{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AG6VB757C2I4GT6CFL6RVKQL76","short_pith_number":"pith:AG6VB757","schema_version":"1.0","canonical_sha256":"01bd50ffbf1691c34fc22afd1aaa0bffbbb3d6d868948d03dc257b209e0fa5aa","source":{"kind":"arxiv","id":"1702.04710","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaoming Liu, Xi Yin","submitted_at":"2017-02-15T18:41:21Z","abstract_excerpt":"This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weight to each side task, which is a crucial problem in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specifi"},"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":"1702.04710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-15T18:41:21Z","cross_cats_sorted":[],"title_canon_sha256":"4212ef04b4aac76b8d1123f6a437a77d9834388b595620e3282f404b91669e59","abstract_canon_sha256":"34c903769b70539fc1434cf896d3f63ffa4a7599d3754d931c1b0ba9a608d447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:40.018115Z","signature_b64":"WTvFO0UIihLVgmd/4qPdO1O9pljTz6uNe0Sf22kuQuIaXf2na8nK9ENUgVlQUYdDybN6Icy0uIovo0vNTAmvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01bd50ffbf1691c34fc22afd1aaa0bffbbb3d6d868948d03dc257b209e0fa5aa","last_reissued_at":"2026-05-18T00:23:40.017463Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:40.017463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaoming Liu, Xi Yin","submitted_at":"2017-02-15T18:41:21Z","abstract_excerpt":"This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weight to each side task, which is a crucial problem in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.04710","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":""},"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":"1702.04710","created_at":"2026-05-18T00:23:40.017576+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.04710v2","created_at":"2026-05-18T00:23:40.017576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.04710","created_at":"2026-05-18T00:23:40.017576+00:00"},{"alias_kind":"pith_short_12","alias_value":"AG6VB757C2I4","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AG6VB757C2I4GT6C","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AG6VB757","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76","json":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76.json","graph_json":"https://pith.science/api/pith-number/AG6VB757C2I4GT6CFL6RVKQL76/graph.json","events_json":"https://pith.science/api/pith-number/AG6VB757C2I4GT6CFL6RVKQL76/events.json","paper":"https://pith.science/paper/AG6VB757"},"agent_actions":{"view_html":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76","download_json":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76.json","view_paper":"https://pith.science/paper/AG6VB757","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.04710&json=true","fetch_graph":"https://pith.science/api/pith-number/AG6VB757C2I4GT6CFL6RVKQL76/graph.json","fetch_events":"https://pith.science/api/pith-number/AG6VB757C2I4GT6CFL6RVKQL76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76/action/storage_attestation","attest_author":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76/action/author_attestation","sign_citation":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76/action/citation_signature","submit_replication":"https://pith.science/pith/AG6VB757C2I4GT6CFL6RVKQL76/action/replication_record"}},"created_at":"2026-05-18T00:23:40.017576+00:00","updated_at":"2026-05-18T00:23:40.017576+00:00"}