{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OA6GHGYN5CMOOECLENLHQ63X6U","short_pith_number":"pith:OA6GHGYN","schema_version":"1.0","canonical_sha256":"703c639b0de898e7104b2356787b77f506e0e4036133659421641381163e4d26","source":{"kind":"arxiv","id":"2508.04028","version":1},"attestation_state":"computed","paper":{"title":"Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Caiyang Yu, Chenwei Tang, Jiancheng Lv, Mengmi Zhang, Shudong Huang, Tao Wang, Yifan Wang, Zhengqing Zang","submitted_at":"2025-08-06T02:44:08Z","abstract_excerpt":"Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval (ITR) task is more challenging. We find that the challenge lies in discriminating both fine-grained attributes and similar subcategories of the downstream data. To address this challenge, we propose Dual prompt Learning with Joint Category-Attribute Reweighting (DCAR), a novel dual-prompt learning framework to achieve precise image-text matching. The framework"},"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":"2508.04028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T02:44:08Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"0de5ac85e36dac5d64ec6e56b39d0642b40bebc2fbbb142b019d6351ef236264","abstract_canon_sha256":"ed6eef892e020a4a52e80b9d6e73af4158460ee2d670184e913cd64356baeea0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:19.373796Z","signature_b64":"iNCL+jz5qn1jIeTyvedlToeOc6Ee9kurxS2X7OhDYNhJ1SZ6dsOnULVPHsneMU6cKGOH2JRm0yby12SbzBrLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"703c639b0de898e7104b2356787b77f506e0e4036133659421641381163e4d26","last_reissued_at":"2026-07-05T11:49:19.373329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:19.373329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Caiyang Yu, Chenwei Tang, Jiancheng Lv, Mengmi Zhang, Shudong Huang, Tao Wang, Yifan Wang, Zhengqing Zang","submitted_at":"2025-08-06T02:44:08Z","abstract_excerpt":"Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval (ITR) task is more challenging. We find that the challenge lies in discriminating both fine-grained attributes and similar subcategories of the downstream data. To address this challenge, we propose Dual prompt Learning with Joint Category-Attribute Reweighting (DCAR), a novel dual-prompt learning framework to achieve precise image-text matching. The framework"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04028","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/2508.04028/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":"2508.04028","created_at":"2026-07-05T11:49:19.373393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04028v1","created_at":"2026-07-05T11:49:19.373393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04028","created_at":"2026-07-05T11:49:19.373393+00:00"},{"alias_kind":"pith_short_12","alias_value":"OA6GHGYN5CMO","created_at":"2026-07-05T11:49:19.373393+00:00"},{"alias_kind":"pith_short_16","alias_value":"OA6GHGYN5CMOOECL","created_at":"2026-07-05T11:49:19.373393+00:00"},{"alias_kind":"pith_short_8","alias_value":"OA6GHGYN","created_at":"2026-07-05T11:49:19.373393+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/OA6GHGYN5CMOOECLENLHQ63X6U","json":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U.json","graph_json":"https://pith.science/api/pith-number/OA6GHGYN5CMOOECLENLHQ63X6U/graph.json","events_json":"https://pith.science/api/pith-number/OA6GHGYN5CMOOECLENLHQ63X6U/events.json","paper":"https://pith.science/paper/OA6GHGYN"},"agent_actions":{"view_html":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U","download_json":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U.json","view_paper":"https://pith.science/paper/OA6GHGYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04028&json=true","fetch_graph":"https://pith.science/api/pith-number/OA6GHGYN5CMOOECLENLHQ63X6U/graph.json","fetch_events":"https://pith.science/api/pith-number/OA6GHGYN5CMOOECLENLHQ63X6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U/action/storage_attestation","attest_author":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U/action/author_attestation","sign_citation":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U/action/citation_signature","submit_replication":"https://pith.science/pith/OA6GHGYN5CMOOECLENLHQ63X6U/action/replication_record"}},"created_at":"2026-07-05T11:49:19.373393+00:00","updated_at":"2026-07-05T11:49:19.373393+00:00"}