{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AFPQFCGKVOPTVUSEMETFVGCSNX","short_pith_number":"pith:AFPQFCGK","schema_version":"1.0","canonical_sha256":"015f0288caab9f3ad24461265a98526dc972b06f5d3646e6d0475e29f4e44f93","source":{"kind":"arxiv","id":"1905.05143","version":2},"attestation_state":"computed","paper":{"title":"VideoGraph: Recognizing Minutes-Long Human Activities in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnold W.M. Smeulders, Efstratios Gavves, Noureldien Hussein","submitted_at":"2019-05-13T16:57:40Z","abstract_excerpt":"Many human activities take minutes to unfold. To represent them, related works opt for statistical pooling, which neglects the temporal structure. Others opt for convolutional methods, as CNN and Non-Local. While successful in learning temporal concepts, they are short of modeling minutes-long temporal dependencies. We propose VideoGraph, a method to achieve the best of two worlds: represent minutes-long human activities and learn their underlying temporal structure. VideoGraph learns a graph-based representation for human activities. The graph, its nodes and edges are learned entirely from 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":"1905.05143","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-13T16:57:40Z","cross_cats_sorted":[],"title_canon_sha256":"7b5e719b2cc82d0f282ae86118b712c8d4a4b9d60aff5aca30b4203af0330819","abstract_canon_sha256":"ce813ae174d4fe486d255fc836c016560d5dd6e56c4d8e4335c3463c698b49ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:33.860421Z","signature_b64":"rjiJQlDoF+wjPwxem2Vk62AZKu4NZV9kmblwf2MMvyfGhBajRsQR/g/fdNauRK3MYebDCUppvGWcrrLt5bUUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"015f0288caab9f3ad24461265a98526dc972b06f5d3646e6d0475e29f4e44f93","last_reissued_at":"2026-07-05T00:11:33.859893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:33.859893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoGraph: Recognizing Minutes-Long Human Activities in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnold W.M. Smeulders, Efstratios Gavves, Noureldien Hussein","submitted_at":"2019-05-13T16:57:40Z","abstract_excerpt":"Many human activities take minutes to unfold. To represent them, related works opt for statistical pooling, which neglects the temporal structure. Others opt for convolutional methods, as CNN and Non-Local. While successful in learning temporal concepts, they are short of modeling minutes-long temporal dependencies. We propose VideoGraph, a method to achieve the best of two worlds: represent minutes-long human activities and learn their underlying temporal structure. VideoGraph learns a graph-based representation for human activities. The graph, its nodes and edges are learned entirely from vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05143","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/1905.05143/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":"1905.05143","created_at":"2026-07-05T00:11:33.859953+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05143v2","created_at":"2026-07-05T00:11:33.859953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05143","created_at":"2026-07-05T00:11:33.859953+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFPQFCGKVOPT","created_at":"2026-07-05T00:11:33.859953+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFPQFCGKVOPTVUSE","created_at":"2026-07-05T00:11:33.859953+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFPQFCGK","created_at":"2026-07-05T00:11:33.859953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.24943","citing_title":"Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04372","citing_title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX","json":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX.json","graph_json":"https://pith.science/api/pith-number/AFPQFCGKVOPTVUSEMETFVGCSNX/graph.json","events_json":"https://pith.science/api/pith-number/AFPQFCGKVOPTVUSEMETFVGCSNX/events.json","paper":"https://pith.science/paper/AFPQFCGK"},"agent_actions":{"view_html":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX","download_json":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX.json","view_paper":"https://pith.science/paper/AFPQFCGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05143&json=true","fetch_graph":"https://pith.science/api/pith-number/AFPQFCGKVOPTVUSEMETFVGCSNX/graph.json","fetch_events":"https://pith.science/api/pith-number/AFPQFCGKVOPTVUSEMETFVGCSNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX/action/storage_attestation","attest_author":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX/action/author_attestation","sign_citation":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX/action/citation_signature","submit_replication":"https://pith.science/pith/AFPQFCGKVOPTVUSEMETFVGCSNX/action/replication_record"}},"created_at":"2026-07-05T00:11:33.859953+00:00","updated_at":"2026-07-05T00:11:33.859953+00:00"}