{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3U5URDKAM6W4XQ4KSGYIQMF5JJ","short_pith_number":"pith:3U5URDKA","schema_version":"1.0","canonical_sha256":"dd3b488d4067adcbc38a91b08830bd4a7343c3c770ab5638b24dbdb301c59561","source":{"kind":"arxiv","id":"2011.11953","version":3},"attestation_state":"computed","paper":{"title":"DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cuicui Kang, Fang Zhao, Ling Shao, Shengcai Liao, Wenhao Wang","submitted_at":"2020-11-24T08:15:53Z","abstract_excerpt":"Existing person re-identification models often have low generalizability, which is mostly due to limited availability of large-scale labeled data in training. However, labeling large-scale training data is very expensive and time-consuming, while large-scale synthetic dataset shows promising value in learning generalizable person re-identification models. Therefore, in this paper a novel and practical person re-identification task is proposed,i.e. how to use labeled synthetic dataset and unlabeled real-world dataset to train a universal model. In this way, human annotations are no longer requi"},"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":"2011.11953","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-24T08:15:53Z","cross_cats_sorted":[],"title_canon_sha256":"0dc17c0c91f763ba8e899c6f37ff0b764fc19e9773712e3635807b0e00666aac","abstract_canon_sha256":"f06afc1fcbb228e1b466c4e7dd258096b564ea310f105faabe86ce8819737f53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:40.470949Z","signature_b64":"R7gy/jhHuH/dU8+h6u1b9BZCZuwILuPwfF2xI7+nyaCVwqgPjXNdC94uGUzZ7oLvaIgMh3pyfHlOdmBpmXksBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd3b488d4067adcbc38a91b08830bd4a7343c3c770ab5638b24dbdb301c59561","last_reissued_at":"2026-07-05T03:24:40.470518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:40.470518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cuicui Kang, Fang Zhao, Ling Shao, Shengcai Liao, Wenhao Wang","submitted_at":"2020-11-24T08:15:53Z","abstract_excerpt":"Existing person re-identification models often have low generalizability, which is mostly due to limited availability of large-scale labeled data in training. However, labeling large-scale training data is very expensive and time-consuming, while large-scale synthetic dataset shows promising value in learning generalizable person re-identification models. Therefore, in this paper a novel and practical person re-identification task is proposed,i.e. how to use labeled synthetic dataset and unlabeled real-world dataset to train a universal model. In this way, human annotations are no longer requi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11953","kind":"arxiv","version":3},"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/2011.11953/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":"2011.11953","created_at":"2026-07-05T03:24:40.470585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.11953v3","created_at":"2026-07-05T03:24:40.470585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11953","created_at":"2026-07-05T03:24:40.470585+00:00"},{"alias_kind":"pith_short_12","alias_value":"3U5URDKAM6W4","created_at":"2026-07-05T03:24:40.470585+00:00"},{"alias_kind":"pith_short_16","alias_value":"3U5URDKAM6W4XQ4K","created_at":"2026-07-05T03:24:40.470585+00:00"},{"alias_kind":"pith_short_8","alias_value":"3U5URDKA","created_at":"2026-07-05T03:24:40.470585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04006","citing_title":"Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ","json":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ.json","graph_json":"https://pith.science/api/pith-number/3U5URDKAM6W4XQ4KSGYIQMF5JJ/graph.json","events_json":"https://pith.science/api/pith-number/3U5URDKAM6W4XQ4KSGYIQMF5JJ/events.json","paper":"https://pith.science/paper/3U5URDKA"},"agent_actions":{"view_html":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ","download_json":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ.json","view_paper":"https://pith.science/paper/3U5URDKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.11953&json=true","fetch_graph":"https://pith.science/api/pith-number/3U5URDKAM6W4XQ4KSGYIQMF5JJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3U5URDKAM6W4XQ4KSGYIQMF5JJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ/action/storage_attestation","attest_author":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ/action/author_attestation","sign_citation":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ/action/citation_signature","submit_replication":"https://pith.science/pith/3U5URDKAM6W4XQ4KSGYIQMF5JJ/action/replication_record"}},"created_at":"2026-07-05T03:24:40.470585+00:00","updated_at":"2026-07-05T03:24:40.470585+00:00"}