{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EZYZ4PAUUPE62NKSUPEZXQDWTQ","short_pith_number":"pith:EZYZ4PAU","schema_version":"1.0","canonical_sha256":"26719e3c14a3c9ed3552a3c99bc0769c228ab1da39864c7ada5bd7ad9b514695","source":{"kind":"arxiv","id":"2103.14803","version":2},"attestation_state":"computed","paper":{"title":"Face Transformer for Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weihong Deng, Yaoyao Zhong","submitted_at":"2021-03-27T03:53:29Z","abstract_excerpt":"Recently there has been a growing interest in Transformer not only in NLP but also in computer vision. We wonder if transformer can be used in face recognition and whether it is better than CNNs. Therefore, we investigate the performance of Transformer models in face recognition. Considering the original Transformer may neglect the inter-patch information, we modify the patch generation process and make the tokens with sliding patches which overlaps with each others. The models are trained on CASIA-WebFace and MS-Celeb-1M databases, and evaluated on several mainstream benchmarks, including LFW"},"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":"2103.14803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-27T03:53:29Z","cross_cats_sorted":[],"title_canon_sha256":"b1a1a27d2575494507853b3ec4ff724885ff4800bbb1a03dfeaeb832612cb849","abstract_canon_sha256":"95566b55586391cda2db44419f3b4f8b6524af504dec36155e577b0ffd9b0118"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:23.361837Z","signature_b64":"YLWGBV7gKzw8kt1/XvAS5zPUh1PGC5shuAjk7Qqcb7nCX7aI2/AnsGPAX6z2Ppc3tfdiOE92B1mJM5Wen5HtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26719e3c14a3c9ed3552a3c99bc0769c228ab1da39864c7ada5bd7ad9b514695","last_reissued_at":"2026-07-05T02:31:23.361344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:23.361344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Face Transformer for Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weihong Deng, Yaoyao Zhong","submitted_at":"2021-03-27T03:53:29Z","abstract_excerpt":"Recently there has been a growing interest in Transformer not only in NLP but also in computer vision. We wonder if transformer can be used in face recognition and whether it is better than CNNs. Therefore, we investigate the performance of Transformer models in face recognition. Considering the original Transformer may neglect the inter-patch information, we modify the patch generation process and make the tokens with sliding patches which overlaps with each others. The models are trained on CASIA-WebFace and MS-Celeb-1M databases, and evaluated on several mainstream benchmarks, including LFW"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14803","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/2103.14803/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":"2103.14803","created_at":"2026-07-05T02:31:23.361403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14803v2","created_at":"2026-07-05T02:31:23.361403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14803","created_at":"2026-07-05T02:31:23.361403+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZYZ4PAUUPE6","created_at":"2026-07-05T02:31:23.361403+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZYZ4PAUUPE62NKS","created_at":"2026-07-05T02:31:23.361403+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZYZ4PAU","created_at":"2026-07-05T02:31:23.361403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12036","citing_title":"Vision Transformers for Face Recognition Need More Registers","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12023","citing_title":"ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12686","citing_title":"BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09127","citing_title":"FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ","json":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ.json","graph_json":"https://pith.science/api/pith-number/EZYZ4PAUUPE62NKSUPEZXQDWTQ/graph.json","events_json":"https://pith.science/api/pith-number/EZYZ4PAUUPE62NKSUPEZXQDWTQ/events.json","paper":"https://pith.science/paper/EZYZ4PAU"},"agent_actions":{"view_html":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ","download_json":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ.json","view_paper":"https://pith.science/paper/EZYZ4PAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14803&json=true","fetch_graph":"https://pith.science/api/pith-number/EZYZ4PAUUPE62NKSUPEZXQDWTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EZYZ4PAUUPE62NKSUPEZXQDWTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ/action/storage_attestation","attest_author":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ/action/author_attestation","sign_citation":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ/action/citation_signature","submit_replication":"https://pith.science/pith/EZYZ4PAUUPE62NKSUPEZXQDWTQ/action/replication_record"}},"created_at":"2026-07-05T02:31:23.361403+00:00","updated_at":"2026-07-05T02:31:23.361403+00:00"}