{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KVOO4G4HNOSRYD6PGCCH2JJO3T","short_pith_number":"pith:KVOO4G4H","schema_version":"1.0","canonical_sha256":"555cee1b876ba51c0fcf30847d252edcde3e4f8a16e3dbd8b955f94b43f5e085","source":{"kind":"arxiv","id":"2112.05329","version":4},"attestation_state":"computed","paper":{"title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jun Saito, Taku Komura, Wenping Wang, Yingruo Fan, Zhaojiang Lin","submitted_at":"2021-12-10T04:21:59Z","abstract_excerpt":"Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with limited context, occasionally resulting in inaccurate lip movements. To tackle this limitation, we propose a Transformer-based autoregressive model, FaceFormer, which encodes the long-term audio context and autoregressively predicts a sequence of animated 3D face meshes. To cope with the data scarcity issue, we integrate the self-supervised pre-trained speech r"},"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":"2112.05329","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T04:21:59Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"4e7bdc883e8609bea952a7a459d6a1a5fde356dc5182c26e9da29f83b8b81442","abstract_canon_sha256":"a7fab1c7a81debba5f0a21c64efdeac1e6e2b5853829171f4584ca5afe259b01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:01.378876Z","signature_b64":"RgCBrb4zR/bcLTtlBHieldm2BDTllvgD9bDOMSjvu+GKXeLnzHQs98Gioc8Gr5CgM7f1d8V1vPZjH+Nb6VJqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"555cee1b876ba51c0fcf30847d252edcde3e4f8a16e3dbd8b955f94b43f5e085","last_reissued_at":"2026-07-05T04:06:01.378494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:01.378494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jun Saito, Taku Komura, Wenping Wang, Yingruo Fan, Zhaojiang Lin","submitted_at":"2021-12-10T04:21:59Z","abstract_excerpt":"Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with limited context, occasionally resulting in inaccurate lip movements. To tackle this limitation, we propose a Transformer-based autoregressive model, FaceFormer, which encodes the long-term audio context and autoregressively predicts a sequence of animated 3D face meshes. To cope with the data scarcity issue, we integrate the self-supervised pre-trained speech r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05329","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.05329/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":"2112.05329","created_at":"2026-07-05T04:06:01.378560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.05329v4","created_at":"2026-07-05T04:06:01.378560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05329","created_at":"2026-07-05T04:06:01.378560+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVOO4G4HNOSR","created_at":"2026-07-05T04:06:01.378560+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVOO4G4HNOSRYD6P","created_at":"2026-07-05T04:06:01.378560+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVOO4G4H","created_at":"2026-07-05T04:06:01.378560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T","json":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T.json","graph_json":"https://pith.science/api/pith-number/KVOO4G4HNOSRYD6PGCCH2JJO3T/graph.json","events_json":"https://pith.science/api/pith-number/KVOO4G4HNOSRYD6PGCCH2JJO3T/events.json","paper":"https://pith.science/paper/KVOO4G4H"},"agent_actions":{"view_html":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T","download_json":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T.json","view_paper":"https://pith.science/paper/KVOO4G4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.05329&json=true","fetch_graph":"https://pith.science/api/pith-number/KVOO4G4HNOSRYD6PGCCH2JJO3T/graph.json","fetch_events":"https://pith.science/api/pith-number/KVOO4G4HNOSRYD6PGCCH2JJO3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T/action/storage_attestation","attest_author":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T/action/author_attestation","sign_citation":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T/action/citation_signature","submit_replication":"https://pith.science/pith/KVOO4G4HNOSRYD6PGCCH2JJO3T/action/replication_record"}},"created_at":"2026-07-05T04:06:01.378560+00:00","updated_at":"2026-07-05T04:06:01.378560+00:00"}