{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:X6RYEI6227ZMDLDLGCU2IE35GO","short_pith_number":"pith:X6RYEI62","schema_version":"1.0","canonical_sha256":"bfa38223dad7f2c1ac6b30a9a4137d33b63ce1f3f82b7f7f200957858bb46936","source":{"kind":"arxiv","id":"1812.02664","version":2},"attestation_state":"computed","paper":{"title":"Recursive Visual Attention in Visual Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Jianhong Zhang, Ji-Rong Wen, Manli Zhang, Yulei Niu, Zhiwu Lu","submitted_at":"2018-12-06T17:00:16Z","abstract_excerpt":"Visual dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded questions, which is the core challenge in visual question answering (VQA); (2) How to infer the co-reference between questions and the dialog history. An example of visual co-reference is: pronouns (\\eg, ``they'') in the question (\\eg, ``Are they on or off?'') are linked with nouns (\\eg, ``lamps'') appearing in the dialog history (\\eg, ``How many lamps are there?'') and the object grou"},"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":"1812.02664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T17:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"797cefb9bdab4651937ae5a1cfe3dece2011ea03dbf2f1951bcc034bc01247bb","abstract_canon_sha256":"1c0d978960986da97cb226536b4c1a2b5c13ec5920cee0fa6555ee318be5e9a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:16.938311Z","signature_b64":"uTl6rZ94gFfm9DaIJm3rdKM71i0rh6s2LRleBF2ucGi7BSqxur42N0lOlRzkZa86BNd9uWfjclg3Ku+EnEKfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa38223dad7f2c1ac6b30a9a4137d33b63ce1f3f82b7f7f200957858bb46936","last_reissued_at":"2026-05-17T23:49:16.937718Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:16.937718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recursive Visual Attention in Visual Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Jianhong Zhang, Ji-Rong Wen, Manli Zhang, Yulei Niu, Zhiwu Lu","submitted_at":"2018-12-06T17:00:16Z","abstract_excerpt":"Visual dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded questions, which is the core challenge in visual question answering (VQA); (2) How to infer the co-reference between questions and the dialog history. An example of visual co-reference is: pronouns (\\eg, ``they'') in the question (\\eg, ``Are they on or off?'') are linked with nouns (\\eg, ``lamps'') appearing in the dialog history (\\eg, ``How many lamps are there?'') and the object grou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02664","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":""},"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":"1812.02664","created_at":"2026-05-17T23:49:16.937818+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02664v2","created_at":"2026-05-17T23:49:16.937818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02664","created_at":"2026-05-17T23:49:16.937818+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6RYEI6227ZM","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6RYEI6227ZMDLDL","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6RYEI62","created_at":"2026-05-18T12:33:01.666342+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/X6RYEI6227ZMDLDLGCU2IE35GO","json":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO.json","graph_json":"https://pith.science/api/pith-number/X6RYEI6227ZMDLDLGCU2IE35GO/graph.json","events_json":"https://pith.science/api/pith-number/X6RYEI6227ZMDLDLGCU2IE35GO/events.json","paper":"https://pith.science/paper/X6RYEI62"},"agent_actions":{"view_html":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO","download_json":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO.json","view_paper":"https://pith.science/paper/X6RYEI62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02664&json=true","fetch_graph":"https://pith.science/api/pith-number/X6RYEI6227ZMDLDLGCU2IE35GO/graph.json","fetch_events":"https://pith.science/api/pith-number/X6RYEI6227ZMDLDLGCU2IE35GO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/action/storage_attestation","attest_author":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/action/author_attestation","sign_citation":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/action/citation_signature","submit_replication":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/action/replication_record"}},"created_at":"2026-05-17T23:49:16.937818+00:00","updated_at":"2026-05-17T23:49:16.937818+00:00"}