{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ILWPQZAUM477XNIVGXYX2NKMPH","short_pith_number":"pith:ILWPQZAU","schema_version":"1.0","canonical_sha256":"42ecf86414673ffbb51535f17d354c79e250703b88afdd0281ab693b6006d207","source":{"kind":"arxiv","id":"2309.09496","version":2},"attestation_state":"computed","paper":{"title":"CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qingmin Liao, Wenming Yang, Yaowei Li, Yaowei Wang, Yating Liu, Zimo Liu","submitted_at":"2023-09-18T05:38:49Z","abstract_excerpt":"Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query. The primary challenge lies in bridging the substantial gap between vision and language modalities, especially when dealing with limited large-scale datasets. In this paper, we introduce a CLIP-based Synergistic Knowledge Transfer (CSKT) approach for TPR. Specifically, to explore the CLIP's knowledge on input side, we first propose a Bidirectional Prompts Transferring (BPT) module constructed by text-to-image and image-to-text bidirectional prompts and coupling projections. Secondly, Dual Adapters"},"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":"2309.09496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T05:38:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cbed9c0c91203b1e268b3548dedd7b62e7cfa5eb9482cf4d983607a7eaf0826c","abstract_canon_sha256":"bfe517512159a66fba41c76562e1debdf6244e8fe95bcf94c45395d22d53c636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:28.498117Z","signature_b64":"NHvvn8MZ3toiuIdOUKHHQhNRDAlKMQHFpDrqaYtSWVMx+6TKYgzyv8pflE9KLfK+5uXvdoaboq3U94GMX9++Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ecf86414673ffbb51535f17d354c79e250703b88afdd0281ab693b6006d207","last_reissued_at":"2026-07-05T07:29:28.497680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:28.497680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qingmin Liao, Wenming Yang, Yaowei Li, Yaowei Wang, Yating Liu, Zimo Liu","submitted_at":"2023-09-18T05:38:49Z","abstract_excerpt":"Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query. The primary challenge lies in bridging the substantial gap between vision and language modalities, especially when dealing with limited large-scale datasets. In this paper, we introduce a CLIP-based Synergistic Knowledge Transfer (CSKT) approach for TPR. Specifically, to explore the CLIP's knowledge on input side, we first propose a Bidirectional Prompts Transferring (BPT) module constructed by text-to-image and image-to-text bidirectional prompts and coupling projections. Secondly, Dual Adapters"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09496","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/2309.09496/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":"2309.09496","created_at":"2026-07-05T07:29:28.497730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09496v2","created_at":"2026-07-05T07:29:28.497730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09496","created_at":"2026-07-05T07:29:28.497730+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILWPQZAUM477","created_at":"2026-07-05T07:29:28.497730+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILWPQZAUM477XNIV","created_at":"2026-07-05T07:29:28.497730+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILWPQZAU","created_at":"2026-07-05T07:29:28.497730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20646","citing_title":"Enhancing Visual Representation for Text-based Person Searching","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH","json":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH.json","graph_json":"https://pith.science/api/pith-number/ILWPQZAUM477XNIVGXYX2NKMPH/graph.json","events_json":"https://pith.science/api/pith-number/ILWPQZAUM477XNIVGXYX2NKMPH/events.json","paper":"https://pith.science/paper/ILWPQZAU"},"agent_actions":{"view_html":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH","download_json":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH.json","view_paper":"https://pith.science/paper/ILWPQZAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09496&json=true","fetch_graph":"https://pith.science/api/pith-number/ILWPQZAUM477XNIVGXYX2NKMPH/graph.json","fetch_events":"https://pith.science/api/pith-number/ILWPQZAUM477XNIVGXYX2NKMPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH/action/storage_attestation","attest_author":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH/action/author_attestation","sign_citation":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH/action/citation_signature","submit_replication":"https://pith.science/pith/ILWPQZAUM477XNIVGXYX2NKMPH/action/replication_record"}},"created_at":"2026-07-05T07:29:28.497730+00:00","updated_at":"2026-07-05T07:29:28.497730+00:00"}