50f4bb9d","resolution":{"observed_at":"2026-08-14T11:17:08.355127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.09445","last_updated":"2019-08-26T03:09:03Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-16T09:01:56.928923Z","submitted_at":"2019-08-26T03:09:03Z","title":"High Performance Visual Object Tracking with Unified Convolutional Networks"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":7,"verified_fuzzy":59},"total_outbound_references":74},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 0 inbound Pith citation observations for arXiv:1908.09445."}