{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UFCUGBEVQR2IQLNRAPC7WF2JYU","short_pith_number":"pith:UFCUGBEV","schema_version":"1.0","canonical_sha256":"a1454304958474882db103c5fb1749c501eb67d671c2b93bdf137b27255b1e70","source":{"kind":"arxiv","id":"1908.04107","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Unified Attention Networks for Vision-and-Language Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jun Yu, Qi Tian, Yuhao Cui, Zhou Yu","submitted_at":"2019-08-12T12:12:17Z","abstract_excerpt":"Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use co-attention models to associate each visual object (e.g., image region) with each textual object (e.g., query word). Despite the success of these co-attention models, they only model inter-modal interactions while neglecting intra-modal interactions. Here we propose a general `unified attention' model that simultaneously captures the intra- and inter-modal interaction"},"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":"1908.04107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"8d94bc4e2c48fb8cf024c01a5fe6258c27679b8bd9063c764852b5f78e57bb03","abstract_canon_sha256":"b073ded74e376d9a97d45ee47cefedd297ce0ae0143cca5d6e913e275769d93b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:10.776098Z","signature_b64":"V7DTETHnmrvlchsbFwoJGvK7u+6m8FjoNAO/+BxuHQfta1K+yCdq8I6gzWAE7egeDD50aLW3RcNKm2jS2XPTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1454304958474882db103c5fb1749c501eb67d671c2b93bdf137b27255b1e70","last_reissued_at":"2026-07-04T23:58:10.775669Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:10.775669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Unified Attention Networks for Vision-and-Language Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jun Yu, Qi Tian, Yuhao Cui, Zhou Yu","submitted_at":"2019-08-12T12:12:17Z","abstract_excerpt":"Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use co-attention models to associate each visual object (e.g., image region) with each textual object (e.g., query word). Despite the success of these co-attention models, they only model inter-modal interactions while neglecting intra-modal interactions. Here we propose a general `unified attention' model that simultaneously captures the intra- and inter-modal interaction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04107","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/1908.04107/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":"1908.04107","created_at":"2026-07-04T23:58:10.775732+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04107v2","created_at":"2026-07-04T23:58:10.775732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04107","created_at":"2026-07-04T23:58:10.775732+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFCUGBEVQR2I","created_at":"2026-07-04T23:58:10.775732+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFCUGBEVQR2IQLNR","created_at":"2026-07-04T23:58:10.775732+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFCUGBEV","created_at":"2026-07-04T23:58:10.775732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20037","citing_title":"Alzheimer's Disease Diagnosis using a Multimodal Approach with 3D MRI and PET","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29302","citing_title":"ViASNet: A Video Ad Saliency Network for Predicting Dynamic Saliency and Viewer Engagement","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU","json":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU.json","graph_json":"https://pith.science/api/pith-number/UFCUGBEVQR2IQLNRAPC7WF2JYU/graph.json","events_json":"https://pith.science/api/pith-number/UFCUGBEVQR2IQLNRAPC7WF2JYU/events.json","paper":"https://pith.science/paper/UFCUGBEV"},"agent_actions":{"view_html":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU","download_json":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU.json","view_paper":"https://pith.science/paper/UFCUGBEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04107&json=true","fetch_graph":"https://pith.science/api/pith-number/UFCUGBEVQR2IQLNRAPC7WF2JYU/graph.json","fetch_events":"https://pith.science/api/pith-number/UFCUGBEVQR2IQLNRAPC7WF2JYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/action/storage_attestation","attest_author":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/action/author_attestation","sign_citation":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/action/citation_signature","submit_replication":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/action/replication_record"}},"created_at":"2026-07-04T23:58:10.775732+00:00","updated_at":"2026-07-04T23:58:10.775732+00:00"}