{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LQO4VHO4WEWS3DZTTIUF473IB4","short_pith_number":"pith:LQO4VHO4","schema_version":"1.0","canonical_sha256":"5c1dca9ddcb12d2d8f339a285e7f680f2b015708bd79bf47f9a215f107bd2d24","source":{"kind":"arxiv","id":"2006.11807","version":1},"attestation_state":"computed","paper":{"title":"Improving Image Captioning with Better Use of Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Xiaodan Zhu, Xipeng Qiu, Xu Zhou, Zhan Shi","submitted_at":"2020-06-21T14:10:47Z","abstract_excerpt":"Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. The representation is then enhanced with neighbouring and contextual nodes with their textual and vis"},"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":"2006.11807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-21T14:10:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8b9639ee570d375ebf4db78f6ee1918cf89bd93ec3e1663045078ce31a749b7f","abstract_canon_sha256":"770d0ade54377d1e15b43162a739ce10c9f983804c82bb4cbf7c2502a3829a3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:53.990500Z","signature_b64":"2CgW13v5mjsktCMd0ywncC/w5C7jfbg8XA0toKoSR/PF+NH+UlR7zPsF5srqMNSJI8CdMk75Es7F7NPOsHOWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c1dca9ddcb12d2d8f339a285e7f680f2b015708bd79bf47f9a215f107bd2d24","last_reissued_at":"2026-07-05T01:11:53.990017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:53.990017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Image Captioning with Better Use of Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Xiaodan Zhu, Xipeng Qiu, Xu Zhou, Zhan Shi","submitted_at":"2020-06-21T14:10:47Z","abstract_excerpt":"Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. The representation is then enhanced with neighbouring and contextual nodes with their textual and vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11807","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11807/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":"2006.11807","created_at":"2026-07-05T01:11:53.990074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11807v1","created_at":"2026-07-05T01:11:53.990074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11807","created_at":"2026-07-05T01:11:53.990074+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQO4VHO4WEWS","created_at":"2026-07-05T01:11:53.990074+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQO4VHO4WEWS3DZT","created_at":"2026-07-05T01:11:53.990074+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQO4VHO4","created_at":"2026-07-05T01:11:53.990074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27147","citing_title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03147","citing_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13540","citing_title":"Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4","json":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4.json","graph_json":"https://pith.science/api/pith-number/LQO4VHO4WEWS3DZTTIUF473IB4/graph.json","events_json":"https://pith.science/api/pith-number/LQO4VHO4WEWS3DZTTIUF473IB4/events.json","paper":"https://pith.science/paper/LQO4VHO4"},"agent_actions":{"view_html":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4","download_json":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4.json","view_paper":"https://pith.science/paper/LQO4VHO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11807&json=true","fetch_graph":"https://pith.science/api/pith-number/LQO4VHO4WEWS3DZTTIUF473IB4/graph.json","fetch_events":"https://pith.science/api/pith-number/LQO4VHO4WEWS3DZTTIUF473IB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/action/storage_attestation","attest_author":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/action/author_attestation","sign_citation":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/action/citation_signature","submit_replication":"https://pith.science/pith/LQO4VHO4WEWS3DZTTIUF473IB4/action/replication_record"}},"created_at":"2026-07-05T01:11:53.990074+00:00","updated_at":"2026-07-05T01:11:53.990074+00:00"}