{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GSZ3B5ENLM7NBIY6FZPJEQBSR6","short_pith_number":"pith:GSZ3B5EN","schema_version":"1.0","canonical_sha256":"34b3b0f48d5b3ed0a31e2e5e9240328fad5ec96d96d4598b427b09a305ff8a67","source":{"kind":"arxiv","id":"2501.04586","version":2},"attestation_state":"computed","paper":{"title":"Identity-Preserving Video Dubbing Using Motion Warping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhua Xian, Fa-Ting Hong, Lijian Lin, Qinjie Lin, Runzhen Liu, Ye Zhu, Yu Li, Yunfei Liu","submitted_at":"2025-01-08T16:06:21Z","abstract_excerpt":"Video dubbing aims to synthesize realistic, lip-synced videos from a reference video and a driving audio signal. Although existing methods can accurately generate mouth shapes driven by audio, they often fail to preserve identity-specific features, largely because they do not effectively capture the nuanced interplay between audio cues and the visual attributes of reference identity . As a result, the generated outputs frequently lack fidelity in reproducing the unique textural and structural details of the reference identity. To address these limitations, we propose IPTalker, a novel and robu"},"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":"2501.04586","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T16:06:21Z","cross_cats_sorted":[],"title_canon_sha256":"dbf01ee89a2da3875846853967791424b14958ac39bfa4ee8f9934b55f40a722","abstract_canon_sha256":"11e734f69f7a332cc7f7a71a291638c183a6a9d3c2592466e0d6e32e922da4a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:02.855324Z","signature_b64":"CdCjc/0WhI9dCZcHsFIb+0PgY7HfQn+mF5PzclKtaBWYjee6pmU/xxX9ntCWzFNQ5q9efyTCxsWT3kaxcG4/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34b3b0f48d5b3ed0a31e2e5e9240328fad5ec96d96d4598b427b09a305ff8a67","last_reissued_at":"2026-07-05T09:59:02.854812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:02.854812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identity-Preserving Video Dubbing Using Motion Warping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhua Xian, Fa-Ting Hong, Lijian Lin, Qinjie Lin, Runzhen Liu, Ye Zhu, Yu Li, Yunfei Liu","submitted_at":"2025-01-08T16:06:21Z","abstract_excerpt":"Video dubbing aims to synthesize realistic, lip-synced videos from a reference video and a driving audio signal. Although existing methods can accurately generate mouth shapes driven by audio, they often fail to preserve identity-specific features, largely because they do not effectively capture the nuanced interplay between audio cues and the visual attributes of reference identity . As a result, the generated outputs frequently lack fidelity in reproducing the unique textural and structural details of the reference identity. To address these limitations, we propose IPTalker, a novel and robu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04586","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/2501.04586/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":"2501.04586","created_at":"2026-07-05T09:59:02.854882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04586v2","created_at":"2026-07-05T09:59:02.854882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04586","created_at":"2026-07-05T09:59:02.854882+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSZ3B5ENLM7N","created_at":"2026-07-05T09:59:02.854882+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSZ3B5ENLM7NBIY6","created_at":"2026-07-05T09:59:02.854882+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSZ3B5EN","created_at":"2026-07-05T09:59:02.854882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28568","citing_title":"KM-Speaker: Keypoint-Based Style Control for High-Quality Speech-Driven 3D Facial Animation and Dialogue Localization","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6","json":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6.json","graph_json":"https://pith.science/api/pith-number/GSZ3B5ENLM7NBIY6FZPJEQBSR6/graph.json","events_json":"https://pith.science/api/pith-number/GSZ3B5ENLM7NBIY6FZPJEQBSR6/events.json","paper":"https://pith.science/paper/GSZ3B5EN"},"agent_actions":{"view_html":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6","download_json":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6.json","view_paper":"https://pith.science/paper/GSZ3B5EN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04586&json=true","fetch_graph":"https://pith.science/api/pith-number/GSZ3B5ENLM7NBIY6FZPJEQBSR6/graph.json","fetch_events":"https://pith.science/api/pith-number/GSZ3B5ENLM7NBIY6FZPJEQBSR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6/action/storage_attestation","attest_author":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6/action/author_attestation","sign_citation":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6/action/citation_signature","submit_replication":"https://pith.science/pith/GSZ3B5ENLM7NBIY6FZPJEQBSR6/action/replication_record"}},"created_at":"2026-07-05T09:59:02.854882+00:00","updated_at":"2026-07-05T09:59:02.854882+00:00"}