{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WFNXSDPEF7TCBZ3XSPBJ26WYK6","short_pith_number":"pith:WFNXSDPE","schema_version":"1.0","canonical_sha256":"b15b790de42fe620e77793c29d7ad857bcd373a7854a35c2027e8a4ad0cd1244","source":{"kind":"arxiv","id":"2207.07802","version":1},"attestation_state":"computed","paper":{"title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Jian Wang, Meng Fang, Xinyu Zhang, Zhifeng Lin, Zhiyin Shao","submitted_at":"2022-07-16T01:26:10Z","abstract_excerpt":"Text-to-image person re-identification (ReID) aims to search for pedestrian images of an interested identity via textual descriptions. It is challenging due to both rich intra-modal variations and significant inter-modal gaps. Existing works usually ignore the difference in feature granularity between the two modalities, i.e., the visual features are usually fine-grained while textual features are coarse, which is mainly responsible for the large inter-modal gaps. In this paper, we propose an end-to-end framework based on transformers to learn granularity-unified representations for both modal"},"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":"2207.07802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-16T01:26:10Z","cross_cats_sorted":[],"title_canon_sha256":"857b9b25013594a27880162d5af138a2ac493a1665491d6b7d10f146f60aa73b","abstract_canon_sha256":"935ca6d1d161336e83410ef493b5d7f168bfaeffed61604688115234f2c184d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:56.587891Z","signature_b64":"vErQ5kOwMC/9p4EtYUWSsQ0L1AQz4EksMPWI7iDLEXx0Qs53mbo599Fj8P8c+Tg7uzH8fqmZp0gsES499agTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b15b790de42fe620e77793c29d7ad857bcd373a7854a35c2027e8a4ad0cd1244","last_reissued_at":"2026-07-05T04:40:56.587497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:56.587497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Jian Wang, Meng Fang, Xinyu Zhang, Zhifeng Lin, Zhiyin Shao","submitted_at":"2022-07-16T01:26:10Z","abstract_excerpt":"Text-to-image person re-identification (ReID) aims to search for pedestrian images of an interested identity via textual descriptions. It is challenging due to both rich intra-modal variations and significant inter-modal gaps. Existing works usually ignore the difference in feature granularity between the two modalities, i.e., the visual features are usually fine-grained while textual features are coarse, which is mainly responsible for the large inter-modal gaps. In this paper, we propose an end-to-end framework based on transformers to learn granularity-unified representations for both modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07802","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/2207.07802/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":"2207.07802","created_at":"2026-07-05T04:40:56.587564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.07802v1","created_at":"2026-07-05T04:40:56.587564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07802","created_at":"2026-07-05T04:40:56.587564+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFNXSDPEF7TC","created_at":"2026-07-05T04:40:56.587564+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFNXSDPEF7TCBZ3X","created_at":"2026-07-05T04:40:56.587564+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFNXSDPE","created_at":"2026-07-05T04:40:56.587564+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/WFNXSDPEF7TCBZ3XSPBJ26WYK6","json":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6.json","graph_json":"https://pith.science/api/pith-number/WFNXSDPEF7TCBZ3XSPBJ26WYK6/graph.json","events_json":"https://pith.science/api/pith-number/WFNXSDPEF7TCBZ3XSPBJ26WYK6/events.json","paper":"https://pith.science/paper/WFNXSDPE"},"agent_actions":{"view_html":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6","download_json":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6.json","view_paper":"https://pith.science/paper/WFNXSDPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.07802&json=true","fetch_graph":"https://pith.science/api/pith-number/WFNXSDPEF7TCBZ3XSPBJ26WYK6/graph.json","fetch_events":"https://pith.science/api/pith-number/WFNXSDPEF7TCBZ3XSPBJ26WYK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6/action/storage_attestation","attest_author":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6/action/author_attestation","sign_citation":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6/action/citation_signature","submit_replication":"https://pith.science/pith/WFNXSDPEF7TCBZ3XSPBJ26WYK6/action/replication_record"}},"created_at":"2026-07-05T04:40:56.587564+00:00","updated_at":"2026-07-05T04:40:56.587564+00:00"}