{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IMYZEOL6XKKGAU3TJK3LD3LRW2","short_pith_number":"pith:IMYZEOL6","schema_version":"1.0","canonical_sha256":"433192397eba946053734ab6b1ed71b689258218bdf351f2942ccdcac1c9b743","source":{"kind":"arxiv","id":"2412.14333","version":1},"attestation_state":"computed","paper":{"title":"Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxu Zhang, Steven Hogue, Xiaohu Guo, Yapeng Tian","submitted_at":"2024-12-18T21:02:07Z","abstract_excerpt":"Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing training complexity and ignoring the inherent relationship between face and body movements. To address the challenges, in this paper, we propose a novel model architecture that jointly generates face and body motions within a single network. This approach leverages shared weights between modalities, facilitated by adapters that enable adaptation to a common lat"},"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":"2412.14333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T21:02:07Z","cross_cats_sorted":[],"title_canon_sha256":"1f2fc495cc2043294d42b008bdd3326b507eb51b53042d85aae9d91a1d08e1f3","abstract_canon_sha256":"e80dab06a8b894ee699f11bb55cef3fd8223bf3d24389d9a6592345c2f52f3ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:45.766222Z","signature_b64":"o7kK6w2r2m0L9Qe7kAOIqRkqsvMUEnzeoCHSL075pux+PJqpEbf+l+XODTG/b0C/JNqZvxI331KV5yM9UVLyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433192397eba946053734ab6b1ed71b689258218bdf351f2942ccdcac1c9b743","last_reissued_at":"2026-07-05T09:51:45.765770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:45.765770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxu Zhang, Steven Hogue, Xiaohu Guo, Yapeng Tian","submitted_at":"2024-12-18T21:02:07Z","abstract_excerpt":"Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing training complexity and ignoring the inherent relationship between face and body movements. To address the challenges, in this paper, we propose a novel model architecture that jointly generates face and body motions within a single network. This approach leverages shared weights between modalities, facilitated by adapters that enable adaptation to a common lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14333","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/2412.14333/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":"2412.14333","created_at":"2026-07-05T09:51:45.765829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14333v1","created_at":"2026-07-05T09:51:45.765829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14333","created_at":"2026-07-05T09:51:45.765829+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMYZEOL6XKKG","created_at":"2026-07-05T09:51:45.765829+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMYZEOL6XKKGAU3T","created_at":"2026-07-05T09:51:45.765829+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMYZEOL6","created_at":"2026-07-05T09:51:45.765829+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/IMYZEOL6XKKGAU3TJK3LD3LRW2","json":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2.json","graph_json":"https://pith.science/api/pith-number/IMYZEOL6XKKGAU3TJK3LD3LRW2/graph.json","events_json":"https://pith.science/api/pith-number/IMYZEOL6XKKGAU3TJK3LD3LRW2/events.json","paper":"https://pith.science/paper/IMYZEOL6"},"agent_actions":{"view_html":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2","download_json":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2.json","view_paper":"https://pith.science/paper/IMYZEOL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14333&json=true","fetch_graph":"https://pith.science/api/pith-number/IMYZEOL6XKKGAU3TJK3LD3LRW2/graph.json","fetch_events":"https://pith.science/api/pith-number/IMYZEOL6XKKGAU3TJK3LD3LRW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2/action/storage_attestation","attest_author":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2/action/author_attestation","sign_citation":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2/action/citation_signature","submit_replication":"https://pith.science/pith/IMYZEOL6XKKGAU3TJK3LD3LRW2/action/replication_record"}},"created_at":"2026-07-05T09:51:45.765829+00:00","updated_at":"2026-07-05T09:51:45.765829+00:00"}