{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OKMK2XN2XIE4VY2ZBVOV2XU2YI","short_pith_number":"pith:OKMK2XN2","schema_version":"1.0","canonical_sha256":"7298ad5dbaba09cae3590d5d5d5e9ac20e21d8ddcb9ec7bbd9302c84c2e9b6ba","source":{"kind":"arxiv","id":"2107.12666","version":2},"attestation_state":"computed","paper":{"title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Dacheng Tao, Zefeng Ding, Zhiyin Shao","submitted_at":"2021-07-27T08:26:47Z","abstract_excerpt":"Text-to-image person re-identification (ReID) aims to search for images containing a person of interest using textual descriptions. However, due to the significant modality gap and the large intra-class variance in textual descriptions, text-to-image ReID remains a challenging problem. Accordingly, in this paper, we propose a Semantically Self-Aligned Network (SSAN) to handle the above problems. First, we propose a novel method that automatically extracts semantically aligned part-level features from the two modalities. Second, we design a multi-view non-local network that captures the relatio"},"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":"2107.12666","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-27T08:26:47Z","cross_cats_sorted":[],"title_canon_sha256":"0d75e6bc085dff793e08b69270ab5a715de46995563fc458f9dbb8808ebc927d","abstract_canon_sha256":"f147cdef641b188cab76abd74d1ba2d5807977820b5fa810658bde9cd47d9111"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:06.178646Z","signature_b64":"BmEp/JELFWxYI3o2xcOdTTqPx2RnkmHcx0PWPbS6xj5QY79DRFqydw7XCovOmWh2AgHT0fgkXcop1Vc/SzqvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7298ad5dbaba09cae3590d5d5d5e9ac20e21d8ddcb9ec7bbd9302c84c2e9b6ba","last_reissued_at":"2026-07-05T03:04:06.178226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:06.178226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Dacheng Tao, Zefeng Ding, Zhiyin Shao","submitted_at":"2021-07-27T08:26:47Z","abstract_excerpt":"Text-to-image person re-identification (ReID) aims to search for images containing a person of interest using textual descriptions. However, due to the significant modality gap and the large intra-class variance in textual descriptions, text-to-image ReID remains a challenging problem. Accordingly, in this paper, we propose a Semantically Self-Aligned Network (SSAN) to handle the above problems. First, we propose a novel method that automatically extracts semantically aligned part-level features from the two modalities. Second, we design a multi-view non-local network that captures the relatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12666","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/2107.12666/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":"2107.12666","created_at":"2026-07-05T03:04:06.178282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12666v2","created_at":"2026-07-05T03:04:06.178282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12666","created_at":"2026-07-05T03:04:06.178282+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKMK2XN2XIE4","created_at":"2026-07-05T03:04:06.178282+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKMK2XN2XIE4VY2Z","created_at":"2026-07-05T03:04:06.178282+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKMK2XN2","created_at":"2026-07-05T03:04:06.178282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23282","citing_title":"Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search","ref_index":6,"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":4,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02242","citing_title":"Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27122","citing_title":"InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30458","citing_title":"Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22171","citing_title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27122","citing_title":"InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23282","citing_title":"Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08598","citing_title":"Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05504","citing_title":"Semantic Communication with an LLM-enabled Knowledge Base","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18376","citing_title":"Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI","json":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI.json","graph_json":"https://pith.science/api/pith-number/OKMK2XN2XIE4VY2ZBVOV2XU2YI/graph.json","events_json":"https://pith.science/api/pith-number/OKMK2XN2XIE4VY2ZBVOV2XU2YI/events.json","paper":"https://pith.science/paper/OKMK2XN2"},"agent_actions":{"view_html":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI","download_json":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI.json","view_paper":"https://pith.science/paper/OKMK2XN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12666&json=true","fetch_graph":"https://pith.science/api/pith-number/OKMK2XN2XIE4VY2ZBVOV2XU2YI/graph.json","fetch_events":"https://pith.science/api/pith-number/OKMK2XN2XIE4VY2ZBVOV2XU2YI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI/action/storage_attestation","attest_author":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI/action/author_attestation","sign_citation":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI/action/citation_signature","submit_replication":"https://pith.science/pith/OKMK2XN2XIE4VY2ZBVOV2XU2YI/action/replication_record"}},"created_at":"2026-07-05T03:04:06.178282+00:00","updated_at":"2026-07-05T03:04:06.178282+00:00"}