{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O3SPU6TCODBPRTJU6J3QWXOWDQ","short_pith_number":"pith:O3SPU6TC","schema_version":"1.0","canonical_sha256":"76e4fa7a6270c2f8cd34f2770b5dd61c2b92b73c7d09956f93263079ec26e51d","source":{"kind":"arxiv","id":"2406.14272","version":1},"attestation_state":"computed","paper":{"title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Gihun Son, Janghoon Ju, Kim Sung-Bin, Lee Chae-Yeon, Oh Hyun-Bin, Suekyeong Nam, Tae-Hyun Oh","submitted_at":"2024-06-20T12:52:46Z","abstract_excerpt":"Recent studies in speech-driven 3D talking head generation have achieved convincing results in verbal articulations. However, generating accurate lip-syncs degrades when applied to input speech in other languages, possibly due to the lack of datasets covering a broad spectrum of facial movements across languages. In this work, we introduce a novel task to generate 3D talking heads from speeches of diverse languages. We collect a new multilingual 2D video dataset comprising over 420 hours of talking videos in 20 languages. With our proposed dataset, we present a multilingually enhanced model th"},"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":"2406.14272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T12:52:46Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"a862a1d02ae763e9274be75f12ac6ba63ed2f4331a18569ac2a0cc2a3989d2b8","abstract_canon_sha256":"a889713c68b0c2fc0b35d1eafceb4977f88ff8338e19d365f15533e158134c80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:41.268496Z","signature_b64":"YMIZNdw6wc1o00EsLdMeD5FjJLH9PQsU6OTgAQrwaz2LfDXiaMb+5/gjRniH+fSmy4r+lOECWG6zERgk5ms9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76e4fa7a6270c2f8cd34f2770b5dd61c2b92b73c7d09956f93263079ec26e51d","last_reissued_at":"2026-07-05T08:34:41.268080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:41.268080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Gihun Son, Janghoon Ju, Kim Sung-Bin, Lee Chae-Yeon, Oh Hyun-Bin, Suekyeong Nam, Tae-Hyun Oh","submitted_at":"2024-06-20T12:52:46Z","abstract_excerpt":"Recent studies in speech-driven 3D talking head generation have achieved convincing results in verbal articulations. However, generating accurate lip-syncs degrades when applied to input speech in other languages, possibly due to the lack of datasets covering a broad spectrum of facial movements across languages. In this work, we introduce a novel task to generate 3D talking heads from speeches of diverse languages. We collect a new multilingual 2D video dataset comprising over 420 hours of talking videos in 20 languages. With our proposed dataset, we present a multilingually enhanced model th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14272","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/2406.14272/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":"2406.14272","created_at":"2026-07-05T08:34:41.268135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14272v1","created_at":"2026-07-05T08:34:41.268135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14272","created_at":"2026-07-05T08:34:41.268135+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3SPU6TCODBP","created_at":"2026-07-05T08:34:41.268135+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3SPU6TCODBPRTJU","created_at":"2026-07-05T08:34:41.268135+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3SPU6TC","created_at":"2026-07-05T08:34:41.268135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2408.05366","citing_title":"The DeepSpeak Dataset","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ","json":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ.json","graph_json":"https://pith.science/api/pith-number/O3SPU6TCODBPRTJU6J3QWXOWDQ/graph.json","events_json":"https://pith.science/api/pith-number/O3SPU6TCODBPRTJU6J3QWXOWDQ/events.json","paper":"https://pith.science/paper/O3SPU6TC"},"agent_actions":{"view_html":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ","download_json":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ.json","view_paper":"https://pith.science/paper/O3SPU6TC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14272&json=true","fetch_graph":"https://pith.science/api/pith-number/O3SPU6TCODBPRTJU6J3QWXOWDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/O3SPU6TCODBPRTJU6J3QWXOWDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ/action/storage_attestation","attest_author":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ/action/author_attestation","sign_citation":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ/action/citation_signature","submit_replication":"https://pith.science/pith/O3SPU6TCODBPRTJU6J3QWXOWDQ/action/replication_record"}},"created_at":"2026-07-05T08:34:41.268135+00:00","updated_at":"2026-07-05T08:34:41.268135+00:00"}