{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XDRKBGH2YB57G7YFYGCZB5SIO3","short_pith_number":"pith:XDRKBGH2","schema_version":"1.0","canonical_sha256":"b8e2a098fac07bf37f05c18590f64876cccb5bcdc7ea62580edfea77542dd26e","source":{"kind":"arxiv","id":"2403.12960","version":3},"attestation_state":"computed","paper":{"title":"FaceXFormer: A Unified Transformer for Facial Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kartik Narayan, Rama Chellappa, Vibashan VS, Vishal M. Patel","submitted_at":"2024-03-19T17:58:04Z","abstract_excerpt":"In this work, we introduce FaceXFormer, an end-to-end unified transformer model capable of performing ten facial analysis tasks within a single framework. These tasks include face parsing, landmark detection, head pose estimation, attribute prediction, age, gender, and race estimation, facial expression recognition, face recognition, and face visibility. Traditional face analysis approaches rely on task-specific architectures and pre-processing techniques, limiting scalability and integration. In contrast, FaceXFormer employs a transformer-based encoder-decoder architecture, where each task is"},"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":"2403.12960","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"8491f1cb1f322336badb7f12e2a3fa86e176331f52df117c0e07d933c8123f20","abstract_canon_sha256":"d344cf9ae103d5c140d226aa62fc55fd31be99ca64026fd64d27da027b5f5521"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:04.536846Z","signature_b64":"mlNdxt0DVcrEXO2OGIyHUGU2KMP6v7aBRJWnqrDM6HyamSgRDgYU4cDZ6XAIkjm/vrldSWKNwl7QznBGajSQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8e2a098fac07bf37f05c18590f64876cccb5bcdc7ea62580edfea77542dd26e","last_reissued_at":"2026-07-05T10:28:04.536183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:04.536183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaceXFormer: A Unified Transformer for Facial Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kartik Narayan, Rama Chellappa, Vibashan VS, Vishal M. Patel","submitted_at":"2024-03-19T17:58:04Z","abstract_excerpt":"In this work, we introduce FaceXFormer, an end-to-end unified transformer model capable of performing ten facial analysis tasks within a single framework. These tasks include face parsing, landmark detection, head pose estimation, attribute prediction, age, gender, and race estimation, facial expression recognition, face recognition, and face visibility. Traditional face analysis approaches rely on task-specific architectures and pre-processing techniques, limiting scalability and integration. In contrast, FaceXFormer employs a transformer-based encoder-decoder architecture, where each task is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12960","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/2403.12960/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":"2403.12960","created_at":"2026-07-05T10:28:04.536255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12960v3","created_at":"2026-07-05T10:28:04.536255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12960","created_at":"2026-07-05T10:28:04.536255+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDRKBGH2YB57","created_at":"2026-07-05T10:28:04.536255+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDRKBGH2YB57G7YF","created_at":"2026-07-05T10:28:04.536255+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDRKBGH2","created_at":"2026-07-05T10:28:04.536255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32040","citing_title":"FaceMoE: Mixture of Experts for Low-Resolution Face Recognition","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09158","citing_title":"FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10417","citing_title":"Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3","json":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3.json","graph_json":"https://pith.science/api/pith-number/XDRKBGH2YB57G7YFYGCZB5SIO3/graph.json","events_json":"https://pith.science/api/pith-number/XDRKBGH2YB57G7YFYGCZB5SIO3/events.json","paper":"https://pith.science/paper/XDRKBGH2"},"agent_actions":{"view_html":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3","download_json":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3.json","view_paper":"https://pith.science/paper/XDRKBGH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12960&json=true","fetch_graph":"https://pith.science/api/pith-number/XDRKBGH2YB57G7YFYGCZB5SIO3/graph.json","fetch_events":"https://pith.science/api/pith-number/XDRKBGH2YB57G7YFYGCZB5SIO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3/action/storage_attestation","attest_author":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3/action/author_attestation","sign_citation":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3/action/citation_signature","submit_replication":"https://pith.science/pith/XDRKBGH2YB57G7YFYGCZB5SIO3/action/replication_record"}},"created_at":"2026-07-05T10:28:04.536255+00:00","updated_at":"2026-07-05T10:28:04.536255+00:00"}