{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VYQZPVGI7S3P3QUCSJYMLA5M72","short_pith_number":"pith:VYQZPVGI","schema_version":"1.0","canonical_sha256":"ae2197d4c8fcb6fdc2829270c583acfe9a4124377989701275bfd925532584ed","source":{"kind":"arxiv","id":"2112.03109","version":3},"attestation_state":"computed","paper":{"title":"General Facial Representation Learning in a Visual-Linguistic Manner","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dong Chen, Dongdong Chen, Fang Wen, Hao Yang, Jianmin Bao, Lu Yuan, Ming Zeng, Ting Zhang, Yangyu Huang, Yinglin Zheng","submitted_at":"2021-12-06T15:22:05Z","abstract_excerpt":"How to learn a universal facial representation that boosts all face analysis tasks? This paper takes one step toward this goal. In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner. On one hand, the framework involves a contrastive loss to learn high-level semantic meaning from image-text pairs. On the other hand, we propose exploring low-level information simultaneously to further enhance the face representation, by adding a masked image mod"},"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":"2112.03109","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-06T15:22:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"38b532de6e06adc15c8a5a84d709681259e888697b16a71b974c4a1051699af3","abstract_canon_sha256":"7c7a1cc98834f873bc3f61e8d6591c98398fbdc489992a2b1e650a0a412fd33e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:38.855046Z","signature_b64":"DLcme+uTXZgoCbkC8t+Hh0INMIUqoHpl01fFrBNwhYRiF0wIoOFiAQ1KWgFBhJZ+a10PNfVXp6J1b2vRLqOmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae2197d4c8fcb6fdc2829270c583acfe9a4124377989701275bfd925532584ed","last_reissued_at":"2026-07-05T04:10:38.854536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:38.854536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General Facial Representation Learning in a Visual-Linguistic Manner","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dong Chen, Dongdong Chen, Fang Wen, Hao Yang, Jianmin Bao, Lu Yuan, Ming Zeng, Ting Zhang, Yangyu Huang, Yinglin Zheng","submitted_at":"2021-12-06T15:22:05Z","abstract_excerpt":"How to learn a universal facial representation that boosts all face analysis tasks? This paper takes one step toward this goal. In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner. On one hand, the framework involves a contrastive loss to learn high-level semantic meaning from image-text pairs. On the other hand, we propose exploring low-level information simultaneously to further enhance the face representation, by adding a masked image mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03109","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/2112.03109/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":"2112.03109","created_at":"2026-07-05T04:10:38.854589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03109v3","created_at":"2026-07-05T04:10:38.854589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03109","created_at":"2026-07-05T04:10:38.854589+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYQZPVGI7S3P","created_at":"2026-07-05T04:10:38.854589+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYQZPVGI7S3P3QUC","created_at":"2026-07-05T04:10:38.854589+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYQZPVGI","created_at":"2026-07-05T04:10:38.854589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.02777","citing_title":"PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2210.08402","citing_title":"LAION-5B: An open large-scale dataset for training next generation image-text models","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25352","citing_title":"GraphPL: Leveraging GNN for Efficient and Robust Modalities Imputation in Patchwork Learning","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72","json":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72.json","graph_json":"https://pith.science/api/pith-number/VYQZPVGI7S3P3QUCSJYMLA5M72/graph.json","events_json":"https://pith.science/api/pith-number/VYQZPVGI7S3P3QUCSJYMLA5M72/events.json","paper":"https://pith.science/paper/VYQZPVGI"},"agent_actions":{"view_html":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72","download_json":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72.json","view_paper":"https://pith.science/paper/VYQZPVGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03109&json=true","fetch_graph":"https://pith.science/api/pith-number/VYQZPVGI7S3P3QUCSJYMLA5M72/graph.json","fetch_events":"https://pith.science/api/pith-number/VYQZPVGI7S3P3QUCSJYMLA5M72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72/action/storage_attestation","attest_author":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72/action/author_attestation","sign_citation":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72/action/citation_signature","submit_replication":"https://pith.science/pith/VYQZPVGI7S3P3QUCSJYMLA5M72/action/replication_record"}},"created_at":"2026-07-05T04:10:38.854589+00:00","updated_at":"2026-07-05T04:10:38.854589+00:00"}