{"as_of":"2026-08-23T21:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:45b40f24a92f0d8460b8f1fe5144865e6b099db7cadef6295a3bdbf3a871f610","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:10:40.798195Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2507.18921/citation-record","integrity":"/paper/2507.18921/integrity","json":"/paper/2507.18921/citation-record.json","paper":"/paper/2507.18921"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:10:41.412505Z","title":"XMem++: Production-level video segmenta- tion from few annotated frames","venue":null,"work_id":"f5a671b4-72c6-48df-ab4b-1144b1a10d9c","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.588341Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:4f63aae60ad2b5e612fbffaec5318bddca468bb7be1cc92022d77d55b2ef5289","observation_id":"36d7a5c3-cc75-486d-a931-f8b24e1f5360","resolution":{"observed_at":"2026-08-15T18:10:41.416861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.399336Z","title":"Object segmentation by long term analysis of point trajectories","venue":null,"work_id":"6bae03af-a8dc-4833-b906-3d284845a49e","year":2010},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.592922Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:479cf53f26b08c9fe053a8212a6d109973619b5784d352aed59b047038e3e64c","observation_id":"ffc90e0c-f9ca-4d50-99cc-c79a12a78eb8","resolution":{"observed_at":"2026-08-15T18:10:41.403780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.387097Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":"52314ab4-bb16-48ad-a3d0-8a3d79f27be3","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.596995Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:c47eb2d778754639b2c8b110437bccea93c4d9ac2a51a8f97daf2aab8dd56e69","observation_id":"d2cf1d0a-afbe-4127-8bf6-09c13007c728","resolution":{"observed_at":"2026-08-15T18:10:41.390989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.374987Z","title":"XMem: long-term video object segmentation with an Atkinson-Shiffrin mem- ory model","venue":null,"work_id":"10c810e2-a83e-4fd1-b35c-f3f2cdceb572","year":2022},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.601020Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:cd8503117cc832e4d0d2fa1cfdd64a640178007e57fdba19965f339d002e3fe2","observation_id":"c1780c51-7afd-4840-8619-03c1db2431ab","resolution":{"observed_at":"2026-08-15T18:10:41.379105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.363324Z","title":"Modular interactive video object segmentation: Interaction-to-mask, propagation and difference-aware fusion","venue":null,"work_id":"203659aa-0b98-49d5-bbd8-b8e9d6009c2b","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.605852Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:59482524a01f9d54556806a42922f5de9366bcaa7ff16873d7fb797242cbd296","observation_id":"9aeacfc9-6c40-48b8-a3d1-1b28f23e3eeb","resolution":{"observed_at":"2026-08-15T18:10:41.367761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.350956Z","title":"Rethink- ing space-time networks with improved memory coverage for efficient video object segmentation","venue":null,"work_id":"68d5c3fc-8f00-4d1a-9d15-fc0813648edc","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.611394Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:ff5e604e49e976ba135405d23bef8a75330b243c1190db0795b34bcb883109dd","observation_id":"6fc6d2a2-c4ac-4c5d-b836-56d7bf5fde51","resolution":{"observed_at":"2026-08-15T18:10:41.355500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.336714Z","title":"Putting the object back into video object segmentation","venue":null,"work_id":"ebd5207d-8d3f-408d-b307-292cde7c07ac","year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.615805Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:53bc5b69d6bb672b10e5e6a8b8518ba41270f2f28ae802a9e13a626d44aef56b","observation_id":"0786f55a-ec9a-4b86-99bd-81cca337d3b3","resolution":{"observed_at":"2026-08-15T18:10:41.342378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-15T18:10:40.620220Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.620220Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:1829083447e138a39de3a4e9086a775731fad203b95daed5b222e11fb0f81720","observation_id":"267d0047-749b-40ad-979f-c581f8c44d02","resolution":{"observed_at":"2026-08-15T18:10:40.620220Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:10:40.623982Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.623982Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:20473cbdd6edb2afa298909594b3b0fbf05226c837963d5b26c933d909760335","observation_id":"234e5f86-78f8-45c8-9987-b865754d9182","resolution":{"observed_at":"2026-08-15T18:10:40.623982Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:10:40.627856Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.627856Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:3045083d0d502b8c59919a01dcc3a02e6be20cbf29bfaba186b939740adeda9e","observation_id":"5f3caaae-6d31-46cb-82b5-5294e1213aef","resolution":{"observed_at":"2026-08-15T18:10:40.627856Z","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":"2026-08-15T18:10:41.310691Z","title":"Lvos: A benchmark for long-term video object segmentation","venue":null,"work_id":"07f0110c-1f67-4985-b3ec-6282a1900c81","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.631867Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:31a20840c71c6dd7a3407ee1c668c2405602aae13a32f5e01265ce6d6a824455","observation_id":"5022a0da-0986-4cec-a4f7-1550058d69f9","resolution":{"observed_at":"2026-08-15T18:10:41.314917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.299911Z","title":"Determining opti- cal flow","venue":null,"work_id":"9c27406d-f2cb-44e5-8864-29a5d11602a0","year":1981},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.636320Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:07b0fdbc3a0f659208508379d7a39ffabd72e898b66817b3a070780c8d57168e","observation_id":"68358438-16d1-4ec7-bc6f-3e5ed12bbe0a","resolution":{"observed_at":"2026-08-15T18:10:41.303758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.288140Z","title":"Segment anything in high quality","venue":null,"work_id":"1bce7223-d1ba-4a9b-8b5f-b7dc693e38ee","year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.641120Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:8983bc300cb04f0782a77ebd600e518d3b57f9bf1ebe7e2f0cc5e125101f204a","observation_id":"9bd13a79-c511-48ee-858a-281a44f7f593","resolution":{"observed_at":"2026-08-15T18:10:41.292165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.276768Z","title":"Segment any- thing","venue":null,"work_id":"78a8ae47-aefa-4a7c-9c10-da47291e4333","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.645014Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:307bbb5291f74f18f50a7e37b188d2c125af579669ad45dacfeeadec688651f4","observation_id":"dd9cb13e-da39-4914-9466-dfa89ab869b2","resolution":{"observed_at":"2026-08-15T18:10:41.280812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.265602Z","title":"The first visual object tracking segmentation vots2023 chal- lenge results","venue":null,"work_id":"6085053d-fe83-4377-af15-5f914e7e87d3","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.649273Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:2226d707179f950a342e697914941eeb57d93950b861790abcd33a59973bf855","observation_id":"cee4ab2c-36f7-4bba-b1b1-f86087428fd9","resolution":{"observed_at":"2026-08-15T18:10:41.269963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.253176Z","title":"The second visual object tracking seg- mentation vots2024 challenge results, 2024","venue":null,"work_id":"2a90ecee-47e2-4870-ab08-12056a04cf9c","year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.652856Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:f8fdf4867b957edfc178dad6b63f2d3d26807d2bbb68666099010aede320630a","observation_id":"27048a54-5fa7-416e-a5d1-af9ab8ed3505","resolution":{"observed_at":"2026-08-15T18:10:41.257329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.241259Z","title":null,"venue":null,"work_id":"1c1474f3-8cf2-4982-9b6a-05216066f855","year":2013},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.657406Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:fddb878157037f4645946be76ad59828a42584751f7290c9819258d34cf6fbec","observation_id":"4b88ce5d-e351-44f0-821c-6762ccc40b6e","resolution":{"observed_at":"2026-08-15T18:10:41.245463Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.229319Z","title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","venue":null,"work_id":"f6dccb08-98c3-49ef-89ae-89977c4d210a","year":2020},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.661866Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:45e28071d24e4dc294c9b80edb9a70edad1359448e86d161ed36f230578be6d9","observation_id":"e00d6614-c949-48ff-941b-4f56775451b3","resolution":{"observed_at":"2026-08-15T18:10:41.233730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.216007Z","title":"Follow anything: Open- set detection, tracking, and following in real-time","venue":null,"work_id":"65f6b9f9-497c-48bf-841a-5339e17c2e1d","year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.665747Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:842a8c09c9fd7297a1af4af6a972e688cd478b1049b96918b8c927cc203494a1","observation_id":"e2f3e31d-c3bf-4275-b76a-cda0f994e062","resolution":{"observed_at":"2026-08-15T18:10:41.220091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.203173Z","title":"Background sub- traction in highly dynamic scenes","venue":null,"work_id":"e356f056-9f18-4bf2-aa2b-9fd2733b01a6","year":2008},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.671835Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:ff418061978eb94134c740c9cd0d5b257fe6c2b78658fad351f58eaa194501cf","observation_id":"5ac64a01-8591-4f8a-b019-982faa1d11db","resolution":{"observed_at":"2026-08-15T18:10:41.207786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.190892Z","title":"The cell tracking challenge: 10 years of objective benchmarking","venue":null,"work_id":"25a16c8f-10d9-4da8-a697-20296d3af256","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.675885Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:3102e4855dd9db6541e8a989bfc16142eb128b6fb20f279b36d4f1d3bbdc9ff4","observation_id":"092f9312-86f3-4e78-879a-2c6fbb9898e2","resolution":{"observed_at":"2026-08-15T18:10:41.195307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.177352Z","title":"Video object segmentation using space-time memory networks","venue":null,"work_id":"cec065aa-5e3a-447a-a872-66d9182a8376","year":2019},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.679695Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:e69b558b29299c75e28615d4ea6fa0b17dd356e26b3e81aef7462a849f03f090","observation_id":"7ba2a628-8d3b-474b-ae08-fb3f38f8be5c","resolution":{"observed_at":"2026-08-15T18:10:41.182180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.164963Z","title":"Perazzi, J","venue":null,"work_id":"9ccdd05d-6535-4fda-afcd-46e1ccb26527","year":2016},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.684289Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:26f4c5ce3a52195b1a2b5630c28d208f561c921565c3bfc03ed9c2a62319a8eb","observation_id":"2ee28fbe-965d-4949-84ca-889908577f50","resolution":{"observed_at":"2026-08-15T18:10:41.169133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.00675","last_updated":"2018-03-01T17:50:08Z","snapshot_observed_at":"2026-08-02T10:51:13.194643Z","submitted_at":"2017-04-03T16:44:46Z","title":"The 2017 DAVIS Challenge on Video Object Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.00675","snapshot_observed_at":"2026-08-15T18:10:40.692765Z","title":"The 2017 davis challenge on video object segmentation.arXiv preprint arXiv:1704.00675, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.692765Z"},"links":{"cited_paper":"/paper/1704.00675","citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:8f093e030a77b6b94a53756ea613520bdf3dd58c49e0365b21e9e2dc27a60974","observation_id":"d7af0672-b879-4dfd-a55b-bebf9f27d9fb","resolution":{"observed_at":"2026-08-15T18:10:40.692765Z","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":"2026-08-15T18:10:41.152305Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"46371618-7ab8-458c-88c2-92c89d0723be","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.697095Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:8e0089d3bce9ac995eb30e6c35660fd8efe61f4d0f1a91077209e20d7067b5a3","observation_id":"1ab1cc05-d04f-43f1-9e8c-142f1bea1eb6","resolution":{"observed_at":"2026-08-15T18:10:41.156580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.140100Z","title":"Deepftsg: Multi-stream asymmetric use-net trellis en- coders with shared decoder feature fusion architecture for video motion segmentation","venue":null,"work_id":"30d76f58-b4c0-4d49-8816-440f100a1009","year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.700913Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:592031013d1760e6020775cdfbe806c2bcac38251c08331361407c8e93c4d0e6","observation_id":"1502749d-2dff-4f00-b8d5-391f930deba7","resolution":{"observed_at":"2026-08-15T18:10:41.144283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00714","last_updated":"2024-10-28T16:37:57Z","snapshot_observed_at":"2026-07-06T18:55:41.459417Z","submitted_at":"2024-08-01T17:00:08Z","title":"SAM 2: Segment Anything in Images and Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00714","snapshot_observed_at":"2026-08-15T18:10:40.705706Z","title":"Sam 2: Segment anything in images and videos","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.705706Z"},"links":{"cited_paper":"/paper/2408.00714","citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:da9cfc644994a098133192a4d439dad06df093a63593696ee7e3fab599e2df49","observation_id":"f034651f-dedf-4aa0-8d76-2ec8c33bdd3f","resolution":{"observed_at":"2026-08-15T18:10:40.705706Z","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":"2026-08-15T18:10:41.127377Z","title":"Learning fast and robust target models for video object segmentation","venue":null,"work_id":"29bf6844-8115-4bdc-9159-6e09d6bd5f45","year":2020},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.709920Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:c535dd1b9d47c2c6f411f607de117dfd3b01d5fc87c53c1855806c62604d9b2c","observation_id":"59a77b76-8e22-4941-a670-0eab17b33e22","resolution":{"observed_at":"2026-08-15T18:10:41.131994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.713812Z","title":"U- net: Convolutional networks for biomedical image segmen- tation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.713812Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:42a18c79a89dc45223876746d525fd723ec55d0ae12d0f060cc4cf2a14e216c9","observation_id":"549f36f5-d17b-4a32-adf2-1c568e393ca5","resolution":{"observed_at":"2026-08-15T18:10:40.713812Z","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":"2026-08-15T18:10:41.107447Z","title":"A practical adap- tive approach for dynamic background subtraction using an invariant colour model and object tracking","venue":null,"work_id":"9e693e24-a9e2-44f1-920f-6ee42ed2d631","year":2005},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.717666Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:2d7677e566241381b61a6e167f4ec7e10f7af2b28dac79fcc8fc1dde31655a7c","observation_id":"950904d4-c631-4ec2-8eff-7be5c2461a38","resolution":{"observed_at":"2026-08-15T18:10:41.111284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.095236Z","title":"Video class agnostic segmentation benchmark for au- tonomous driving","venue":null,"work_id":"5079f6a5-66b4-4600-b18c-29836249c191","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.721679Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:e4a018a09a33ba92951f5c7d664aded5d579229f413d986d9d3f044e66432c0a","observation_id":"a7514384-4f61-4ba1-b5b7-0b92090efcaa","resolution":{"observed_at":"2026-08-15T18:10:41.099242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.083315Z","title":"Breaking the” object” in video object segmentation","venue":null,"work_id":"e405b38b-fc27-4397-a522-810550aab6f8","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.725290Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:995ade74809a5bb2693c8bbd2284d55d2e7ccd596665e08736bfcb278a70692a","observation_id":"486a087d-8e43-414f-b4ee-e9fe54574702","resolution":{"observed_at":"2026-08-15T18:10:41.087274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.069630Z","title":"Ensemble deep learning object detection fusion for cell tracking, mitosis, and lineage","venue":null,"work_id":"dd2f7403-7ecc-454e-8dc2-9f403c2498da","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.729298Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:4c820b8b9c45475d1f1f10cecb79f449029c205941909ce4407cca73ef997396","observation_id":"757bc660-b4fb-4fd8-bc7e-0dd96de309e5","resolution":{"observed_at":"2026-08-15T18:10:41.075266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.056993Z","title":"Dino-tracker: Taming dino for self-supervised point track- ing in a single video","venue":null,"work_id":"f6a5d9f1-ca77-4851-82dd-075fb601ce76","year":2025},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.733024Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:86fdb3d7645198e533bc70eea97623f8db707d38d35921d6099d6a060e39f853","observation_id":"43433bec-1f7a-441a-99d1-064e945f299c","resolution":{"observed_at":"2026-08-15T18:10:41.061046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.736710Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.736710Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:c1cbc8574bb4a511c7561746c93b1dd70e3c935b2b480c523e6261b28140b9ce","observation_id":"e034f397-f695-4828-8206-d12b2eca23cd","resolution":{"observed_at":"2026-08-15T18:10:40.736710Z","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":"2026-08-15T18:10:41.036028Z","title":"A Comprehensive Review of Modern Object Segmenta- tion Approaches","venue":null,"work_id":"7d5cc34e-51f0-4a75-9cdc-99c3fee44c8e","year":2022},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.741252Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:0383ed25f8eef7d3962c8c309de574bfccc975cf7826bfa0264aad37d1d1c655","observation_id":"7b58fd39-e3f7-4dcc-9243-4e57a2354fb6","resolution":{"observed_at":"2026-08-15T18:10:41.039957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.024642Z","title":"A learning algorithm for continually running fully recurrent neural networks.Neu- ral computation, 1(2):270–280, 1989","venue":null,"work_id":"3b6a0c62-1283-466a-9878-d34225365b80","year":1989},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.745116Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:d91aeebb0cfee8017c261e6afc99e4f9a8517ca23d40e4a8661c3fc7aa7ad427","observation_id":"355a0d63-8477-4310-9000-88edd5cfa801","resolution":{"observed_at":"2026-08-15T18:10:41.028468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:41.011319Z","title":null,"venue":null,"work_id":"6a72c1bb-7bab-4cd7-89af-1d32cb5b851c","year":null},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.749088Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:3b84af23b91b05e841698fe934457568b77b131c1fb143ecf99106d3f74e656f","observation_id":"77a4e5bf-1112-4a5f-913a-6db58e66a78c","resolution":{"observed_at":"2026-08-15T18:10:41.015338Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.997573Z","title":"Youtube-vos: Sequence-to-sequence video object segmentation","venue":null,"work_id":"7d670c68-fc2c-4975-bb62-8e613a2d4112","year":2018},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.753131Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:9bb29acb0d06b118979b9cb33c20356c4e2279f14e8e4741b877a24b7febfd69","observation_id":"1acaa5a2-c393-4d65-a436-b347a28e7453","resolution":{"observed_at":"2026-08-15T18:10:41.002560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.03327","last_updated":"2018-09-06T04:19:45Z","snapshot_observed_at":"2026-08-20T04:50:05.503590Z","submitted_at":"2018-09-06T04:19:45Z","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.03327","snapshot_observed_at":"2026-08-15T18:10:40.757116Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.757116Z"},"links":{"cited_paper":"/paper/1809.03327","citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:5cec3e9fbab31d9d8c576f0793e3d350dfc4697a870a990ec130b76d80f7e453","observation_id":"d2a9b1b2-7958-4543-9971-e5ca7a1c86c1","resolution":{"observed_at":"2026-08-15T18:10:40.757116Z","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":"2026-08-15T18:10:40.984894Z","title":"Learning spatio-temporal transformer for vi- sual tracking","venue":null,"work_id":"3cb68429-eb95-4a1a-88fd-a18733bfbacf","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.761072Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:f5ac74d9db6467a710ca6295923a50bc91dbd7a5dc9df7e7303206ba2fcc9f7d","observation_id":"200a9815-7b1e-482c-a52a-4e016257f932","resolution":{"observed_at":"2026-08-15T18:10:40.989038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.973012Z","title":"Decoupling features in hierar- chical propagation for video object segmentation","venue":null,"work_id":"24934287-53a1-4264-940c-b5b36861a3a0","year":2022},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.764783Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:e79cb11628439d761b4452595d990b620a78c8ab39b71296d341505734a257c4","observation_id":"d6c1bb3b-1986-4f67-9709-dce2cd0b0cbf","resolution":{"observed_at":"2026-08-15T18:10:40.977510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.960480Z","title":"Collaborative video object segmentation by foreground-background inte- gration","venue":null,"work_id":"b490bef7-cfb1-4be9-bab9-a82abd9c162f","year":2020},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.768589Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:f8a3e3aa5e66e152e3bae2b199dc58e828221b984e1596065ecf1796d9151bc3","observation_id":"3d90cb1c-0f46-474a-bc5e-32e7cdc4cc26","resolution":{"observed_at":"2026-08-15T18:10:40.964782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.947881Z","title":"Associating ob- jects with transformers for video object segmentation","venue":null,"work_id":"621c7358-6f15-47d1-a985-06cee0527066","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.773072Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:172279982487246011c9b563c1fa6fa9946db68c5d3e610d2cafff970be4095c","observation_id":"91bceb3e-a575-4ec4-8fd0-c15aadc82f6c","resolution":{"observed_at":"2026-08-15T18:10:40.952298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.934767Z","title":"Collabora- tive video object segmentation by multi-scale foreground- background integration","venue":null,"work_id":"db5452c2-e3a3-465f-949e-c059a8e604e6","year":2021},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.778268Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:33f8c2f9b32cfd4d04a9ad46717a528f5b88ff721b93d9b724114ab3abb2f17b","observation_id":"ecf0b8cc-4b54-4ac0-96fe-c5284f412b73","resolution":{"observed_at":"2026-08-15T18:10:40.938828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.922980Z","title":"Scalable video object segmen- tation with identification mechanism","venue":null,"work_id":"f4112554-63de-40e0-8890-6a853ddac3a0","year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.781843Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:f0d6104a9c53f4712f853a64c437a7c4c95f324166c71d5df536764f91ca05a0","observation_id":"3da5e763-88a1-4424-b806-92ec432ed737","resolution":{"observed_at":"2026-08-15T18:10:40.927171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.908492Z","title":"Joint feature learning and relation modeling for tracking: A one-stream framework","venue":null,"work_id":"13c3ab71-c987-4b58-8677-b9a040f05df1","year":2022},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.785517Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:c9d0634cdffb9aa964b4496489d53ed3171a84aa589bd3b6333c1464bb1d38dc","observation_id":"6360d43b-1d38-4ec4-9ec9-42dab251595d","resolution":{"observed_at":"2026-08-15T18:10:40.913719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-16T07:54:28.918946Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-15T18:10:40.789908Z","title":"Wide residual net- works","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.789908Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:66399562150d1f20c9ff311ad876e265f20eb15aa9cadeaa3cce328fa43a7414","observation_id":"ab1a807d-fc92-45f3-ba16-dad2d30e2154","resolution":{"observed_at":"2026-08-15T18:10:40.789908Z","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":"2026-08-15T18:10:40.896833Z","title":"RMem: Re- stricted Memory Banks Improve Video Object Segmentation","venue":null,"work_id":"be5e8268-1540-4b7f-84b7-4de4b5bb8204","year":2024},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.794407Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:53570b74079bf14f05dcd1abbb1c47e4a93e05af4e87ac39fd4fa5eef34201b3","observation_id":"ecd846c8-a482-4324-adc5-e97be01a5907","resolution":{"observed_at":"2026-08-15T18:10:40.900556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:10:40.882788Z","title":"Tracking anything in high quality, 2023","venue":null,"work_id":"5018268e-2c9a-46de-b65a-c857754861f9","year":2023},"citing_paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T18:10:40.798195Z"},"links":{"citing_paper":"/paper/2507.18921"},"observation_digest":"sha256:1bc989b2830f683b2bcc7956c615f4185beafc63f9135c27c20e43b403bad453","observation_id":"bf46cf98-5acc-43b6-ad38-1ba39913a79d","resolution":{"observed_at":"2026-08-15T18:10:40.888660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.18921","last_updated":"2025-07-25T03:28:05Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T04:50:44.477553Z","submitted_at":"2025-07-25T03:28:05Z","title":"HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":39},"total_outbound_references":50},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2507.18921."}