{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MGIYAXKZ6RFY42V25ZFZOTMR7E","short_pith_number":"pith:MGIYAXKZ","schema_version":"1.0","canonical_sha256":"6191805d59f44b8e6abaee4b974d91f93d1a76853c60ad9a1b1cff04f5afcbbd","source":{"kind":"arxiv","id":"2401.15687","version":2},"attestation_state":"computed","paper":{"title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Dafei Qin, Han Liang, Jingyi Yu, Lan Xu, Longwen Zhang, Pengyu Long, Qingcheng Zhao, Qixuan Zhang, Yingliang Zhang","submitted_at":"2024-01-28T16:17:59Z","abstract_excerpt":"The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism and a lack of lexible conditioning. We address this challenge through a trilogy. We first introduce Generalized Neural Parametric Facial Asset (GNPFA), an efficient variational auto-encoder mapping facial geometry and images to a highly generalized expression latent space, decoupling expressions and identities. Then, we utilize GNPFA to extract high-quality "},"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":"2401.15687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-28T16:17:59Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"6e3159e89e2a9861367374572cc777bfdd2eb8d2625e3aa844003546fb836fd7","abstract_canon_sha256":"a6ae4193761bb5f928d43a3791c1e9818daedc60d4b04750e1e7cfd74b70aba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:54.601268Z","signature_b64":"lLYZQiBDI5O8c07zHze3kNJY3eKJjct/N2+wACVeIVOyUy7dPRrA5Ynpmkuih0DqJKi4ow04bf/b3T9svqdfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6191805d59f44b8e6abaee4b974d91f93d1a76853c60ad9a1b1cff04f5afcbbd","last_reissued_at":"2026-07-05T07:38:54.600795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:54.600795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Dafei Qin, Han Liang, Jingyi Yu, Lan Xu, Longwen Zhang, Pengyu Long, Qingcheng Zhao, Qixuan Zhang, Yingliang Zhang","submitted_at":"2024-01-28T16:17:59Z","abstract_excerpt":"The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism and a lack of lexible conditioning. We address this challenge through a trilogy. We first introduce Generalized Neural Parametric Facial Asset (GNPFA), an efficient variational auto-encoder mapping facial geometry and images to a highly generalized expression latent space, decoupling expressions and identities. Then, we utilize GNPFA to extract high-quality "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15687","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/2401.15687/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":"2401.15687","created_at":"2026-07-05T07:38:54.600849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15687v2","created_at":"2026-07-05T07:38:54.600849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15687","created_at":"2026-07-05T07:38:54.600849+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGIYAXKZ6RFY","created_at":"2026-07-05T07:38:54.600849+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGIYAXKZ6RFY42V2","created_at":"2026-07-05T07:38:54.600849+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGIYAXKZ","created_at":"2026-07-05T07:38:54.600849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31294","citing_title":"TokTalk: Expressive Real-time Facial Animation from Audio-LLM Tokens","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E","json":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E.json","graph_json":"https://pith.science/api/pith-number/MGIYAXKZ6RFY42V25ZFZOTMR7E/graph.json","events_json":"https://pith.science/api/pith-number/MGIYAXKZ6RFY42V25ZFZOTMR7E/events.json","paper":"https://pith.science/paper/MGIYAXKZ"},"agent_actions":{"view_html":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E","download_json":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E.json","view_paper":"https://pith.science/paper/MGIYAXKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15687&json=true","fetch_graph":"https://pith.science/api/pith-number/MGIYAXKZ6RFY42V25ZFZOTMR7E/graph.json","fetch_events":"https://pith.science/api/pith-number/MGIYAXKZ6RFY42V25ZFZOTMR7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E/action/storage_attestation","attest_author":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E/action/author_attestation","sign_citation":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E/action/citation_signature","submit_replication":"https://pith.science/pith/MGIYAXKZ6RFY42V25ZFZOTMR7E/action/replication_record"}},"created_at":"2026-07-05T07:38:54.600849+00:00","updated_at":"2026-07-05T07:38:54.600849+00:00"}