{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U2SQS3FEMEYSSWX2URY73CUO3A","short_pith_number":"pith:U2SQS3FE","schema_version":"1.0","canonical_sha256":"a6a5096ca46131295afaa471fd8a8ed82bf566ccd39e2e40ae490b570484b38d","source":{"kind":"arxiv","id":"2310.00434","version":2},"attestation_state":"computed","paper":{"title":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jenny Sheng, Matthieu Lin, Minjing Yu, Sheng Ye, Tian Lv, Yong-jin Liu, Yu-Hui Wen, Zhiyao Sun","submitted_at":"2023-09-30T17:01:18Z","abstract_excerpt":"The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the corresponding natural facial motion. However, existing methods either employ a deterministic model for speech-to-motion mapping or encode the style using a one-hot encoding scheme. Notably, the one-hot encoding approach fails to capture the complexity of the style and thus limits generalization ability. In this paper, we propose DiffPoseTalk, a generative framework based on the diffusion model combined with a style enco"},"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":"2310.00434","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-30T17:01:18Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"221acc1992d0cdd44c5dc8af51b80437a4138cfe7e60214802d550ca040cf904","abstract_canon_sha256":"e7fa8da7d5cd82abe61d7e91c469af03a5f6074b54f69039ee0170189f8ee274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:44.387122Z","signature_b64":"nc4pW+5u9mPq+BhN/nfO6Ly7HvWWOvUUomLGkyPTnn84p+1cLD+xNdXiftsh49TDrbm9CBLNjAvwMyaXRQWqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6a5096ca46131295afaa471fd8a8ed82bf566ccd39e2e40ae490b570484b38d","last_reissued_at":"2026-07-05T08:18:44.386621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:44.386621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jenny Sheng, Matthieu Lin, Minjing Yu, Sheng Ye, Tian Lv, Yong-jin Liu, Yu-Hui Wen, Zhiyao Sun","submitted_at":"2023-09-30T17:01:18Z","abstract_excerpt":"The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the corresponding natural facial motion. However, existing methods either employ a deterministic model for speech-to-motion mapping or encode the style using a one-hot encoding scheme. Notably, the one-hot encoding approach fails to capture the complexity of the style and thus limits generalization ability. In this paper, we propose DiffPoseTalk, a generative framework based on the diffusion model combined with a style enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00434","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/2310.00434/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":"2310.00434","created_at":"2026-07-05T08:18:44.386680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00434v2","created_at":"2026-07-05T08:18:44.386680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00434","created_at":"2026-07-05T08:18:44.386680+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2SQS3FEMEYS","created_at":"2026-07-05T08:18:44.386680+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2SQS3FEMEYSSWX2","created_at":"2026-07-05T08:18:44.386680+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2SQS3FE","created_at":"2026-07-05T08:18:44.386680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.11321","citing_title":"KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17211","citing_title":"EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A","json":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A.json","graph_json":"https://pith.science/api/pith-number/U2SQS3FEMEYSSWX2URY73CUO3A/graph.json","events_json":"https://pith.science/api/pith-number/U2SQS3FEMEYSSWX2URY73CUO3A/events.json","paper":"https://pith.science/paper/U2SQS3FE"},"agent_actions":{"view_html":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A","download_json":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A.json","view_paper":"https://pith.science/paper/U2SQS3FE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00434&json=true","fetch_graph":"https://pith.science/api/pith-number/U2SQS3FEMEYSSWX2URY73CUO3A/graph.json","fetch_events":"https://pith.science/api/pith-number/U2SQS3FEMEYSSWX2URY73CUO3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A/action/storage_attestation","attest_author":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A/action/author_attestation","sign_citation":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A/action/citation_signature","submit_replication":"https://pith.science/pith/U2SQS3FEMEYSSWX2URY73CUO3A/action/replication_record"}},"created_at":"2026-07-05T08:18:44.386680+00:00","updated_at":"2026-07-05T08:18:44.386680+00:00"}