{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:K7OUF65PY7YVG2M4UT5P54G67X","short_pith_number":"pith:K7OUF65P","schema_version":"1.0","canonical_sha256":"57dd42fbafc7f153699ca4fafef0defdd9d7bb011f45e458d9985f32adb25357","source":{"kind":"arxiv","id":"1904.11451","version":3},"attestation_state":"computed","paper":{"title":"Large Scale Holistic Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Diba, Jurgen Gall, Luc Van Gool, Manohar Paluri, Mohsen Fayyaz, Rainer Stiefelhagen, Vivek Sharma","submitted_at":"2019-04-25T16:49:13Z","abstract_excerpt":"Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing on a highly specific video understanding task and thus leaving a significant gap towards describing the overall content of a video. We fill this gap by presenting a large-scale \"Holistic Video Understanding Dataset\"~(HVU). HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semanti"},"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":"1904.11451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-25T16:49:13Z","cross_cats_sorted":[],"title_canon_sha256":"b80fbf3adfb225f8d1d0abe52b7c979ad80ee0be3209f106bc516a92456ae153","abstract_canon_sha256":"1a544c262aa88bd0a8c36e5f76f63a40651f76565b0ceac7fd08cc731dc8b5b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:25.794555Z","signature_b64":"3hhwYP9vkyAzT2uckrgdHx4w3/vPf1gCEwxMoSt3Z76TiA+Qfmy6YgeV3WwVgbHMTQQZZjUUcuX/faNbVtFfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57dd42fbafc7f153699ca4fafef0defdd9d7bb011f45e458d9985f32adb25357","last_reissued_at":"2026-07-05T01:59:25.794129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:25.794129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Scale Holistic Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Diba, Jurgen Gall, Luc Van Gool, Manohar Paluri, Mohsen Fayyaz, Rainer Stiefelhagen, Vivek Sharma","submitted_at":"2019-04-25T16:49:13Z","abstract_excerpt":"Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing on a highly specific video understanding task and thus leaving a significant gap towards describing the overall content of a video. We fill this gap by presenting a large-scale \"Holistic Video Understanding Dataset\"~(HVU). HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11451","kind":"arxiv","version":3},"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/1904.11451/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":"1904.11451","created_at":"2026-07-05T01:59:25.794193+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11451v3","created_at":"2026-07-05T01:59:25.794193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11451","created_at":"2026-07-05T01:59:25.794193+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7OUF65PY7YV","created_at":"2026-07-05T01:59:25.794193+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7OUF65PY7YVG2M4","created_at":"2026-07-05T01:59:25.794193+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7OUF65P","created_at":"2026-07-05T01:59:25.794193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20838","citing_title":"USV: Towards Understanding the User-generated Short-form Videos","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X","json":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X.json","graph_json":"https://pith.science/api/pith-number/K7OUF65PY7YVG2M4UT5P54G67X/graph.json","events_json":"https://pith.science/api/pith-number/K7OUF65PY7YVG2M4UT5P54G67X/events.json","paper":"https://pith.science/paper/K7OUF65P"},"agent_actions":{"view_html":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X","download_json":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X.json","view_paper":"https://pith.science/paper/K7OUF65P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11451&json=true","fetch_graph":"https://pith.science/api/pith-number/K7OUF65PY7YVG2M4UT5P54G67X/graph.json","fetch_events":"https://pith.science/api/pith-number/K7OUF65PY7YVG2M4UT5P54G67X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X/action/storage_attestation","attest_author":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X/action/author_attestation","sign_citation":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X/action/citation_signature","submit_replication":"https://pith.science/pith/K7OUF65PY7YVG2M4UT5P54G67X/action/replication_record"}},"created_at":"2026-07-05T01:59:25.794193+00:00","updated_at":"2026-07-05T01:59:25.794193+00:00"}