{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:USQ7GADJVZR3LXC752BJMQFFI5","short_pith_number":"pith:USQ7GADJ","schema_version":"1.0","canonical_sha256":"a4a1f30069ae63b5dc5fee829640a5475b77ea9bb82ef2f8386fecc8c38c377c","source":{"kind":"arxiv","id":"1809.07999","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Dual Attention Memory for Video Story Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Jin-Hwa Kim, Kyung-Min Kim, Seong-Ho Choi","submitted_at":"2018-09-21T09:19:12Z","abstract_excerpt":"We propose a video story question-answering (QA) architecture, Multimodal Dual Attention Memory (MDAM). The key idea is to use a dual attention mechanism with late fusion. MDAM uses self-attention to learn the latent concepts in scene frames and captions. Given a question, MDAM uses the second attention over these latent concepts. Multimodal fusion is performed after the dual attention processes (late fusion). Using this processing pipeline, MDAM learns to infer a high-level vision-language joint representation from an abstraction of the full video content. We evaluate MDAM on PororoQA and Mov"},"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":"1809.07999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-21T09:19:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"02d1986ff19a0b39c809ef84960828de76eb68e02fd8e3e348a044eeede540c4","abstract_canon_sha256":"d0204ef94ac3ca2cb95b94071a0aec0f9e8b2f7252efdf11e43aa62ebc147b35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:10.616735Z","signature_b64":"mItKrmNAfxw43uU69fW23JHK0NASTRYDs+2OylPq0zGB75ZLxAvIsNgyZtTx1o7AiY+WUV2eHCPJHbE2pxPNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4a1f30069ae63b5dc5fee829640a5475b77ea9bb82ef2f8386fecc8c38c377c","last_reissued_at":"2026-05-18T00:05:10.616070Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:10.616070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Dual Attention Memory for Video Story Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Jin-Hwa Kim, Kyung-Min Kim, Seong-Ho Choi","submitted_at":"2018-09-21T09:19:12Z","abstract_excerpt":"We propose a video story question-answering (QA) architecture, Multimodal Dual Attention Memory (MDAM). The key idea is to use a dual attention mechanism with late fusion. MDAM uses self-attention to learn the latent concepts in scene frames and captions. Given a question, MDAM uses the second attention over these latent concepts. Multimodal fusion is performed after the dual attention processes (late fusion). Using this processing pipeline, MDAM learns to infer a high-level vision-language joint representation from an abstraction of the full video content. We evaluate MDAM on PororoQA and Mov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07999","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":"1809.07999","created_at":"2026-05-18T00:05:10.616166+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.07999v1","created_at":"2026-05-18T00:05:10.616166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07999","created_at":"2026-05-18T00:05:10.616166+00:00"},{"alias_kind":"pith_short_12","alias_value":"USQ7GADJVZR3","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"USQ7GADJVZR3LXC7","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"USQ7GADJ","created_at":"2026-05-18T12:32:56.356000+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/USQ7GADJVZR3LXC752BJMQFFI5","json":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5.json","graph_json":"https://pith.science/api/pith-number/USQ7GADJVZR3LXC752BJMQFFI5/graph.json","events_json":"https://pith.science/api/pith-number/USQ7GADJVZR3LXC752BJMQFFI5/events.json","paper":"https://pith.science/paper/USQ7GADJ"},"agent_actions":{"view_html":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5","download_json":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5.json","view_paper":"https://pith.science/paper/USQ7GADJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.07999&json=true","fetch_graph":"https://pith.science/api/pith-number/USQ7GADJVZR3LXC752BJMQFFI5/graph.json","fetch_events":"https://pith.science/api/pith-number/USQ7GADJVZR3LXC752BJMQFFI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5/action/storage_attestation","attest_author":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5/action/author_attestation","sign_citation":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5/action/citation_signature","submit_replication":"https://pith.science/pith/USQ7GADJVZR3LXC752BJMQFFI5/action/replication_record"}},"created_at":"2026-05-18T00:05:10.616166+00:00","updated_at":"2026-05-18T00:05:10.616166+00:00"}