{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G6MZWBPM7IGFEL6BXSYWK67RSF","short_pith_number":"pith:G6MZWBPM","schema_version":"1.0","canonical_sha256":"37999b05ecfa0c522fc1bcb1657bf19148332fc15df53f786d5cf8c839ddbdc6","source":{"kind":"arxiv","id":"2507.00506","version":1},"attestation_state":"computed","paper":{"title":"SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Juncheng Wu, Shoudong Han, Yunfei Xie, Yuxuan Cheng, Yuyin Zhou","submitted_at":"2025-07-01T07:21:31Z","abstract_excerpt":"Recent advancements in adapting vision-language pre-training models like CLIP for person re-identification (ReID) tasks often rely on complex adapter design or modality-specific tuning while neglecting cross-modal interaction, leading to high computational costs or suboptimal alignment. To address these limitations, we propose a simple yet effective framework named Selective Cross-modal Prompt Tuning (SCING) that enhances cross-modal alignment and robustness against real-world perturbations. Our method introduces two key innovations: Firstly, we proposed Selective Visual Prompt Fusion (SVIP), "},"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":"2507.00506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:21:31Z","cross_cats_sorted":[],"title_canon_sha256":"f317524f271e6fd8fcb905b51357321e7e268df15a8be5fbacc7554049b0e55f","abstract_canon_sha256":"308463f7bc26f26c7a2c8e8313cd72ceecf9e3e632007321475d88e7389f26a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:10.033480Z","signature_b64":"vrsI9+/+4kKWjJdbH1je1tgRpvDan6Uy7lbBled8qwqQVZzhRDEBWXlRf7FfQz/erLMC0Gz8sMVvW5epi1qcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37999b05ecfa0c522fc1bcb1657bf19148332fc15df53f786d5cf8c839ddbdc6","last_reissued_at":"2026-07-05T11:30:10.033060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:10.033060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Juncheng Wu, Shoudong Han, Yunfei Xie, Yuxuan Cheng, Yuyin Zhou","submitted_at":"2025-07-01T07:21:31Z","abstract_excerpt":"Recent advancements in adapting vision-language pre-training models like CLIP for person re-identification (ReID) tasks often rely on complex adapter design or modality-specific tuning while neglecting cross-modal interaction, leading to high computational costs or suboptimal alignment. To address these limitations, we propose a simple yet effective framework named Selective Cross-modal Prompt Tuning (SCING) that enhances cross-modal alignment and robustness against real-world perturbations. Our method introduces two key innovations: Firstly, we proposed Selective Visual Prompt Fusion (SVIP), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00506","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/2507.00506/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":"2507.00506","created_at":"2026-07-05T11:30:10.033116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00506v1","created_at":"2026-07-05T11:30:10.033116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00506","created_at":"2026-07-05T11:30:10.033116+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6MZWBPM7IGF","created_at":"2026-07-05T11:30:10.033116+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6MZWBPM7IGFEL6B","created_at":"2026-07-05T11:30:10.033116+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6MZWBPM","created_at":"2026-07-05T11:30:10.033116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22190","citing_title":"From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF","json":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF.json","graph_json":"https://pith.science/api/pith-number/G6MZWBPM7IGFEL6BXSYWK67RSF/graph.json","events_json":"https://pith.science/api/pith-number/G6MZWBPM7IGFEL6BXSYWK67RSF/events.json","paper":"https://pith.science/paper/G6MZWBPM"},"agent_actions":{"view_html":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF","download_json":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF.json","view_paper":"https://pith.science/paper/G6MZWBPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00506&json=true","fetch_graph":"https://pith.science/api/pith-number/G6MZWBPM7IGFEL6BXSYWK67RSF/graph.json","fetch_events":"https://pith.science/api/pith-number/G6MZWBPM7IGFEL6BXSYWK67RSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF/action/storage_attestation","attest_author":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF/action/author_attestation","sign_citation":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF/action/citation_signature","submit_replication":"https://pith.science/pith/G6MZWBPM7IGFEL6BXSYWK67RSF/action/replication_record"}},"created_at":"2026-07-05T11:30:10.033116+00:00","updated_at":"2026-07-05T11:30:10.033116+00:00"}