{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OGFBEJ5SGXOF77D34X4LY77OPG","short_pith_number":"pith:OGFBEJ5S","schema_version":"1.0","canonical_sha256":"718a1227b235dc5ffc7be5f8bc7fee79b5865aa6fc74b5603a5d2178c3b5c065","source":{"kind":"arxiv","id":"2102.06837","version":1},"attestation_state":"computed","paper":{"title":"Learning Speech-driven 3D Conversational Gestures from Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Theobalt, Dushyant Mehta, Gerard Pons-Moll, Hans-Peter Seidel, Ikhsanul Habibie, Lingjie Liu, Mohamed Elgharib, Weipeng Xu","submitted_at":"2021-02-13T01:05:39Z","abstract_excerpt":"We propose the first approach to automatically and jointly synthesize both the synchronous 3D conversational body and hand gestures, as well as 3D face and head animations, of a virtual character from speech input. Our algorithm uses a CNN architecture that leverages the inherent correlation between facial expression and hand gestures. Synthesis of conversational body gestures is a multi-modal problem since many similar gestures can plausibly accompany the same input speech. To synthesize plausible body gestures in this setting, we train a Generative Adversarial Network (GAN) based model that "},"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":"2102.06837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-13T01:05:39Z","cross_cats_sorted":[],"title_canon_sha256":"6481f88f976187c66b82a7f090a72a32b95eab6a015a628da83a8a756a4f98b3","abstract_canon_sha256":"fa9bbe5704787508be59489213bf3e35b73ce2879bbe5a51814b30e64c9d268f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:58.820651Z","signature_b64":"YdDVBw1jdyUXeQVb3Tp8cmxZZui5owxgVTHD9CthSlo9t/gfFaj6vhfsAiP2wN9nNux0EcryjZTE9oRcUmEbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718a1227b235dc5ffc7be5f8bc7fee79b5865aa6fc74b5603a5d2178c3b5c065","last_reissued_at":"2026-07-05T02:14:58.820192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:58.820192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Speech-driven 3D Conversational Gestures from Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Theobalt, Dushyant Mehta, Gerard Pons-Moll, Hans-Peter Seidel, Ikhsanul Habibie, Lingjie Liu, Mohamed Elgharib, Weipeng Xu","submitted_at":"2021-02-13T01:05:39Z","abstract_excerpt":"We propose the first approach to automatically and jointly synthesize both the synchronous 3D conversational body and hand gestures, as well as 3D face and head animations, of a virtual character from speech input. Our algorithm uses a CNN architecture that leverages the inherent correlation between facial expression and hand gestures. Synthesis of conversational body gestures is a multi-modal problem since many similar gestures can plausibly accompany the same input speech. To synthesize plausible body gestures in this setting, we train a Generative Adversarial Network (GAN) based model that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06837","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/2102.06837/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":"2102.06837","created_at":"2026-07-05T02:14:58.820255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.06837v1","created_at":"2026-07-05T02:14:58.820255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06837","created_at":"2026-07-05T02:14:58.820255+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGFBEJ5SGXOF","created_at":"2026-07-05T02:14:58.820255+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGFBEJ5SGXOF77D3","created_at":"2026-07-05T02:14:58.820255+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGFBEJ5S","created_at":"2026-07-05T02:14:58.820255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10927","citing_title":"LiveGesture Streamable Co-Speech Gesture Generation Model","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG","json":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG.json","graph_json":"https://pith.science/api/pith-number/OGFBEJ5SGXOF77D34X4LY77OPG/graph.json","events_json":"https://pith.science/api/pith-number/OGFBEJ5SGXOF77D34X4LY77OPG/events.json","paper":"https://pith.science/paper/OGFBEJ5S"},"agent_actions":{"view_html":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG","download_json":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG.json","view_paper":"https://pith.science/paper/OGFBEJ5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.06837&json=true","fetch_graph":"https://pith.science/api/pith-number/OGFBEJ5SGXOF77D34X4LY77OPG/graph.json","fetch_events":"https://pith.science/api/pith-number/OGFBEJ5SGXOF77D34X4LY77OPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG/action/storage_attestation","attest_author":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG/action/author_attestation","sign_citation":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG/action/citation_signature","submit_replication":"https://pith.science/pith/OGFBEJ5SGXOF77D34X4LY77OPG/action/replication_record"}},"created_at":"2026-07-05T02:14:58.820255+00:00","updated_at":"2026-07-05T02:14:58.820255+00:00"}