{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ITEKZEV7ZPZBKGEQKYYURAPX4V","short_pith_number":"pith:ITEKZEV7","schema_version":"1.0","canonical_sha256":"44c8ac92bfcbf215189056314881f7e56283d87b9e733c417c5984bec0409872","source":{"kind":"arxiv","id":"1811.04595","version":1},"attestation_state":"computed","paper":{"title":"Holistic Multi-modal Memory Network for Movie Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Tuan Luu, Anran Wang, Chuan-Sheng Foo, Hongyuan Zhu, Vijay Chandrasekhar, Yi Tay","submitted_at":"2018-11-12T08:10:21Z","abstract_excerpt":"Answering questions according to multi-modal context is a challenging problem as it requires a deep integration of different data sources. Existing approaches only employ partial interactions among data sources in one attention hop. In this paper, we present the Holistic Multi-modal Memory Network (HMMN) framework which fully considers the interactions between different input sources (multi-modal context, question) in each hop. In addition, it takes answer choices into consideration during the context retrieval stage. Therefore, the proposed framework effectively integrates multi-modal context"},"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":"1811.04595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-12T08:10:21Z","cross_cats_sorted":[],"title_canon_sha256":"4b70dfa2e4995739763f3efe7f86060aaa4b449c45b06d55254f0df883524780","abstract_canon_sha256":"e6a1f969600596eccc290e757817b727ef9493f790fdb809dec7ef59142cc667"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:04.646337Z","signature_b64":"1z+dJ127pC5PeaJihd+S/OB7fkt+UQgGTRMcJhQTgv2khqxeOuuwCT4P4p6KdS+U0IUGkUyNpYDjCfAiEzkMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44c8ac92bfcbf215189056314881f7e56283d87b9e733c417c5984bec0409872","last_reissued_at":"2026-05-18T00:01:04.645753Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:04.645753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Holistic Multi-modal Memory Network for Movie Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Tuan Luu, Anran Wang, Chuan-Sheng Foo, Hongyuan Zhu, Vijay Chandrasekhar, Yi Tay","submitted_at":"2018-11-12T08:10:21Z","abstract_excerpt":"Answering questions according to multi-modal context is a challenging problem as it requires a deep integration of different data sources. Existing approaches only employ partial interactions among data sources in one attention hop. In this paper, we present the Holistic Multi-modal Memory Network (HMMN) framework which fully considers the interactions between different input sources (multi-modal context, question) in each hop. In addition, it takes answer choices into consideration during the context retrieval stage. Therefore, the proposed framework effectively integrates multi-modal context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04595","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":"1811.04595","created_at":"2026-05-18T00:01:04.645849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.04595v1","created_at":"2026-05-18T00:01:04.645849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04595","created_at":"2026-05-18T00:01:04.645849+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITEKZEV7ZPZB","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITEKZEV7ZPZBKGEQ","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITEKZEV7","created_at":"2026-05-18T12:32:31.084164+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/ITEKZEV7ZPZBKGEQKYYURAPX4V","json":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V.json","graph_json":"https://pith.science/api/pith-number/ITEKZEV7ZPZBKGEQKYYURAPX4V/graph.json","events_json":"https://pith.science/api/pith-number/ITEKZEV7ZPZBKGEQKYYURAPX4V/events.json","paper":"https://pith.science/paper/ITEKZEV7"},"agent_actions":{"view_html":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V","download_json":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V.json","view_paper":"https://pith.science/paper/ITEKZEV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.04595&json=true","fetch_graph":"https://pith.science/api/pith-number/ITEKZEV7ZPZBKGEQKYYURAPX4V/graph.json","fetch_events":"https://pith.science/api/pith-number/ITEKZEV7ZPZBKGEQKYYURAPX4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V/action/storage_attestation","attest_author":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V/action/author_attestation","sign_citation":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V/action/citation_signature","submit_replication":"https://pith.science/pith/ITEKZEV7ZPZBKGEQKYYURAPX4V/action/replication_record"}},"created_at":"2026-05-18T00:01:04.645849+00:00","updated_at":"2026-05-18T00:01:04.645849+00:00"}