{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YVN5RUWV76MR24L5PXA5OSIGK2","short_pith_number":"pith:YVN5RUWV","schema_version":"1.0","canonical_sha256":"c55bd8d2d5ff991d717d7dc1d7490656b736e2837934ffea404a794fb4a6f50b","source":{"kind":"arxiv","id":"2107.09293","version":1},"attestation_state":"computed","paper":{"title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changjie Fan, Lincheng Li, Suzhen Wang, Xin Yu, Yu Ding","submitted_at":"2021-07-20T07:22:42Z","abstract_excerpt":"We propose an audio-driven talking-head method to generate photo-realistic talking-head videos from a single reference image. In this work, we tackle two key challenges: (i) producing natural head motions that match speech prosody, and (ii) maintaining the appearance of a speaker in a large head motion while stabilizing the non-face regions. We first design a head pose predictor by modeling rigid 6D head movements with a motion-aware recurrent neural network (RNN). In this way, the predicted head poses act as the low-frequency holistic movements of a talking head, thus allowing our latter netw"},"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":"2107.09293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-20T07:22:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"834def8dab7605eb6e404427d8a4e3529a3ed492a321dab0a698e5f8275760a5","abstract_canon_sha256":"26ba0c14d9a1580e5691e0a8db58a4cc15c7f196ebb9111e663950e9d3b23664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:28.318759Z","signature_b64":"HtcboxfLZTMbJmpW7pyOaXQjhV0GS9i0p8NlsY8E16Zd8cfkH78LQS63YS4bLg7XKMfuOiK4RIQVHXjg2/qKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c55bd8d2d5ff991d717d7dc1d7490656b736e2837934ffea404a794fb4a6f50b","last_reissued_at":"2026-07-05T02:59:28.318283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:28.318283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changjie Fan, Lincheng Li, Suzhen Wang, Xin Yu, Yu Ding","submitted_at":"2021-07-20T07:22:42Z","abstract_excerpt":"We propose an audio-driven talking-head method to generate photo-realistic talking-head videos from a single reference image. In this work, we tackle two key challenges: (i) producing natural head motions that match speech prosody, and (ii) maintaining the appearance of a speaker in a large head motion while stabilizing the non-face regions. We first design a head pose predictor by modeling rigid 6D head movements with a motion-aware recurrent neural network (RNN). In this way, the predicted head poses act as the low-frequency holistic movements of a talking head, thus allowing our latter netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09293","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/2107.09293/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":"2107.09293","created_at":"2026-07-05T02:59:28.318372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.09293v1","created_at":"2026-07-05T02:59:28.318372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09293","created_at":"2026-07-05T02:59:28.318372+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVN5RUWV76MR","created_at":"2026-07-05T02:59:28.318372+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVN5RUWV76MR24L5","created_at":"2026-07-05T02:59:28.318372+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVN5RUWV","created_at":"2026-07-05T02:59:28.318372+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01031","citing_title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09534","citing_title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19636","citing_title":"CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2","json":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2.json","graph_json":"https://pith.science/api/pith-number/YVN5RUWV76MR24L5PXA5OSIGK2/graph.json","events_json":"https://pith.science/api/pith-number/YVN5RUWV76MR24L5PXA5OSIGK2/events.json","paper":"https://pith.science/paper/YVN5RUWV"},"agent_actions":{"view_html":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2","download_json":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2.json","view_paper":"https://pith.science/paper/YVN5RUWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.09293&json=true","fetch_graph":"https://pith.science/api/pith-number/YVN5RUWV76MR24L5PXA5OSIGK2/graph.json","fetch_events":"https://pith.science/api/pith-number/YVN5RUWV76MR24L5PXA5OSIGK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2/action/storage_attestation","attest_author":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2/action/author_attestation","sign_citation":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2/action/citation_signature","submit_replication":"https://pith.science/pith/YVN5RUWV76MR24L5PXA5OSIGK2/action/replication_record"}},"created_at":"2026-07-05T02:59:28.318372+00:00","updated_at":"2026-07-05T02:59:28.318372+00:00"}