{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IZVLBNM2FYORAACQVXINHEXPAP","short_pith_number":"pith:IZVLBNM2","schema_version":"1.0","canonical_sha256":"466ab0b59a2e1d100050add0d392ef03d347fac7b459d791e4aa2d8c593461b2","source":{"kind":"arxiv","id":"2212.05005","version":4},"attestation_state":"computed","paper":{"title":"Memories are One-to-Many Mapping Alleviators in Talking Face Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Anni Tang, Jun Ling, Li Song, Tianyu He, Xu Tan","submitted_at":"2022-12-09T17:45:36Z","abstract_excerpt":"Talking face generation aims at generating photo-realistic video portraits of a target person driven by input audio. Due to its nature of one-to-many mapping from the input audio to the output video (e.g., one speech content may have multiple feasible visual appearances), learning a deterministic mapping like previous works brings ambiguity during training, and thus causes inferior visual results. Although this one-to-many mapping could be alleviated in part by a two-stage framework (i.e., an audio-to-expression model followed by a neural-rendering model), it is still insufficient since the pr"},"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":"2212.05005","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-09T17:45:36Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"76aaa7a1b2a912f45535b8301eead03d26294b926f572f0229b7b2f6f0ade5c5","abstract_canon_sha256":"6fcdec86007242f981dccfe4d169e130bebf2ac7a2025cddca4d1831784f75bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:47.624699Z","signature_b64":"poEzFfDe+zNwp110+WnklRmMyd3MoIsYhLB4UWJpdKoaDGz6kfCiqIHBLPc/Fwccmi/jmvbIoP9Eu2JaCmEtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"466ab0b59a2e1d100050add0d392ef03d347fac7b459d791e4aa2d8c593461b2","last_reissued_at":"2026-07-05T09:44:47.624159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:47.624159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memories are One-to-Many Mapping Alleviators in Talking Face Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Anni Tang, Jun Ling, Li Song, Tianyu He, Xu Tan","submitted_at":"2022-12-09T17:45:36Z","abstract_excerpt":"Talking face generation aims at generating photo-realistic video portraits of a target person driven by input audio. Due to its nature of one-to-many mapping from the input audio to the output video (e.g., one speech content may have multiple feasible visual appearances), learning a deterministic mapping like previous works brings ambiguity during training, and thus causes inferior visual results. Although this one-to-many mapping could be alleviated in part by a two-stage framework (i.e., an audio-to-expression model followed by a neural-rendering model), it is still insufficient since the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05005","kind":"arxiv","version":4},"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/2212.05005/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":"2212.05005","created_at":"2026-07-05T09:44:47.624226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.05005v4","created_at":"2026-07-05T09:44:47.624226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05005","created_at":"2026-07-05T09:44:47.624226+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZVLBNM2FYOR","created_at":"2026-07-05T09:44:47.624226+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZVLBNM2FYORAACQ","created_at":"2026-07-05T09:44:47.624226+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZVLBNM2","created_at":"2026-07-05T09:44:47.624226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18675","citing_title":"GaussianSpeech: Audio-Driven Gaussian Avatars","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP","json":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP.json","graph_json":"https://pith.science/api/pith-number/IZVLBNM2FYORAACQVXINHEXPAP/graph.json","events_json":"https://pith.science/api/pith-number/IZVLBNM2FYORAACQVXINHEXPAP/events.json","paper":"https://pith.science/paper/IZVLBNM2"},"agent_actions":{"view_html":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP","download_json":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP.json","view_paper":"https://pith.science/paper/IZVLBNM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.05005&json=true","fetch_graph":"https://pith.science/api/pith-number/IZVLBNM2FYORAACQVXINHEXPAP/graph.json","fetch_events":"https://pith.science/api/pith-number/IZVLBNM2FYORAACQVXINHEXPAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP/action/storage_attestation","attest_author":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP/action/author_attestation","sign_citation":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP/action/citation_signature","submit_replication":"https://pith.science/pith/IZVLBNM2FYORAACQVXINHEXPAP/action/replication_record"}},"created_at":"2026-07-05T09:44:47.624226+00:00","updated_at":"2026-07-05T09:44:47.624226+00:00"}