{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PRPA2IXR6ZYTEMLVT76H5SERKJ","short_pith_number":"pith:PRPA2IXR","schema_version":"1.0","canonical_sha256":"7c5e0d22f1f6713231759ffc7ec89152489bc365ab663d30b253dc60dd3af9b0","source":{"kind":"arxiv","id":"2409.10281","version":1},"attestation_state":"computed","paper":{"title":"DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Changyin Zhou, Dan Xu, Fa-Ting Hong, Fei Yu, Yu Li, Yunfei Liu","submitted_at":"2024-09-16T13:44:20Z","abstract_excerpt":"Audio-driven talking head synthesis strives to generate lifelike video portraits from provided audio. The diffusion model, recognized for its superior quality and robust generalization, has been explored for this task. However, establishing a robust correspondence between temporal audio cues and corresponding spatial facial expressions with diffusion models remains a significant challenge in talking head generation. To bridge this gap, we present DreamHead, a hierarchical diffusion framework that learns spatial-temporal correspondences in talking head synthesis without compromising the model's"},"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":"2409.10281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-16T13:44:20Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"24d9213420ec73b18a3ef35969ebf9e1cfbd633d618bbefd0c1c5246110fd27c","abstract_canon_sha256":"f614222c833f49b20773c0ab752a08860194c4a90bb2a4490f6e62edfc91994d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:37.831232Z","signature_b64":"9LlCffzdvk1RbQL+Z5nm+l0UPfsOsRd6GB+Pa0lZZgpXm32dh5qsVy/LefirF6uNDMEPCpz0RC/nVzfH3PtJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c5e0d22f1f6713231759ffc7ec89152489bc365ab663d30b253dc60dd3af9b0","last_reissued_at":"2026-07-05T09:07:37.830699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:37.830699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Changyin Zhou, Dan Xu, Fa-Ting Hong, Fei Yu, Yu Li, Yunfei Liu","submitted_at":"2024-09-16T13:44:20Z","abstract_excerpt":"Audio-driven talking head synthesis strives to generate lifelike video portraits from provided audio. The diffusion model, recognized for its superior quality and robust generalization, has been explored for this task. However, establishing a robust correspondence between temporal audio cues and corresponding spatial facial expressions with diffusion models remains a significant challenge in talking head generation. To bridge this gap, we present DreamHead, a hierarchical diffusion framework that learns spatial-temporal correspondences in talking head synthesis without compromising the model's"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10281","kind":"arxiv","version":1},"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/2409.10281/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":"2409.10281","created_at":"2026-07-05T09:07:37.830757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10281v1","created_at":"2026-07-05T09:07:37.830757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10281","created_at":"2026-07-05T09:07:37.830757+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRPA2IXR6ZYT","created_at":"2026-07-05T09:07:37.830757+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRPA2IXR6ZYTEMLV","created_at":"2026-07-05T09:07:37.830757+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRPA2IXR","created_at":"2026-07-05T09:07:37.830757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17290","citing_title":"Free-viewpoint Human Animation with Pose-correlated Reference Selection","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ","json":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ.json","graph_json":"https://pith.science/api/pith-number/PRPA2IXR6ZYTEMLVT76H5SERKJ/graph.json","events_json":"https://pith.science/api/pith-number/PRPA2IXR6ZYTEMLVT76H5SERKJ/events.json","paper":"https://pith.science/paper/PRPA2IXR"},"agent_actions":{"view_html":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ","download_json":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ.json","view_paper":"https://pith.science/paper/PRPA2IXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10281&json=true","fetch_graph":"https://pith.science/api/pith-number/PRPA2IXR6ZYTEMLVT76H5SERKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PRPA2IXR6ZYTEMLVT76H5SERKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ/action/storage_attestation","attest_author":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ/action/author_attestation","sign_citation":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ/action/citation_signature","submit_replication":"https://pith.science/pith/PRPA2IXR6ZYTEMLVT76H5SERKJ/action/replication_record"}},"created_at":"2026-07-05T09:07:37.830757+00:00","updated_at":"2026-07-05T09:07:37.830757+00:00"}