{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J5IGZFNJERUABUHSAYI27D4HCK","short_pith_number":"pith:J5IGZFNJ","schema_version":"1.0","canonical_sha256":"4f506c95a9246800d0f20611af8f8712bdf7001fc7d0f36ba44f6fd869fea0b5","source":{"kind":"arxiv","id":"2205.15278","version":3},"attestation_state":"computed","paper":{"title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Xu, Hang Zhou, Kaisiyuan Wang, Qianyi Wu, Wayne Wu, Xinya Ji, Xun Cao","submitted_at":"2022-05-30T17:39:45Z","abstract_excerpt":"Although significant progress has been made to audio-driven talking face generation, existing methods either neglect facial emotion or cannot be applied to arbitrary subjects. In this paper, we propose the Emotion-Aware Motion Model (EAMM) to generate one-shot emotional talking faces by involving an emotion source video. Specifically, we first propose an Audio2Facial-Dynamics module, which renders talking faces from audio-driven unsupervised zero- and first-order key-points motion. Then through exploring the motion model's properties, we further propose an Implicit Emotion Displacement Learner"},"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":"2205.15278","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T17:39:45Z","cross_cats_sorted":[],"title_canon_sha256":"b8bc5ccd9b20c4a60e53964dd6701db457d67c2f1e49be7f450fb8185da1b5df","abstract_canon_sha256":"d1a33f66df859b427640820746b13c91d5b100097c8e4819e63b86bdfec4b403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:16.719485Z","signature_b64":"NnrD0ActkFPfVbaIMNck+FQSSNiU98qRz06DH+77ziCqe4fIqPVe6yEoZDCOuIxmEoJ2MdEHAEnjDd5sj5X5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f506c95a9246800d0f20611af8f8712bdf7001fc7d0f36ba44f6fd869fea0b5","last_reissued_at":"2026-07-05T05:00:16.718935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:16.718935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Xu, Hang Zhou, Kaisiyuan Wang, Qianyi Wu, Wayne Wu, Xinya Ji, Xun Cao","submitted_at":"2022-05-30T17:39:45Z","abstract_excerpt":"Although significant progress has been made to audio-driven talking face generation, existing methods either neglect facial emotion or cannot be applied to arbitrary subjects. In this paper, we propose the Emotion-Aware Motion Model (EAMM) to generate one-shot emotional talking faces by involving an emotion source video. Specifically, we first propose an Audio2Facial-Dynamics module, which renders talking faces from audio-driven unsupervised zero- and first-order key-points motion. Then through exploring the motion model's properties, we further propose an Implicit Emotion Displacement Learner"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15278","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/2205.15278/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":"2205.15278","created_at":"2026-07-05T05:00:16.719001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15278v3","created_at":"2026-07-05T05:00:16.719001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15278","created_at":"2026-07-05T05:00:16.719001+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5IGZFNJERUA","created_at":"2026-07-05T05:00:16.719001+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5IGZFNJERUABUHS","created_at":"2026-07-05T05:00:16.719001+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5IGZFNJ","created_at":"2026-07-05T05:00:16.719001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.09534","citing_title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK","json":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK.json","graph_json":"https://pith.science/api/pith-number/J5IGZFNJERUABUHSAYI27D4HCK/graph.json","events_json":"https://pith.science/api/pith-number/J5IGZFNJERUABUHSAYI27D4HCK/events.json","paper":"https://pith.science/paper/J5IGZFNJ"},"agent_actions":{"view_html":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK","download_json":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK.json","view_paper":"https://pith.science/paper/J5IGZFNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15278&json=true","fetch_graph":"https://pith.science/api/pith-number/J5IGZFNJERUABUHSAYI27D4HCK/graph.json","fetch_events":"https://pith.science/api/pith-number/J5IGZFNJERUABUHSAYI27D4HCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK/action/storage_attestation","attest_author":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK/action/author_attestation","sign_citation":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK/action/citation_signature","submit_replication":"https://pith.science/pith/J5IGZFNJERUABUHSAYI27D4HCK/action/replication_record"}},"created_at":"2026-07-05T05:00:16.719001+00:00","updated_at":"2026-07-05T05:00:16.719001+00:00"}