{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3WT52QVBA2QM43LKPF26AWRAFZ","short_pith_number":"pith:3WT52QVB","schema_version":"1.0","canonical_sha256":"dda7dd42a106a0ce6d6a7975e05a202e4370ae0ff441bb2fcaf082e1e30526cf","source":{"kind":"arxiv","id":"2312.01841","version":2},"attestation_state":"computed","paper":{"title":"VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Daiheng Gao, Hao Zhu, Kangneng Zhou, Liefeng Bo, Longhao Zhang, Peng Zhang, Xinya Ji, Xun Cao, Xusen Sun","submitted_at":"2023-12-04T12:25:37Z","abstract_excerpt":"Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, expressive facial expressions, natural head pose generation, and high video quality. However, no model has yet led or tied on all these metrics due to the one-to-many mapping between audio and motion. In this paper, we propose VividTalk, a two-stage generic framework that supports generating high-visual quality talking head videos with all the above properties. Specifically, in the first stage, we map the audio to mesh by learning two motions, including non-rigid expressi"},"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":"2312.01841","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T12:25:37Z","cross_cats_sorted":[],"title_canon_sha256":"4397ca8d74fccf07284f9f775744da011f384242ac2c01423e65975bd4182137","abstract_canon_sha256":"84949096585e57aaa42f9f7587f72d9529c00fa3ad3fe8132d5921d3edcbb479"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:13.091094Z","signature_b64":"EhnZQ7TPOcf8KY3zbmYde7PQtfm/vQatkC2vdcyvjD7IAtmAgCkemslNs78F7+yGnctBkTKfcik7CO58z6IyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dda7dd42a106a0ce6d6a7975e05a202e4370ae0ff441bb2fcaf082e1e30526cf","last_reissued_at":"2026-07-05T07:21:13.090608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:13.090608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Daiheng Gao, Hao Zhu, Kangneng Zhou, Liefeng Bo, Longhao Zhang, Peng Zhang, Xinya Ji, Xun Cao, Xusen Sun","submitted_at":"2023-12-04T12:25:37Z","abstract_excerpt":"Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, expressive facial expressions, natural head pose generation, and high video quality. However, no model has yet led or tied on all these metrics due to the one-to-many mapping between audio and motion. In this paper, we propose VividTalk, a two-stage generic framework that supports generating high-visual quality talking head videos with all the above properties. Specifically, in the first stage, we map the audio to mesh by learning two motions, including non-rigid expressi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01841","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/2312.01841/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":"2312.01841","created_at":"2026-07-05T07:21:13.090670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01841v2","created_at":"2026-07-05T07:21:13.090670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01841","created_at":"2026-07-05T07:21:13.090670+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WT52QVBA2QM","created_at":"2026-07-05T07:21:13.090670+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WT52QVBA2QM43LK","created_at":"2026-07-05T07:21:13.090670+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WT52QVB","created_at":"2026-07-05T07:21:13.090670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.16748","citing_title":"Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2411.09209","citing_title":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ","json":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ.json","graph_json":"https://pith.science/api/pith-number/3WT52QVBA2QM43LKPF26AWRAFZ/graph.json","events_json":"https://pith.science/api/pith-number/3WT52QVBA2QM43LKPF26AWRAFZ/events.json","paper":"https://pith.science/paper/3WT52QVB"},"agent_actions":{"view_html":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ","download_json":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ.json","view_paper":"https://pith.science/paper/3WT52QVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01841&json=true","fetch_graph":"https://pith.science/api/pith-number/3WT52QVBA2QM43LKPF26AWRAFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3WT52QVBA2QM43LKPF26AWRAFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ/action/storage_attestation","attest_author":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ/action/author_attestation","sign_citation":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ/action/citation_signature","submit_replication":"https://pith.science/pith/3WT52QVBA2QM43LKPF26AWRAFZ/action/replication_record"}},"created_at":"2026-07-05T07:21:13.090670+00:00","updated_at":"2026-07-05T07:21:13.090670+00:00"}