{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YYLRYO6OKNFKNRMD34RZBRL3QN","short_pith_number":"pith:YYLRYO6O","schema_version":"1.0","canonical_sha256":"c6171c3bce534aa6c583df2390c57b8378bd6cd0293f6047bc011da15d0995a9","source":{"kind":"arxiv","id":"2312.10921","version":1},"attestation_state":"computed","paper":{"title":"AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bo Peng, Dongze Li, Jing Dong, Kang Zhao, Tieniu Tan, Wei Wang, Yingya Zhang","submitted_at":"2023-12-18T04:14:38Z","abstract_excerpt":"Audio-driven talking head synthesis is a promising topic with wide applications in digital human, film making and virtual reality. Recent NeRF-based approaches have shown superiority in quality and fidelity compared to previous studies. However, when it comes to few-shot talking head generation, a practical scenario where only few seconds of talking video is available for one identity, two limitations emerge: 1) they either have no base model, which serves as a facial prior for fast convergence, or ignore the importance of audio when building the prior; 2) most of them overlook the degree of c"},"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":"2312.10921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-18T04:14:38Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"7e8a65f388f271cee35c66d95421bfb022d52856fc7d607a5be66104f328dd86","abstract_canon_sha256":"7fe077845030dd56a4b5a260ee9dff474d809125171eb2f51d88583d847db4b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:14.311390Z","signature_b64":"FAtZ0ESP61pPXLL9xcqkcOvEcp/f/euhYHX4gtb+rEnCIAZyH9SiDafGLcCBOHmhEOXKbvL6ZsDisbk64+X8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6171c3bce534aa6c583df2390c57b8378bd6cd0293f6047bc011da15d0995a9","last_reissued_at":"2026-07-05T07:25:14.310840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:14.310840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bo Peng, Dongze Li, Jing Dong, Kang Zhao, Tieniu Tan, Wei Wang, Yingya Zhang","submitted_at":"2023-12-18T04:14:38Z","abstract_excerpt":"Audio-driven talking head synthesis is a promising topic with wide applications in digital human, film making and virtual reality. Recent NeRF-based approaches have shown superiority in quality and fidelity compared to previous studies. However, when it comes to few-shot talking head generation, a practical scenario where only few seconds of talking video is available for one identity, two limitations emerge: 1) they either have no base model, which serves as a facial prior for fast convergence, or ignore the importance of audio when building the prior; 2) most of them overlook the degree of c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10921","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/2312.10921/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":"2312.10921","created_at":"2026-07-05T07:25:14.310898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10921v1","created_at":"2026-07-05T07:25:14.310898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10921","created_at":"2026-07-05T07:25:14.310898+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYLRYO6OKNFK","created_at":"2026-07-05T07:25:14.310898+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYLRYO6OKNFKNRMD","created_at":"2026-07-05T07:25:14.310898+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYLRYO6O","created_at":"2026-07-05T07:25:14.310898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.13442","citing_title":"EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN","json":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN.json","graph_json":"https://pith.science/api/pith-number/YYLRYO6OKNFKNRMD34RZBRL3QN/graph.json","events_json":"https://pith.science/api/pith-number/YYLRYO6OKNFKNRMD34RZBRL3QN/events.json","paper":"https://pith.science/paper/YYLRYO6O"},"agent_actions":{"view_html":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN","download_json":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN.json","view_paper":"https://pith.science/paper/YYLRYO6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10921&json=true","fetch_graph":"https://pith.science/api/pith-number/YYLRYO6OKNFKNRMD34RZBRL3QN/graph.json","fetch_events":"https://pith.science/api/pith-number/YYLRYO6OKNFKNRMD34RZBRL3QN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN/action/storage_attestation","attest_author":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN/action/author_attestation","sign_citation":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN/action/citation_signature","submit_replication":"https://pith.science/pith/YYLRYO6OKNFKNRMD34RZBRL3QN/action/replication_record"}},"created_at":"2026-07-05T07:25:14.310898+00:00","updated_at":"2026-07-05T07:25:14.310898+00:00"}