{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F3N4R5ZIQEUNYRJE7WZ2BJO2GU","short_pith_number":"pith:F3N4R5ZI","schema_version":"1.0","canonical_sha256":"2edbc8f7288128dc4524fdb3a0a5da35267cd1e0a8373c4c564a358150ba43bd","source":{"kind":"arxiv","id":"2110.10807","version":1},"attestation_state":"computed","paper":{"title":"Text-Based Person Search with Limited Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Zhang, Sen He, Tao Xiang, Xiao Han","submitted_at":"2021-10-20T22:20:47Z","abstract_excerpt":"Text-based person search (TBPS) aims at retrieving a target person from an image gallery with a descriptive text query. Solving such a fine-grained cross-modal retrieval task is challenging, which is further hampered by the lack of large-scale datasets. In this paper, we present a framework with two novel components to handle the problems brought by limited data. Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch. "},"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":"2110.10807","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-20T22:20:47Z","cross_cats_sorted":[],"title_canon_sha256":"5fc4b3d4f696a5d161a0806c3848355ff9e24aae845a8f217ef2d58257daf4c7","abstract_canon_sha256":"59392d634c10bfa424068ab996c41671bf9b30de336bdb83349f082512e5ee26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:32.534480Z","signature_b64":"/HwZDcVvxE6XnWRaGuUrsL/24JfLf+/gvfQCdcLZ5P4R3lv1U2+3OorBxzt/D5vUsC6/reJwJGtQTjjwgx9nDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2edbc8f7288128dc4524fdb3a0a5da35267cd1e0a8373c4c564a358150ba43bd","last_reissued_at":"2026-07-05T03:24:32.533992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:32.533992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Based Person Search with Limited Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Zhang, Sen He, Tao Xiang, Xiao Han","submitted_at":"2021-10-20T22:20:47Z","abstract_excerpt":"Text-based person search (TBPS) aims at retrieving a target person from an image gallery with a descriptive text query. Solving such a fine-grained cross-modal retrieval task is challenging, which is further hampered by the lack of large-scale datasets. In this paper, we present a framework with two novel components to handle the problems brought by limited data. Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10807","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/2110.10807/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":"2110.10807","created_at":"2026-07-05T03:24:32.534051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10807v1","created_at":"2026-07-05T03:24:32.534051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10807","created_at":"2026-07-05T03:24:32.534051+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3N4R5ZIQEUN","created_at":"2026-07-05T03:24:32.534051+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3N4R5ZIQEUNYRJE","created_at":"2026-07-05T03:24:32.534051+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3N4R5ZI","created_at":"2026-07-05T03:24:32.534051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU","json":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU.json","graph_json":"https://pith.science/api/pith-number/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/graph.json","events_json":"https://pith.science/api/pith-number/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/events.json","paper":"https://pith.science/paper/F3N4R5ZI"},"agent_actions":{"view_html":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU","download_json":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU.json","view_paper":"https://pith.science/paper/F3N4R5ZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10807&json=true","fetch_graph":"https://pith.science/api/pith-number/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/graph.json","fetch_events":"https://pith.science/api/pith-number/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/action/storage_attestation","attest_author":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/action/author_attestation","sign_citation":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/action/citation_signature","submit_replication":"https://pith.science/pith/F3N4R5ZIQEUNYRJE7WZ2BJO2GU/action/replication_record"}},"created_at":"2026-07-05T03:24:32.534051+00:00","updated_at":"2026-07-05T03:24:32.534051+00:00"}