{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WAW4UAOHKSGDA3OLZRSYWBLKFF","short_pith_number":"pith:WAW4UAOH","schema_version":"1.0","canonical_sha256":"b02dca01c7548c306dcbcc658b056a2949b5dbdddcbe5a13bf68127e3a6e5c6a","source":{"kind":"arxiv","id":"2305.08293","version":1},"attestation_state":"computed","paper":{"title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaowei Fang, Gangming Zhao, Guanbin Li, Liang Lin, Pengxu Wei, Weizhi Zhong, Yinqi Cai","submitted_at":"2023-05-15T01:31:32Z","abstract_excerpt":"Generating talking face videos from audio attracts lots of research interest. A few person-specific methods can generate vivid videos but require the target speaker's videos for training or fine-tuning. Existing person-generic methods have difficulty in generating realistic and lip-synced videos while preserving identity information. To tackle this problem, we propose a two-stage framework consisting of audio-to-landmark generation and landmark-to-video rendering procedures. First, we devise a novel Transformer-based landmark generator to infer lip and jaw landmarks from the audio. Prior landm"},"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":"2305.08293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T01:31:32Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"999c3506a119519517a85d72b712f1fd753e4270de70a7c259a8d1fe61b83d04","abstract_canon_sha256":"7c24ca8299ad4c76e9904ef3779e9d2518972be91a1a3b40a8345690afa7414d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:59.639671Z","signature_b64":"IIGUiklV5U/ExwgkdkYqiNirAe1DA929Lm8/4T/N7tmgXjyNJj+JnJOB3nWBrnA5FYmR9kXlXs0pq0SJODyPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b02dca01c7548c306dcbcc658b056a2949b5dbdddcbe5a13bf68127e3a6e5c6a","last_reissued_at":"2026-07-05T06:09:59.639199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:59.639199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaowei Fang, Gangming Zhao, Guanbin Li, Liang Lin, Pengxu Wei, Weizhi Zhong, Yinqi Cai","submitted_at":"2023-05-15T01:31:32Z","abstract_excerpt":"Generating talking face videos from audio attracts lots of research interest. A few person-specific methods can generate vivid videos but require the target speaker's videos for training or fine-tuning. Existing person-generic methods have difficulty in generating realistic and lip-synced videos while preserving identity information. To tackle this problem, we propose a two-stage framework consisting of audio-to-landmark generation and landmark-to-video rendering procedures. First, we devise a novel Transformer-based landmark generator to infer lip and jaw landmarks from the audio. Prior landm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08293","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/2305.08293/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":"2305.08293","created_at":"2026-07-05T06:09:59.639255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08293v1","created_at":"2026-07-05T06:09:59.639255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08293","created_at":"2026-07-05T06:09:59.639255+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAW4UAOHKSGD","created_at":"2026-07-05T06:09:59.639255+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAW4UAOHKSGDA3OL","created_at":"2026-07-05T06:09:59.639255+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAW4UAOH","created_at":"2026-07-05T06:09:59.639255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19833","citing_title":"Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF","json":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF.json","graph_json":"https://pith.science/api/pith-number/WAW4UAOHKSGDA3OLZRSYWBLKFF/graph.json","events_json":"https://pith.science/api/pith-number/WAW4UAOHKSGDA3OLZRSYWBLKFF/events.json","paper":"https://pith.science/paper/WAW4UAOH"},"agent_actions":{"view_html":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF","download_json":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF.json","view_paper":"https://pith.science/paper/WAW4UAOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08293&json=true","fetch_graph":"https://pith.science/api/pith-number/WAW4UAOHKSGDA3OLZRSYWBLKFF/graph.json","fetch_events":"https://pith.science/api/pith-number/WAW4UAOHKSGDA3OLZRSYWBLKFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF/action/storage_attestation","attest_author":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF/action/author_attestation","sign_citation":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF/action/citation_signature","submit_replication":"https://pith.science/pith/WAW4UAOHKSGDA3OLZRSYWBLKFF/action/replication_record"}},"created_at":"2026-07-05T06:09:59.639255+00:00","updated_at":"2026-07-05T06:09:59.639255+00:00"}