{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ANDOBAP6WTV2LRB3FKKN4KKGMU","short_pith_number":"pith:ANDOBAP6","schema_version":"1.0","canonical_sha256":"0346e081feb4eba5c43b2a94de2946650620e05e722fc091332c458dabffa8f2","source":{"kind":"arxiv","id":"1705.08421","version":4},"attestation_state":"computed","paper":{"title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carl Vondrick, Caroline Pantofaru, Chen Sun, Chunhui Gu, Cordelia Schmid, David A. Ross, George Toderici, Jitendra Malik, Rahul Sukthankar, Sudheendra Vijayanarasimhan, Susanna Ricco, Yeqing Li","submitted_at":"2017-05-23T17:11:46Z","abstract_excerpt":"This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute vi"},"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":"1705.08421","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-23T17:11:46Z","cross_cats_sorted":[],"title_canon_sha256":"655b8059b336d3dee05032048acf35ffd8fe6a2abefe260c6a81aaf2a21eef1c","abstract_canon_sha256":"aa85339a0e04df3e1f905595104fdb85682f03a25986ca092cbd7a82875f3122"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:19.358332Z","signature_b64":"nmba+AxhNlJ3t6YPDKD0RggJ1/fON9advZ6WZJVSemUX/0oxFJX7Upsp77uBBib9Lei1v0puAB1CrN+9PBkcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0346e081feb4eba5c43b2a94de2946650620e05e722fc091332c458dabffa8f2","last_reissued_at":"2026-05-18T00:17:19.357679Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:19.357679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carl Vondrick, Caroline Pantofaru, Chen Sun, Chunhui Gu, Cordelia Schmid, David A. Ross, George Toderici, Jitendra Malik, Rahul Sukthankar, Sudheendra Vijayanarasimhan, Susanna Ricco, Yeqing Li","submitted_at":"2017-05-23T17:11:46Z","abstract_excerpt":"This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08421","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1705.08421","created_at":"2026-05-18T00:17:19.357771+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08421v4","created_at":"2026-05-18T00:17:19.357771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08421","created_at":"2026-05-18T00:17:19.357771+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANDOBAP6WTV2","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANDOBAP6WTV2LRB3","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANDOBAP6","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.13484","citing_title":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU","json":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU.json","graph_json":"https://pith.science/api/pith-number/ANDOBAP6WTV2LRB3FKKN4KKGMU/graph.json","events_json":"https://pith.science/api/pith-number/ANDOBAP6WTV2LRB3FKKN4KKGMU/events.json","paper":"https://pith.science/paper/ANDOBAP6"},"agent_actions":{"view_html":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU","download_json":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU.json","view_paper":"https://pith.science/paper/ANDOBAP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08421&json=true","fetch_graph":"https://pith.science/api/pith-number/ANDOBAP6WTV2LRB3FKKN4KKGMU/graph.json","fetch_events":"https://pith.science/api/pith-number/ANDOBAP6WTV2LRB3FKKN4KKGMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU/action/storage_attestation","attest_author":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU/action/author_attestation","sign_citation":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU/action/citation_signature","submit_replication":"https://pith.science/pith/ANDOBAP6WTV2LRB3FKKN4KKGMU/action/replication_record"}},"created_at":"2026-05-18T00:17:19.357771+00:00","updated_at":"2026-05-18T00:17:19.357771+00:00"}