{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CGOHR6D7BBLOMTKWEH7IUNE6RF","short_pith_number":"pith:CGOHR6D7","schema_version":"1.0","canonical_sha256":"119c78f87f0856e64d5621fe8a349e8946a0230c3f3885c578708a6b50c15a51","source":{"kind":"arxiv","id":"2109.03529","version":1},"attestation_state":"computed","paper":{"title":"RefineCap: Concept-Aware Refinement for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junliang Xing, Shuo Jin, Yekun Chai","submitted_at":"2021-09-08T10:12:14Z","abstract_excerpt":"Automatically translating images to texts involves image scene understanding and language modeling. In this paper, we propose a novel model, termed RefineCap, that refines the output vocabulary of the language decoder using decoder-guided visual semantics, and implicitly learns the mapping between visual tag words and images. The proposed Visual-Concept Refinement method can allow the generator to attend to semantic details in the image, thereby generating more semantically descriptive captions. Our model achieves superior performance on the MS-COCO dataset in comparison with previous visual-c"},"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":"2109.03529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T10:12:14Z","cross_cats_sorted":[],"title_canon_sha256":"dff3b695d71c92857534cdf340a774d4536051615429e51ae86aa30babbd8822","abstract_canon_sha256":"5beb36b723dff1e3e98aeef321c2ff30d15530cd92183b1ff9db0de7d928095c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:40.528489Z","signature_b64":"XWmZTFO1HhbpZqqPlohWoAyouNeqPZ5EzZAN8JF8j2TVgbY/R269rSzNPG4/iiX4Hxhgebxidz4XVi+QYtYxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"119c78f87f0856e64d5621fe8a349e8946a0230c3f3885c578708a6b50c15a51","last_reissued_at":"2026-07-05T03:12:40.528132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:40.528132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RefineCap: Concept-Aware Refinement for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junliang Xing, Shuo Jin, Yekun Chai","submitted_at":"2021-09-08T10:12:14Z","abstract_excerpt":"Automatically translating images to texts involves image scene understanding and language modeling. In this paper, we propose a novel model, termed RefineCap, that refines the output vocabulary of the language decoder using decoder-guided visual semantics, and implicitly learns the mapping between visual tag words and images. The proposed Visual-Concept Refinement method can allow the generator to attend to semantic details in the image, thereby generating more semantically descriptive captions. Our model achieves superior performance on the MS-COCO dataset in comparison with previous visual-c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03529","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/2109.03529/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":"2109.03529","created_at":"2026-07-05T03:12:40.528192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03529v1","created_at":"2026-07-05T03:12:40.528192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03529","created_at":"2026-07-05T03:12:40.528192+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGOHR6D7BBLO","created_at":"2026-07-05T03:12:40.528192+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGOHR6D7BBLOMTKW","created_at":"2026-07-05T03:12:40.528192+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGOHR6D7","created_at":"2026-07-05T03:12:40.528192+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/CGOHR6D7BBLOMTKWEH7IUNE6RF","json":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF.json","graph_json":"https://pith.science/api/pith-number/CGOHR6D7BBLOMTKWEH7IUNE6RF/graph.json","events_json":"https://pith.science/api/pith-number/CGOHR6D7BBLOMTKWEH7IUNE6RF/events.json","paper":"https://pith.science/paper/CGOHR6D7"},"agent_actions":{"view_html":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF","download_json":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF.json","view_paper":"https://pith.science/paper/CGOHR6D7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03529&json=true","fetch_graph":"https://pith.science/api/pith-number/CGOHR6D7BBLOMTKWEH7IUNE6RF/graph.json","fetch_events":"https://pith.science/api/pith-number/CGOHR6D7BBLOMTKWEH7IUNE6RF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF/action/storage_attestation","attest_author":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF/action/author_attestation","sign_citation":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF/action/citation_signature","submit_replication":"https://pith.science/pith/CGOHR6D7BBLOMTKWEH7IUNE6RF/action/replication_record"}},"created_at":"2026-07-05T03:12:40.528192+00:00","updated_at":"2026-07-05T03:12:40.528192+00:00"}