{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5YXRU5VMMX2YEPA2YLW2IXMZ6N","short_pith_number":"pith:5YXRU5VM","schema_version":"1.0","canonical_sha256":"ee2f1a76ac65f5823c1ac2eda45d99f36d0cc47597375da0a19179c01b570a11","source":{"kind":"arxiv","id":"1904.04357","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyou Fan, Chi Zhang, Heng Huang, Shu Zhang, Wensheng Wang, Xiaofan Zhang","submitted_at":"2019-04-08T21:10:16Z","abstract_excerpt":"In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention. Our VideoQA model firstly generates the global context-aware visual and tex"},"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":"1904.04357","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T21:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"1ab76a314d63b990bd057fba57a0328f0091ac68c06e5a224c105033fbcb96c4","abstract_canon_sha256":"c85e9066af8ab8ba20445dd8d6ef9a9d31dff7b5d07021b4550a882d6451c40d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:59.202892Z","signature_b64":"rTsJ58OAIKK/FJ8wOxzt9096lR3qDMSUi/OArGfoCCWo1drREgrPFwW5hGUS40i/c9kD5GUXdVYmRRH9p4J+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee2f1a76ac65f5823c1ac2eda45d99f36d0cc47597375da0a19179c01b570a11","last_reissued_at":"2026-05-17T23:48:59.202494Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:59.202494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyou Fan, Chi Zhang, Heng Huang, Shu Zhang, Wensheng Wang, Xiaofan Zhang","submitted_at":"2019-04-08T21:10:16Z","abstract_excerpt":"In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention. Our VideoQA model firstly generates the global context-aware visual and tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04357","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":"1904.04357","created_at":"2026-05-17T23:48:59.202561+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.04357v1","created_at":"2026-05-17T23:48:59.202561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04357","created_at":"2026-05-17T23:48:59.202561+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YXRU5VMMX2Y","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YXRU5VMMX2YEPA2","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YXRU5VM","created_at":"2026-05-18T12:33:10.108867+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/5YXRU5VMMX2YEPA2YLW2IXMZ6N","json":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N.json","graph_json":"https://pith.science/api/pith-number/5YXRU5VMMX2YEPA2YLW2IXMZ6N/graph.json","events_json":"https://pith.science/api/pith-number/5YXRU5VMMX2YEPA2YLW2IXMZ6N/events.json","paper":"https://pith.science/paper/5YXRU5VM"},"agent_actions":{"view_html":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N","download_json":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N.json","view_paper":"https://pith.science/paper/5YXRU5VM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.04357&json=true","fetch_graph":"https://pith.science/api/pith-number/5YXRU5VMMX2YEPA2YLW2IXMZ6N/graph.json","fetch_events":"https://pith.science/api/pith-number/5YXRU5VMMX2YEPA2YLW2IXMZ6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N/action/storage_attestation","attest_author":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N/action/author_attestation","sign_citation":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N/action/citation_signature","submit_replication":"https://pith.science/pith/5YXRU5VMMX2YEPA2YLW2IXMZ6N/action/replication_record"}},"created_at":"2026-05-17T23:48:59.202561+00:00","updated_at":"2026-05-17T23:48:59.202561+00:00"}