{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:65WMIYQD6VER5IXBEW5JS5WVB3","short_pith_number":"pith:65WMIYQD","schema_version":"1.0","canonical_sha256":"f76cc46203f5491ea2e125ba9976d50ef7cb550a4dc9ae9bdb44caeedd72b6f1","source":{"kind":"arxiv","id":"1805.09313","version":4},"attestation_state":"computed","paper":{"title":"End-to-End Speech-Driven Facial Animation with Temporal GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Konstantinos Vougioukas, Maja Pantic, Stavros Petridis","submitted_at":"2018-05-23T17:54:32Z","abstract_excerpt":"Speech-driven facial animation is the process which uses speech signals to automatically synthesize a talking character. The majority of work in this domain creates a mapping from audio features to visual features. This often requires post-processing using computer graphics techniques to produce realistic albeit subject dependent results. We present a system for generating videos of a talking head, using a still image of a person and an audio clip containing speech, that doesn't rely on any handcrafted intermediate features. To the best of our knowledge, this is the first method capable of gen"},"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":"1805.09313","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-05-23T17:54:32Z","cross_cats_sorted":["cs.CV","cs.SD","eess.IV"],"title_canon_sha256":"87d6ce1923286c183e0c30d748e687cbb3b6c376f665fbfab6dd6dbebe58437f","abstract_canon_sha256":"d873368ffa12da60f23587356d58d2e259556d28881700bc9fc3a25e4e2b424c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:21.724380Z","signature_b64":"pI+7GNgFGouShqCugcVnWv+2mkxNX8bYLbH38QfhOthWIDot44iIKLQ6IAkm41Kgngr4zxOCQ4+LBpNfprCkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f76cc46203f5491ea2e125ba9976d50ef7cb550a4dc9ae9bdb44caeedd72b6f1","last_reissued_at":"2026-05-18T00:10:21.723729Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:21.723729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Speech-Driven Facial Animation with Temporal GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Konstantinos Vougioukas, Maja Pantic, Stavros Petridis","submitted_at":"2018-05-23T17:54:32Z","abstract_excerpt":"Speech-driven facial animation is the process which uses speech signals to automatically synthesize a talking character. The majority of work in this domain creates a mapping from audio features to visual features. This often requires post-processing using computer graphics techniques to produce realistic albeit subject dependent results. We present a system for generating videos of a talking head, using a still image of a person and an audio clip containing speech, that doesn't rely on any handcrafted intermediate features. To the best of our knowledge, this is the first method capable of gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09313","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.09313","created_at":"2026-05-18T00:10:21.723819+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09313v4","created_at":"2026-05-18T00:10:21.723819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09313","created_at":"2026-05-18T00:10:21.723819+00:00"},{"alias_kind":"pith_short_12","alias_value":"65WMIYQD6VER","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"65WMIYQD6VER5IXB","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"65WMIYQD","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2309.09346","citing_title":"Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3","json":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3.json","graph_json":"https://pith.science/api/pith-number/65WMIYQD6VER5IXBEW5JS5WVB3/graph.json","events_json":"https://pith.science/api/pith-number/65WMIYQD6VER5IXBEW5JS5WVB3/events.json","paper":"https://pith.science/paper/65WMIYQD"},"agent_actions":{"view_html":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3","download_json":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3.json","view_paper":"https://pith.science/paper/65WMIYQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09313&json=true","fetch_graph":"https://pith.science/api/pith-number/65WMIYQD6VER5IXBEW5JS5WVB3/graph.json","fetch_events":"https://pith.science/api/pith-number/65WMIYQD6VER5IXBEW5JS5WVB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3/action/storage_attestation","attest_author":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3/action/author_attestation","sign_citation":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3/action/citation_signature","submit_replication":"https://pith.science/pith/65WMIYQD6VER5IXBEW5JS5WVB3/action/replication_record"}},"created_at":"2026-05-18T00:10:21.723819+00:00","updated_at":"2026-05-18T00:10:21.723819+00:00"}