{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:L6W5BVLMOHJCW7GOW7RYCKAKEV","short_pith_number":"pith:L6W5BVLM","schema_version":"1.0","canonical_sha256":"5fadd0d56c71d22b7cceb7e381280a255076fdc562fd4abcf909f0a675083eca","source":{"kind":"arxiv","id":"1707.06355","version":1},"attestation_state":"computed","paper":{"title":"Video Question Answering via Attribute-Augmented Attention Network Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jun Xiao, Long Chen, Yimeng Li, Yueting Zhuang, Yunan Ye, Zhou Zhao","submitted_at":"2017-07-20T03:12:29Z","abstract_excerpt":"Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle the problem of static image question, which may be ineffectively for video question answering due to the insufficiency of modeling the temporal dynamics of video contents. In this paper, we study the problem of video question answering by modeling its temporal dynamics with frame-level attention mechanism. We propose the attribute-augmented attention networ"},"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":"1707.06355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-20T03:12:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9dd9524b3dc314a7844ffde03b5e3a99293ba80f0ebbc866d638017a1cbd7c05","abstract_canon_sha256":"ae0f4b99607d49edf25a410d66f8dcf878f0b21bf150e4d999c891d4e05bc4e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:54.055473Z","signature_b64":"lo5Xb6ACu0274pd/8RR20mlsp/MxCM52PezZffaWRQf+73PLeWaKGoBYCNqXn2bSqqdK1fRbg9tMdsybjIsVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fadd0d56c71d22b7cceb7e381280a255076fdc562fd4abcf909f0a675083eca","last_reissued_at":"2026-05-18T00:39:54.054778Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:54.054778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Question Answering via Attribute-Augmented Attention Network Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jun Xiao, Long Chen, Yimeng Li, Yueting Zhuang, Yunan Ye, Zhou Zhao","submitted_at":"2017-07-20T03:12:29Z","abstract_excerpt":"Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle the problem of static image question, which may be ineffectively for video question answering due to the insufficiency of modeling the temporal dynamics of video contents. In this paper, we study the problem of video question answering by modeling its temporal dynamics with frame-level attention mechanism. We propose the attribute-augmented attention networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06355","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":""},"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":"1707.06355","created_at":"2026-05-18T00:39:54.054894+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.06355v1","created_at":"2026-05-18T00:39:54.054894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06355","created_at":"2026-05-18T00:39:54.054894+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6W5BVLMOHJC","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6W5BVLMOHJCW7GO","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6W5BVLM","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV","json":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV.json","graph_json":"https://pith.science/api/pith-number/L6W5BVLMOHJCW7GOW7RYCKAKEV/graph.json","events_json":"https://pith.science/api/pith-number/L6W5BVLMOHJCW7GOW7RYCKAKEV/events.json","paper":"https://pith.science/paper/L6W5BVLM"},"agent_actions":{"view_html":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV","download_json":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV.json","view_paper":"https://pith.science/paper/L6W5BVLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.06355&json=true","fetch_graph":"https://pith.science/api/pith-number/L6W5BVLMOHJCW7GOW7RYCKAKEV/graph.json","fetch_events":"https://pith.science/api/pith-number/L6W5BVLMOHJCW7GOW7RYCKAKEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV/action/storage_attestation","attest_author":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV/action/author_attestation","sign_citation":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV/action/citation_signature","submit_replication":"https://pith.science/pith/L6W5BVLMOHJCW7GOW7RYCKAKEV/action/replication_record"}},"created_at":"2026-05-18T00:39:54.054894+00:00","updated_at":"2026-05-18T00:39:54.054894+00:00"}