{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RXCOKHVKCB6EUETS3HIDQGMGFN","short_pith_number":"pith:RXCOKHVK","schema_version":"1.0","canonical_sha256":"8dc4e51eaa107c4a1272d9d03819862b6843c53483ecfafa2869192162fadc34","source":{"kind":"arxiv","id":"2101.08783","version":3},"attestation_state":"computed","paper":{"title":"A Person Re-identification Data Augmentation Method with Adversarial Defense Effect","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Weng, Feng Ye, Liwen Chen, Yifan Luo, Yunpeng Gong, Zhiyong Zeng","submitted_at":"2021-01-21T12:07:57Z","abstract_excerpt":"The security of the Person Re-identification(ReID) model plays a decisive role in the application of ReID. However, deep neural networks have been shown to be vulnerable, and adding undetectable adversarial perturbations to clean images can trick deep neural networks that perform well in clean images. We propose a ReID multi-modal data augmentation method with adversarial defense effect: 1) Grayscale Patch Replacement, it consists of Local Grayscale Patch Replacement(LGPR) and Global Grayscale Patch Replacement(GGPR). This method can not only improve the accuracy of the model, but also help th"},"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":"2101.08783","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-21T12:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"b606f142e9eeec2e826630bdba3ff1a9ec199d644374d62f54766cb16e56d5ee","abstract_canon_sha256":"2da3a4cdc3b5114eb57c24bfbef4016d0d7282f69cbc05dc7ed3e33976043707"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:57.156693Z","signature_b64":"e2p0Z/EkPOdamwsb89Td2mVf41Toa8fWijZKodhylsIA/42XuKjuKV/E4JDdE7x0nTYkPxYVHvL7awvzWvtDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc4e51eaa107c4a1272d9d03819862b6843c53483ecfafa2869192162fadc34","last_reissued_at":"2026-07-05T02:29:57.156215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:57.156215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Person Re-identification Data Augmentation Method with Adversarial Defense Effect","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Weng, Feng Ye, Liwen Chen, Yifan Luo, Yunpeng Gong, Zhiyong Zeng","submitted_at":"2021-01-21T12:07:57Z","abstract_excerpt":"The security of the Person Re-identification(ReID) model plays a decisive role in the application of ReID. However, deep neural networks have been shown to be vulnerable, and adding undetectable adversarial perturbations to clean images can trick deep neural networks that perform well in clean images. We propose a ReID multi-modal data augmentation method with adversarial defense effect: 1) Grayscale Patch Replacement, it consists of Local Grayscale Patch Replacement(LGPR) and Global Grayscale Patch Replacement(GGPR). This method can not only improve the accuracy of the model, but also help th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08783","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/2101.08783/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":"2101.08783","created_at":"2026-07-05T02:29:57.156273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.08783v3","created_at":"2026-07-05T02:29:57.156273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08783","created_at":"2026-07-05T02:29:57.156273+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXCOKHVKCB6E","created_at":"2026-07-05T02:29:57.156273+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXCOKHVKCB6EUETS","created_at":"2026-07-05T02:29:57.156273+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXCOKHVK","created_at":"2026-07-05T02:29:57.156273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18047","citing_title":"GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN","json":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN.json","graph_json":"https://pith.science/api/pith-number/RXCOKHVKCB6EUETS3HIDQGMGFN/graph.json","events_json":"https://pith.science/api/pith-number/RXCOKHVKCB6EUETS3HIDQGMGFN/events.json","paper":"https://pith.science/paper/RXCOKHVK"},"agent_actions":{"view_html":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN","download_json":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN.json","view_paper":"https://pith.science/paper/RXCOKHVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.08783&json=true","fetch_graph":"https://pith.science/api/pith-number/RXCOKHVKCB6EUETS3HIDQGMGFN/graph.json","fetch_events":"https://pith.science/api/pith-number/RXCOKHVKCB6EUETS3HIDQGMGFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN/action/storage_attestation","attest_author":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN/action/author_attestation","sign_citation":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN/action/citation_signature","submit_replication":"https://pith.science/pith/RXCOKHVKCB6EUETS3HIDQGMGFN/action/replication_record"}},"created_at":"2026-07-05T02:29:57.156273+00:00","updated_at":"2026-07-05T02:29:57.156273+00:00"}