{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LFXRB7TCCMJ2YQBYUP5COBDX3F","short_pith_number":"pith:LFXRB7TC","schema_version":"1.0","canonical_sha256":"596f10fe621313ac4038a3fa270477d96ef276cd8e889d400b40a6b4e683ec22","source":{"kind":"arxiv","id":"2012.06567","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Study of Deep Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chongruo Wu, Chunhui Liu, Joseph Tighe, Mohammadreza Zolfaghari, Mu Li, R. Manmatha, Xinyu Li, Yi Zhu, Yuanjun Xiong, Zhi Zhang","submitted_at":"2020-12-11T18:54:08Z","abstract_excerpt":"Video action recognition is one of the representative tasks for video understanding. Over the last decade, we have witnessed great advancements in video action recognition thanks to the emergence of deep learning. But we also encountered new challenges, including modeling long-range temporal information in videos, high computation costs, and incomparable results due to datasets and evaluation protocol variances. In this paper, we provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition. We first introduce the 17 video action recognition datasets "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2012.06567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-11T18:54:08Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"114abf0ad1c148ab00422f4602ce087b35f8be1a29d6497680644d38c1c370b7","abstract_canon_sha256":"a3c6feb206bb0a7974b65d5d003925a5500fd333bb34e55d4bb08e373c52ef3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:53.015451Z","signature_b64":"H8fI8BjXoQqfEC9YVdcd/tB8kouP9Y5JQLD598Nq9ufiO9vAg9VMt9CsOQOgkdRGlnF7JD36iRoV1SpeYfLyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"596f10fe621313ac4038a3fa270477d96ef276cd8e889d400b40a6b4e683ec22","last_reissued_at":"2026-07-05T01:58:53.014962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:53.014962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Study of Deep Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chongruo Wu, Chunhui Liu, Joseph Tighe, Mohammadreza Zolfaghari, Mu Li, R. Manmatha, Xinyu Li, Yi Zhu, Yuanjun Xiong, Zhi Zhang","submitted_at":"2020-12-11T18:54:08Z","abstract_excerpt":"Video action recognition is one of the representative tasks for video understanding. Over the last decade, we have witnessed great advancements in video action recognition thanks to the emergence of deep learning. But we also encountered new challenges, including modeling long-range temporal information in videos, high computation costs, and incomparable results due to datasets and evaluation protocol variances. In this paper, we provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition. We first introduce the 17 video action recognition datasets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06567","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.06567/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2012.06567","created_at":"2026-07-05T01:58:53.015028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06567v1","created_at":"2026-07-05T01:58:53.015028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06567","created_at":"2026-07-05T01:58:53.015028+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFXRB7TCCMJ2","created_at":"2026-07-05T01:58:53.015028+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFXRB7TCCMJ2YQBY","created_at":"2026-07-05T01:58:53.015028+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFXRB7TC","created_at":"2026-07-05T01:58:53.015028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27777","citing_title":"TRUST: Efficient Abdominal Trauma Recognition via Image-to-Ultrasound-Video Transfer Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2410.18717","citing_title":"Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy Versus Performance","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15578","citing_title":"AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and Reasoning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F","json":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F.json","graph_json":"https://pith.science/api/pith-number/LFXRB7TCCMJ2YQBYUP5COBDX3F/graph.json","events_json":"https://pith.science/api/pith-number/LFXRB7TCCMJ2YQBYUP5COBDX3F/events.json","paper":"https://pith.science/paper/LFXRB7TC"},"agent_actions":{"view_html":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F","download_json":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F.json","view_paper":"https://pith.science/paper/LFXRB7TC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06567&json=true","fetch_graph":"https://pith.science/api/pith-number/LFXRB7TCCMJ2YQBYUP5COBDX3F/graph.json","fetch_events":"https://pith.science/api/pith-number/LFXRB7TCCMJ2YQBYUP5COBDX3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F/action/storage_attestation","attest_author":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F/action/author_attestation","sign_citation":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F/action/citation_signature","submit_replication":"https://pith.science/pith/LFXRB7TCCMJ2YQBYUP5COBDX3F/action/replication_record"}},"created_at":"2026-07-05T01:58:53.015028+00:00","updated_at":"2026-07-05T01:58:53.015028+00:00"}