{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ILV4MY6J2KH4TEBQC6WQDRNJAO","short_pith_number":"pith:ILV4MY6J","schema_version":"1.0","canonical_sha256":"42ebc663c9d28fc9903017ad01c5a903884905ba776a72799660e2f128da3d4e","source":{"kind":"arxiv","id":"2006.00753","version":2},"attestation_state":"computed","paper":{"title":"Structured Multimodal Attentions for TextVQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Chenyu Gao, Hui Li, Peng Wang, Qi Wu, Qi Zhu, Yuliang Liu","submitted_at":"2020-06-01T07:07:36Z","abstract_excerpt":"In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text relationships appearing in the image, and then designs a multimodal graph attention network to reason over it. Finally, the outputs from the above modules are processed by a global-local attentional answering module to produce an answer splicing together tokens from both OCR and general vocabulary iteratively by following M4C. Our proposed model outperforms"},"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":"2006.00753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-01T07:07:36Z","cross_cats_sorted":[],"title_canon_sha256":"d6e62d0e1f2a98fafc3d7c64f3cf3c130a8b2f0a713709dccb183e2d1ca7a1d1","abstract_canon_sha256":"82201c90154dd71f1278f04b358a38071852551b9239defbad8bbf381a3f813e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:06.113326Z","signature_b64":"94mfcMnTy4v2MeMgOWi5LuNF9kwVeA5uBNvLX5wVzT9e4UX0oVNleKcboaX4FpvtYBelyGAuAjZwHZcb4p3HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ebc663c9d28fc9903017ad01c5a903884905ba776a72799660e2f128da3d4e","last_reissued_at":"2026-07-05T03:35:06.112820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:06.112820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Multimodal Attentions for TextVQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Chenyu Gao, Hui Li, Peng Wang, Qi Wu, Qi Zhu, Yuliang Liu","submitted_at":"2020-06-01T07:07:36Z","abstract_excerpt":"In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text relationships appearing in the image, and then designs a multimodal graph attention network to reason over it. Finally, the outputs from the above modules are processed by a global-local attentional answering module to produce an answer splicing together tokens from both OCR and general vocabulary iteratively by following M4C. Our proposed model outperforms"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00753","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/2006.00753/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":"2006.00753","created_at":"2026-07-05T03:35:06.112877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.00753v2","created_at":"2026-07-05T03:35:06.112877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00753","created_at":"2026-07-05T03:35:06.112877+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILV4MY6J2KH4","created_at":"2026-07-05T03:35:06.112877+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILV4MY6J2KH4TEBQ","created_at":"2026-07-05T03:35:06.112877+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILV4MY6J","created_at":"2026-07-05T03:35:06.112877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO","json":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO.json","graph_json":"https://pith.science/api/pith-number/ILV4MY6J2KH4TEBQC6WQDRNJAO/graph.json","events_json":"https://pith.science/api/pith-number/ILV4MY6J2KH4TEBQC6WQDRNJAO/events.json","paper":"https://pith.science/paper/ILV4MY6J"},"agent_actions":{"view_html":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO","download_json":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO.json","view_paper":"https://pith.science/paper/ILV4MY6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.00753&json=true","fetch_graph":"https://pith.science/api/pith-number/ILV4MY6J2KH4TEBQC6WQDRNJAO/graph.json","fetch_events":"https://pith.science/api/pith-number/ILV4MY6J2KH4TEBQC6WQDRNJAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO/action/storage_attestation","attest_author":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO/action/author_attestation","sign_citation":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO/action/citation_signature","submit_replication":"https://pith.science/pith/ILV4MY6J2KH4TEBQC6WQDRNJAO/action/replication_record"}},"created_at":"2026-07-05T03:35:06.112877+00:00","updated_at":"2026-07-05T03:35:06.112877+00:00"}