{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RJ3GOZEO7CKAOSBR4EWQZQCWRV","short_pith_number":"pith:RJ3GOZEO","schema_version":"1.0","canonical_sha256":"8a7667648ef894074831e12d0cc0568d57318d83de87be8d1a3dd97652a0c5e2","source":{"kind":"arxiv","id":"2406.18068","version":2},"attestation_state":"computed","paper":{"title":"Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aniket Bera, Dinesh Manocha, Uttaran Bhattacharya","submitted_at":"2024-06-26T04:53:11Z","abstract_excerpt":"We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse face landmarks and upper-body joints, estimated directly from video data, to generate plausible emotive character motions. Given a speech audio waveform and a token sequence of the speaker's face landmark motion and body-joint motion computed from a video, our method synthesizes the motion sequences for the speaker's face landmarks and body joints to match the"},"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":"2406.18068","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-26T04:53:11Z","cross_cats_sorted":[],"title_canon_sha256":"a139d53ce72a7b51e12b6ddc5fa7817adc83257a150a81197630d47df0df50e8","abstract_canon_sha256":"144e3564f0071dc1ffa21c6662ff4c67d023180d7c308303980c328bf66b9fec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:24.425298Z","signature_b64":"7rS0lCr2VQ9sUTRBe2bn5y1G9H2eb7eG/NCI8knT41JUewmpdkppURcLzfKeCFlOfXAYRlt+aX2D2Fvh7EEMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7667648ef894074831e12d0cc0568d57318d83de87be8d1a3dd97652a0c5e2","last_reissued_at":"2026-07-05T09:39:24.424869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:24.424869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aniket Bera, Dinesh Manocha, Uttaran Bhattacharya","submitted_at":"2024-06-26T04:53:11Z","abstract_excerpt":"We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse face landmarks and upper-body joints, estimated directly from video data, to generate plausible emotive character motions. Given a speech audio waveform and a token sequence of the speaker's face landmark motion and body-joint motion computed from a video, our method synthesizes the motion sequences for the speaker's face landmarks and body joints to match the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18068","kind":"arxiv","version":2},"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/2406.18068/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":"2406.18068","created_at":"2026-07-05T09:39:24.424926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18068v2","created_at":"2026-07-05T09:39:24.424926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18068","created_at":"2026-07-05T09:39:24.424926+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ3GOZEO7CKA","created_at":"2026-07-05T09:39:24.424926+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ3GOZEO7CKAOSBR","created_at":"2026-07-05T09:39:24.424926+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ3GOZEO","created_at":"2026-07-05T09:39:24.424926+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/RJ3GOZEO7CKAOSBR4EWQZQCWRV","json":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV.json","graph_json":"https://pith.science/api/pith-number/RJ3GOZEO7CKAOSBR4EWQZQCWRV/graph.json","events_json":"https://pith.science/api/pith-number/RJ3GOZEO7CKAOSBR4EWQZQCWRV/events.json","paper":"https://pith.science/paper/RJ3GOZEO"},"agent_actions":{"view_html":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV","download_json":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV.json","view_paper":"https://pith.science/paper/RJ3GOZEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18068&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ3GOZEO7CKAOSBR4EWQZQCWRV/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ3GOZEO7CKAOSBR4EWQZQCWRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV/action/storage_attestation","attest_author":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV/action/author_attestation","sign_citation":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV/action/citation_signature","submit_replication":"https://pith.science/pith/RJ3GOZEO7CKAOSBR4EWQZQCWRV/action/replication_record"}},"created_at":"2026-07-05T09:39:24.424926+00:00","updated_at":"2026-07-05T09:39:24.424926+00:00"}