{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XHLBZ4HZRF7XFAETTB25VQLYAS","short_pith_number":"pith:XHLBZ4HZ","schema_version":"1.0","canonical_sha256":"b9d61cf0f9897f7280939875dac17804a7dc0449e349c5ab842d9b1d741aa08d","source":{"kind":"arxiv","id":"1906.10770","version":1},"attestation_state":"computed","paper":{"title":"Deep Modular Co-Attention Networks for Visual Question Answering","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":"2019-06-25T22:16:03Z","abstract_excerpt":"Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Atte"},"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":"1906.10770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-25T22:16:03Z","cross_cats_sorted":[],"title_canon_sha256":"730e91ec248ea12e6d9bb19f7e80ef9ab4411689411c691f675d96c9982458a8","abstract_canon_sha256":"04ccba8f55b7b4b7d7f9b64a9096b2e460b0ad9232394a025d5b55919b9837ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:14.835331Z","signature_b64":"B4ArrQOOb+zD2ZZYzILfENOd1JOhHF4z/jhzDDRCYeyFqyGuyiwhUXkINAIDCuumLlWqE2Zjws9qbpDC1LiMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9d61cf0f9897f7280939875dac17804a7dc0449e349c5ab842d9b1d741aa08d","last_reissued_at":"2026-05-17T23:42:14.834675Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:14.834675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Modular Co-Attention Networks for Visual Question Answering","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":"2019-06-25T22:16:03Z","abstract_excerpt":"Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Atte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10770","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":"1906.10770","created_at":"2026-05-17T23:42:14.834780+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.10770v1","created_at":"2026-05-17T23:42:14.834780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10770","created_at":"2026-05-17T23:42:14.834780+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHLBZ4HZRF7X","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHLBZ4HZRF7XFAET","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHLBZ4HZ","created_at":"2026-05-18T12:33:33.725879+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/XHLBZ4HZRF7XFAETTB25VQLYAS","json":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS.json","graph_json":"https://pith.science/api/pith-number/XHLBZ4HZRF7XFAETTB25VQLYAS/graph.json","events_json":"https://pith.science/api/pith-number/XHLBZ4HZRF7XFAETTB25VQLYAS/events.json","paper":"https://pith.science/paper/XHLBZ4HZ"},"agent_actions":{"view_html":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS","download_json":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS.json","view_paper":"https://pith.science/paper/XHLBZ4HZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.10770&json=true","fetch_graph":"https://pith.science/api/pith-number/XHLBZ4HZRF7XFAETTB25VQLYAS/graph.json","fetch_events":"https://pith.science/api/pith-number/XHLBZ4HZRF7XFAETTB25VQLYAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/action/storage_attestation","attest_author":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/action/author_attestation","sign_citation":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/action/citation_signature","submit_replication":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/action/replication_record"}},"created_at":"2026-05-17T23:42:14.834780+00:00","updated_at":"2026-05-17T23:42:14.834780+00:00"}