{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SOEYGFE56ZWZBE6AOWAZ3CNEOT","short_pith_number":"pith:SOEYGFE5","schema_version":"1.0","canonical_sha256":"938983149df66d9093c075819d89a474d6fe83868fdb6e0bf037128959a9dcd4","source":{"kind":"arxiv","id":"2005.00214","version":2},"attestation_state":"computed","paper":{"title":"The AVA-Kinetics Localized Human Actions Video Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexander Vostrikov, Andrew Zisserman, Ang Li, David A. Ross, Jo\\~ao Carreira, Meghana Thotakuri","submitted_at":"2020-05-01T04:17:14Z","abstract_excerpt":"This paper describes the AVA-Kinetics localized human actions video dataset. The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these new AVA annotated Kinetics clips. The dataset contains over 230k clips annotated with the 80 AVA action classes for each of the humans in key-frames. We describe the annotation process and provide statistics about the new dataset. We also include a baseline evaluation using the Video Action Transformer Network on the AVA-Kinetics dataset, demonstrating improve"},"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":"2005.00214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-01T04:17:14Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"94b7e69b0114756e5469c5758fb258cf60b14e520bfc99cc73960fbf08ae9b26","abstract_canon_sha256":"e3d8ed43fd8675b48e0dec6784512d3fe110c068a6c3daddb5893335aad0f0f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:04:42.773008Z","signature_b64":"v8ZDKGWxOKaxsDleDBSIRglZxGx5sc0/tnQAnbRcP08zEXVGOA3+Y4QnswVCp6LMYgYSxSQpjjLTmG1sClFZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"938983149df66d9093c075819d89a474d6fe83868fdb6e0bf037128959a9dcd4","last_reissued_at":"2026-07-05T01:04:42.772534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:04:42.772534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The AVA-Kinetics Localized Human Actions Video Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexander Vostrikov, Andrew Zisserman, Ang Li, David A. Ross, Jo\\~ao Carreira, Meghana Thotakuri","submitted_at":"2020-05-01T04:17:14Z","abstract_excerpt":"This paper describes the AVA-Kinetics localized human actions video dataset. The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these new AVA annotated Kinetics clips. The dataset contains over 230k clips annotated with the 80 AVA action classes for each of the humans in key-frames. We describe the annotation process and provide statistics about the new dataset. We also include a baseline evaluation using the Video Action Transformer Network on the AVA-Kinetics dataset, demonstrating improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00214","kind":"arxiv","version":2},"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/2005.00214/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":"2005.00214","created_at":"2026-07-05T01:04:42.772591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00214v2","created_at":"2026-07-05T01:04:42.772591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00214","created_at":"2026-07-05T01:04:42.772591+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOEYGFE56ZWZ","created_at":"2026-07-05T01:04:42.772591+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOEYGFE56ZWZBE6A","created_at":"2026-07-05T01:04:42.772591+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOEYGFE5","created_at":"2026-07-05T01:04:42.772591+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31187","citing_title":"Learning to Deny: Action Denial in Multimodal Large Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2407.08101","citing_title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2212.03191","citing_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT","json":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT.json","graph_json":"https://pith.science/api/pith-number/SOEYGFE56ZWZBE6AOWAZ3CNEOT/graph.json","events_json":"https://pith.science/api/pith-number/SOEYGFE56ZWZBE6AOWAZ3CNEOT/events.json","paper":"https://pith.science/paper/SOEYGFE5"},"agent_actions":{"view_html":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT","download_json":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT.json","view_paper":"https://pith.science/paper/SOEYGFE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00214&json=true","fetch_graph":"https://pith.science/api/pith-number/SOEYGFE56ZWZBE6AOWAZ3CNEOT/graph.json","fetch_events":"https://pith.science/api/pith-number/SOEYGFE56ZWZBE6AOWAZ3CNEOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT/action/storage_attestation","attest_author":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT/action/author_attestation","sign_citation":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT/action/citation_signature","submit_replication":"https://pith.science/pith/SOEYGFE56ZWZBE6AOWAZ3CNEOT/action/replication_record"}},"created_at":"2026-07-05T01:04:42.772591+00:00","updated_at":"2026-07-05T01:04:42.772591+00:00"}