{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MST32T3G7PGSDUEZ2JDI3PTNER","short_pith_number":"pith:MST32T3G","schema_version":"1.0","canonical_sha256":"64a7bd4f66fbcd21d099d2468dbe6d24694b8ec17c70951aab3d43e381b8b6c9","source":{"kind":"arxiv","id":"2412.20646","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Visual Representation for Text-based Person Searching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diping Li, Huangqun Chen, Jiafeng Xiao, Ling Xu, Ming Fang, Weifeng Zhang, Wei Shen, Yuxia Wang","submitted_at":"2024-12-30T01:38:14Z","abstract_excerpt":"Text-based person search aims to retrieve the matched pedestrians from a large-scale image database according to the text description. The core difficulty of this task is how to extract effective details from pedestrian images and texts, and achieve cross-modal alignment in a common latent space. Prior works adopt image and text encoders pre-trained on unimodal data to extract global and local features from image and text respectively, and then global-local alignment is achieved explicitly. However, these approaches still lack the ability of understanding visual details, and the retrieval accu"},"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":"2412.20646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T01:38:14Z","cross_cats_sorted":[],"title_canon_sha256":"8af776f6b77dea9e4769d7ca4d62bfd95e19e4f06b0d3e4d626b7830da119163","abstract_canon_sha256":"5f70f53f7f99d4ac2cf22ac40ffc7023c29bf6bf660fe2a8ec55de47527fcbfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:20.205241Z","signature_b64":"rmyCoe45BV+nGOVEFwMT9hgOL0p8ykZ0ohODAcSqUbB8XubhIoxHev6Di2wiZADODwfU6e6no8/xRIpTm9u4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64a7bd4f66fbcd21d099d2468dbe6d24694b8ec17c70951aab3d43e381b8b6c9","last_reissued_at":"2026-07-05T09:55:20.204472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:20.204472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Visual Representation for Text-based Person Searching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diping Li, Huangqun Chen, Jiafeng Xiao, Ling Xu, Ming Fang, Weifeng Zhang, Wei Shen, Yuxia Wang","submitted_at":"2024-12-30T01:38:14Z","abstract_excerpt":"Text-based person search aims to retrieve the matched pedestrians from a large-scale image database according to the text description. The core difficulty of this task is how to extract effective details from pedestrian images and texts, and achieve cross-modal alignment in a common latent space. Prior works adopt image and text encoders pre-trained on unimodal data to extract global and local features from image and text respectively, and then global-local alignment is achieved explicitly. However, these approaches still lack the ability of understanding visual details, and the retrieval accu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20646","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/2412.20646/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":"2412.20646","created_at":"2026-07-05T09:55:20.204539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20646v1","created_at":"2026-07-05T09:55:20.204539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20646","created_at":"2026-07-05T09:55:20.204539+00:00"},{"alias_kind":"pith_short_12","alias_value":"MST32T3G7PGS","created_at":"2026-07-05T09:55:20.204539+00:00"},{"alias_kind":"pith_short_16","alias_value":"MST32T3G7PGSDUEZ","created_at":"2026-07-05T09:55:20.204539+00:00"},{"alias_kind":"pith_short_8","alias_value":"MST32T3G","created_at":"2026-07-05T09:55:20.204539+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/MST32T3G7PGSDUEZ2JDI3PTNER","json":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER.json","graph_json":"https://pith.science/api/pith-number/MST32T3G7PGSDUEZ2JDI3PTNER/graph.json","events_json":"https://pith.science/api/pith-number/MST32T3G7PGSDUEZ2JDI3PTNER/events.json","paper":"https://pith.science/paper/MST32T3G"},"agent_actions":{"view_html":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER","download_json":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER.json","view_paper":"https://pith.science/paper/MST32T3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20646&json=true","fetch_graph":"https://pith.science/api/pith-number/MST32T3G7PGSDUEZ2JDI3PTNER/graph.json","fetch_events":"https://pith.science/api/pith-number/MST32T3G7PGSDUEZ2JDI3PTNER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER/action/storage_attestation","attest_author":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER/action/author_attestation","sign_citation":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER/action/citation_signature","submit_replication":"https://pith.science/pith/MST32T3G7PGSDUEZ2JDI3PTNER/action/replication_record"}},"created_at":"2026-07-05T09:55:20.204539+00:00","updated_at":"2026-07-05T09:55:20.204539+00:00"}