{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3QLZHFUUCYDDMF3M32MSMRECZO","short_pith_number":"pith:3QLZHFUU","schema_version":"1.0","canonical_sha256":"dc17939694160636176cde99264482cba9ae652365fb132392bd21eb5bbd96b1","source":{"kind":"arxiv","id":"1812.05252","version":4},"attestation_state":"computed","paper":{"title":"Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Gao Peng, Haoxuan You, Hongsheng Li, Pan Lu, Steven Hoi, Xiaogang Wang, Zhengkai Jiang","submitted_at":"2018-12-13T03:41:18Z","abstract_excerpt":"Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fusing multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities. It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering. We also show that the proposed dynamic intra-modality attention flow conditioned on the other modality can dynamically m"},"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":"1812.05252","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-13T03:41:18Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"36f096eff034b738e10ba3eaebf9c4c4a3d84010907532733414f45001875d9b","abstract_canon_sha256":"33ba5e865a7713871e9a9dac86d73351aed8ce4a7f26b154becbc94770d47a14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:29.734624Z","signature_b64":"St9XxhJ+12e88cOAP+gDx/l6OJeZqYlVDyZkCsU0Z5nrgDy+vEQ99gJteRwGymRv8p4Jtu9GoPJZlBxI/lu5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc17939694160636176cde99264482cba9ae652365fb132392bd21eb5bbd96b1","last_reissued_at":"2026-07-04T23:59:29.734138Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:29.734138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Gao Peng, Haoxuan You, Hongsheng Li, Pan Lu, Steven Hoi, Xiaogang Wang, Zhengkai Jiang","submitted_at":"2018-12-13T03:41:18Z","abstract_excerpt":"Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fusing multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities. It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering. We also show that the proposed dynamic intra-modality attention flow conditioned on the other modality can dynamically m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.05252","kind":"arxiv","version":4},"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/1812.05252/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":"1812.05252","created_at":"2026-07-04T23:59:29.734197+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.05252v4","created_at":"2026-07-04T23:59:29.734197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05252","created_at":"2026-07-04T23:59:29.734197+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QLZHFUUCYDD","created_at":"2026-07-04T23:59:29.734197+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QLZHFUUCYDDMF3M","created_at":"2026-07-04T23:59:29.734197+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QLZHFUU","created_at":"2026-07-04T23:59:29.734197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04107","citing_title":"Multimodal Unified Attention Networks for Vision-and-Language Interactions","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO","json":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO.json","graph_json":"https://pith.science/api/pith-number/3QLZHFUUCYDDMF3M32MSMRECZO/graph.json","events_json":"https://pith.science/api/pith-number/3QLZHFUUCYDDMF3M32MSMRECZO/events.json","paper":"https://pith.science/paper/3QLZHFUU"},"agent_actions":{"view_html":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO","download_json":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO.json","view_paper":"https://pith.science/paper/3QLZHFUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.05252&json=true","fetch_graph":"https://pith.science/api/pith-number/3QLZHFUUCYDDMF3M32MSMRECZO/graph.json","fetch_events":"https://pith.science/api/pith-number/3QLZHFUUCYDDMF3M32MSMRECZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO/action/storage_attestation","attest_author":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO/action/author_attestation","sign_citation":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO/action/citation_signature","submit_replication":"https://pith.science/pith/3QLZHFUUCYDDMF3M32MSMRECZO/action/replication_record"}},"created_at":"2026-07-04T23:59:29.734197+00:00","updated_at":"2026-07-04T23:59:29.734197+00:00"}