{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WKYVHSZT7Q2PW7B6X2DIHFDZF2","short_pith_number":"pith:WKYVHSZT","schema_version":"1.0","canonical_sha256":"b2b153cb33fc34fb7c3ebe868394792eaac37afd94c28aaa8ff0388245ca3cb0","source":{"kind":"arxiv","id":"2303.00448","version":2},"attestation_state":"computed","paper":{"title":"The style transformer with common knowledge optimization for image-text retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jinqiao Shi, Wenrui Li, Xiaopeng Fan, Zhengyu Ma","submitted_at":"2023-03-01T12:17:33Z","abstract_excerpt":"Image-text retrieval which associates different modalities has drawn broad attention due to its excellent research value and broad real-world application. However, most of the existing methods haven't taken the high-level semantic relationships (\"style embedding\") and common knowledge from multi-modalities into full consideration. To this end, we introduce a novel style transformer network with common knowledge optimization (CKSTN) for image-text retrieval. The main module is the common knowledge adaptor (CKA) with both the style embedding extractor (SEE) and the common knowledge optimization "},"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":"2303.00448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T12:17:33Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"57cfdca88a7a3057e740928ec023488c1ca44d4c96d935065456037649b95846","abstract_canon_sha256":"4af87945cba6f2679d971be41de41b30d20245f4ba4f38cd9a32f207aa67c67a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:16.270475Z","signature_b64":"IT1RdA/E1GbwZ6EqmErpbARhcm80FA9axgVb32v8S+h5ABBIO4XBBXsqWVea2TLlhjXCtLOZMXzLtAMcV+ReCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b153cb33fc34fb7c3ebe868394792eaac37afd94c28aaa8ff0388245ca3cb0","last_reissued_at":"2026-07-05T05:57:16.269969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:16.269969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The style transformer with common knowledge optimization for image-text retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jinqiao Shi, Wenrui Li, Xiaopeng Fan, Zhengyu Ma","submitted_at":"2023-03-01T12:17:33Z","abstract_excerpt":"Image-text retrieval which associates different modalities has drawn broad attention due to its excellent research value and broad real-world application. However, most of the existing methods haven't taken the high-level semantic relationships (\"style embedding\") and common knowledge from multi-modalities into full consideration. To this end, we introduce a novel style transformer network with common knowledge optimization (CKSTN) for image-text retrieval. The main module is the common knowledge adaptor (CKA) with both the style embedding extractor (SEE) and the common knowledge optimization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00448","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/2303.00448/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":"2303.00448","created_at":"2026-07-05T05:57:16.270029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00448v2","created_at":"2026-07-05T05:57:16.270029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00448","created_at":"2026-07-05T05:57:16.270029+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKYVHSZT7Q2P","created_at":"2026-07-05T05:57:16.270029+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKYVHSZT7Q2PW7B6","created_at":"2026-07-05T05:57:16.270029+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKYVHSZT","created_at":"2026-07-05T05:57:16.270029+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/WKYVHSZT7Q2PW7B6X2DIHFDZF2","json":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2.json","graph_json":"https://pith.science/api/pith-number/WKYVHSZT7Q2PW7B6X2DIHFDZF2/graph.json","events_json":"https://pith.science/api/pith-number/WKYVHSZT7Q2PW7B6X2DIHFDZF2/events.json","paper":"https://pith.science/paper/WKYVHSZT"},"agent_actions":{"view_html":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2","download_json":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2.json","view_paper":"https://pith.science/paper/WKYVHSZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00448&json=true","fetch_graph":"https://pith.science/api/pith-number/WKYVHSZT7Q2PW7B6X2DIHFDZF2/graph.json","fetch_events":"https://pith.science/api/pith-number/WKYVHSZT7Q2PW7B6X2DIHFDZF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2/action/storage_attestation","attest_author":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2/action/author_attestation","sign_citation":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2/action/citation_signature","submit_replication":"https://pith.science/pith/WKYVHSZT7Q2PW7B6X2DIHFDZF2/action/replication_record"}},"created_at":"2026-07-05T05:57:16.270029+00:00","updated_at":"2026-07-05T05:57:16.270029+00:00"}