{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IEK2N6SQOGLY2KCVV6RHGKREK4","short_pith_number":"pith:IEK2N6SQ","schema_version":"1.0","canonical_sha256":"4115a6fa5071978d2855afa2732a245733bce6efe3faa0333b9f50cbf8d289af","source":{"kind":"arxiv","id":"2007.04514","version":2},"attestation_state":"computed","paper":{"title":"Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel P.K. Lun, Jun Xiao, Kin-man Lam, Rui Zhao, Tianshan Liu","submitted_at":"2020-07-09T02:29:34Z","abstract_excerpt":"Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between different tasks, which may lead to task interference when training the multi-task networks. To address this problem, we propose a novel selective feature-sharing method, and establish a multi-task network for facial expression recognition and facial expression synthesis. The proposed method can effectively transfer beneficial features between different tasks,"},"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":"2007.04514","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-09T02:29:34Z","cross_cats_sorted":[],"title_canon_sha256":"82bc49f08b403d6a27d45c1c6cbcb4b92e662a0234b590c21767a9240252a112","abstract_canon_sha256":"bdf03151e5ce309ebe1edeb11e43745d48562c5fea40fe76ac756bfce628cfe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:25.962674Z","signature_b64":"x/YWxb7nespikH3I6l/w1clix2fqAhXeNnhLpnLW3nBXjTJxCuTyV7DC74KrS1WFN6iRHX1HdZBXv2zCL2hnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4115a6fa5071978d2855afa2732a245733bce6efe3faa0333b9f50cbf8d289af","last_reissued_at":"2026-07-05T03:35:25.962268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:25.962268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel P.K. Lun, Jun Xiao, Kin-man Lam, Rui Zhao, Tianshan Liu","submitted_at":"2020-07-09T02:29:34Z","abstract_excerpt":"Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between different tasks, which may lead to task interference when training the multi-task networks. To address this problem, we propose a novel selective feature-sharing method, and establish a multi-task network for facial expression recognition and facial expression synthesis. The proposed method can effectively transfer beneficial features between different tasks,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04514","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/2007.04514/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":"2007.04514","created_at":"2026-07-05T03:35:25.962327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04514v2","created_at":"2026-07-05T03:35:25.962327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04514","created_at":"2026-07-05T03:35:25.962327+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEK2N6SQOGLY","created_at":"2026-07-05T03:35:25.962327+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEK2N6SQOGLY2KCV","created_at":"2026-07-05T03:35:25.962327+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEK2N6SQ","created_at":"2026-07-05T03:35:25.962327+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/IEK2N6SQOGLY2KCVV6RHGKREK4","json":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4.json","graph_json":"https://pith.science/api/pith-number/IEK2N6SQOGLY2KCVV6RHGKREK4/graph.json","events_json":"https://pith.science/api/pith-number/IEK2N6SQOGLY2KCVV6RHGKREK4/events.json","paper":"https://pith.science/paper/IEK2N6SQ"},"agent_actions":{"view_html":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4","download_json":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4.json","view_paper":"https://pith.science/paper/IEK2N6SQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04514&json=true","fetch_graph":"https://pith.science/api/pith-number/IEK2N6SQOGLY2KCVV6RHGKREK4/graph.json","fetch_events":"https://pith.science/api/pith-number/IEK2N6SQOGLY2KCVV6RHGKREK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4/action/storage_attestation","attest_author":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4/action/author_attestation","sign_citation":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4/action/citation_signature","submit_replication":"https://pith.science/pith/IEK2N6SQOGLY2KCVV6RHGKREK4/action/replication_record"}},"created_at":"2026-07-05T03:35:25.962327+00:00","updated_at":"2026-07-05T03:35:25.962327+00:00"}