{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WSVJAV454D2VE3NKRUSP4P6XH7","short_pith_number":"pith:WSVJAV45","schema_version":"1.0","canonical_sha256":"b4aa90579de0f5526daa8d24fe3fd73fe7df04a2c23e8631315f3bf5c8a1fa84","source":{"kind":"arxiv","id":"2402.16124","version":1},"attestation_state":"computed","paper":{"title":"AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhou, Hideki Koike, Kaisiyuan Wang, Wenqing Chu, Yasheng Sun","submitted_at":"2024-02-25T15:51:05Z","abstract_excerpt":"While considerable progress has been made in achieving accurate lip synchronization for 3D speech-driven talking face generation, the task of incorporating expressive facial detail synthesis aligned with the speaker's speaking status remains challenging. Our goal is to directly leverage the inherent style information conveyed by human speech for generating an expressive talking face that aligns with the speaking status. In this paper, we propose AVI-Talking, an Audio-Visual Instruction system for expressive Talking face generation. This system harnesses the robust contextual reasoning and hall"},"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":"2402.16124","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-25T15:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"563b01211bcb09f3102ea3c452ec4ed92ea7066d218df8cfd0c37b914a5c0ed1","abstract_canon_sha256":"6c2e43dfa2c73ea4fc504672e2bc59aece7d379facb151a704a39c6280654446"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:02.374707Z","signature_b64":"tinChueHgTabX2Mr1ZC+ijEhIofKp+WLlV9YcKOZ4W0WWQ2ptKbELQWRgfQvQ3WegthyTDwqEZx40Hl7/1P0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4aa90579de0f5526daa8d24fe3fd73fe7df04a2c23e8631315f3bf5c8a1fa84","last_reissued_at":"2026-07-05T07:49:02.374274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:02.374274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhou, Hideki Koike, Kaisiyuan Wang, Wenqing Chu, Yasheng Sun","submitted_at":"2024-02-25T15:51:05Z","abstract_excerpt":"While considerable progress has been made in achieving accurate lip synchronization for 3D speech-driven talking face generation, the task of incorporating expressive facial detail synthesis aligned with the speaker's speaking status remains challenging. Our goal is to directly leverage the inherent style information conveyed by human speech for generating an expressive talking face that aligns with the speaking status. In this paper, we propose AVI-Talking, an Audio-Visual Instruction system for expressive Talking face generation. This system harnesses the robust contextual reasoning and hall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16124","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/2402.16124/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":"2402.16124","created_at":"2026-07-05T07:49:02.374338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16124v1","created_at":"2026-07-05T07:49:02.374338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16124","created_at":"2026-07-05T07:49:02.374338+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSVJAV454D2V","created_at":"2026-07-05T07:49:02.374338+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSVJAV454D2VE3NK","created_at":"2026-07-05T07:49:02.374338+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSVJAV45","created_at":"2026-07-05T07:49:02.374338+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/WSVJAV454D2VE3NKRUSP4P6XH7","json":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7.json","graph_json":"https://pith.science/api/pith-number/WSVJAV454D2VE3NKRUSP4P6XH7/graph.json","events_json":"https://pith.science/api/pith-number/WSVJAV454D2VE3NKRUSP4P6XH7/events.json","paper":"https://pith.science/paper/WSVJAV45"},"agent_actions":{"view_html":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7","download_json":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7.json","view_paper":"https://pith.science/paper/WSVJAV45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16124&json=true","fetch_graph":"https://pith.science/api/pith-number/WSVJAV454D2VE3NKRUSP4P6XH7/graph.json","fetch_events":"https://pith.science/api/pith-number/WSVJAV454D2VE3NKRUSP4P6XH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7/action/storage_attestation","attest_author":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7/action/author_attestation","sign_citation":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7/action/citation_signature","submit_replication":"https://pith.science/pith/WSVJAV454D2VE3NKRUSP4P6XH7/action/replication_record"}},"created_at":"2026-07-05T07:49:02.374338+00:00","updated_at":"2026-07-05T07:49:02.374338+00:00"}