{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZAADIOMWU34JT2K3KAN2LLDVCA","short_pith_number":"pith:ZAADIOMW","schema_version":"1.0","canonical_sha256":"c800343996a6f899e95b501ba5ac75100b89ae6d2f114f35b171bccdb2f78657","source":{"kind":"arxiv","id":"2505.01932","version":2},"attestation_state":"computed","paper":{"title":"OT-Talk: Animating 3D Talking Head with Optimal Transportation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Heather Yu, Liang Peng, Xianfeng Gu, Xiang Gao, Xinmu Wang, Xiyun Song, Zongfang Lin","submitted_at":"2025-05-03T21:49:23Z","abstract_excerpt":"Animating 3D head meshes using audio inputs has significant applications in AR/VR, gaming, and entertainment through 3D avatars. However, bridging the modality gap between speech signals and facial dynamics remains a challenge, often resulting in incorrect lip syncing and unnatural facial movements. To address this, we propose OT-Talk, the first approach to leverage optimal transportation to optimize the learning model in talking head animation. Building on existing learning frameworks, we utilize a pre-trained Hubert model to extract audio features and a transformer model to process temporal "},"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":"2505.01932","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.GR","submitted_at":"2025-05-03T21:49:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"784ae0b829d854bed04b2ae9bb1abcaeb87ca91fb9ccd6593699bd6e84cf6832","abstract_canon_sha256":"56e35311006634f0c3a13651b6f254372fbc22ed27ae24ccbbf4c2aa4741939b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:04.812009Z","signature_b64":"S16+Y5pWFJdY7dPjn5h05Yx6bJqA/hDw+TNYoJwqXXEExqB0bpLOie1DgYAdbD0xy9Gq2P1UfjL0GqFaHa2hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c800343996a6f899e95b501ba5ac75100b89ae6d2f114f35b171bccdb2f78657","last_reissued_at":"2026-07-05T11:01:04.811469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:04.811469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OT-Talk: Animating 3D Talking Head with Optimal Transportation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Heather Yu, Liang Peng, Xianfeng Gu, Xiang Gao, Xinmu Wang, Xiyun Song, Zongfang Lin","submitted_at":"2025-05-03T21:49:23Z","abstract_excerpt":"Animating 3D head meshes using audio inputs has significant applications in AR/VR, gaming, and entertainment through 3D avatars. However, bridging the modality gap between speech signals and facial dynamics remains a challenge, often resulting in incorrect lip syncing and unnatural facial movements. To address this, we propose OT-Talk, the first approach to leverage optimal transportation to optimize the learning model in talking head animation. Building on existing learning frameworks, we utilize a pre-trained Hubert model to extract audio features and a transformer model to process temporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01932","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/2505.01932/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":"2505.01932","created_at":"2026-07-05T11:01:04.811536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01932v2","created_at":"2026-07-05T11:01:04.811536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01932","created_at":"2026-07-05T11:01:04.811536+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAADIOMWU34J","created_at":"2026-07-05T11:01:04.811536+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAADIOMWU34JT2K3","created_at":"2026-07-05T11:01:04.811536+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAADIOMW","created_at":"2026-07-05T11:01:04.811536+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/ZAADIOMWU34JT2K3KAN2LLDVCA","json":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA.json","graph_json":"https://pith.science/api/pith-number/ZAADIOMWU34JT2K3KAN2LLDVCA/graph.json","events_json":"https://pith.science/api/pith-number/ZAADIOMWU34JT2K3KAN2LLDVCA/events.json","paper":"https://pith.science/paper/ZAADIOMW"},"agent_actions":{"view_html":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA","download_json":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA.json","view_paper":"https://pith.science/paper/ZAADIOMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01932&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAADIOMWU34JT2K3KAN2LLDVCA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAADIOMWU34JT2K3KAN2LLDVCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA/action/storage_attestation","attest_author":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA/action/author_attestation","sign_citation":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA/action/citation_signature","submit_replication":"https://pith.science/pith/ZAADIOMWU34JT2K3KAN2LLDVCA/action/replication_record"}},"created_at":"2026-07-05T11:01:04.811536+00:00","updated_at":"2026-07-05T11:01:04.811536+00:00"}