{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6KTNSVVGQYCFUEU3THLQUOG2ON","short_pith_number":"pith:6KTNSVVG","schema_version":"1.0","canonical_sha256":"f2a6d956a686045a129b99d70a38da73529851fd1ae8690e87f92dc399b7109c","source":{"kind":"arxiv","id":"2401.04747","version":2},"attestation_state":"computed","paper":{"title":"DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ailing Zeng, Jianan Wang, Junming Chen, Qifeng Chen, Yu Li, Yunfei Liu","submitted_at":"2024-01-09T11:38:18Z","abstract_excerpt":"We propose DiffSHEG, a Diffusion-based approach for Speech-driven Holistic 3D Expression and Gesture generation with arbitrary length. While previous works focused on co-speech gesture or expression generation individually, the joint generation of synchronized expressions and gestures remains barely explored. To address this, our diffusion-based co-speech motion generation transformer enables uni-directional information flow from expression to gesture, facilitating improved matching of joint expression-gesture distributions. Furthermore, we introduce an outpainting-based sampling strategy for "},"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":"2401.04747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-09T11:38:18Z","cross_cats_sorted":["cs.AI","cs.CV","cs.GR","eess.AS"],"title_canon_sha256":"58052438f05b75fcf14da570b8453eb1afbd30813744454d1574722f9633cd02","abstract_canon_sha256":"4d832237cbbe41e22b8ab64e155299a3cffa4ae7aedabbcedfd78dee5ac7f1db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:08.550702Z","signature_b64":"vH4lYq1lIN2tnJpXgr6crGOUrKmPguooaLLYZoyYJE8ZvzUDrvgF7XN5PzXMTp0Kr08q4P8UxGumqRwqQ7XNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a6d956a686045a129b99d70a38da73529851fd1ae8690e87f92dc399b7109c","last_reissued_at":"2026-07-05T08:05:08.550252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:08.550252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ailing Zeng, Jianan Wang, Junming Chen, Qifeng Chen, Yu Li, Yunfei Liu","submitted_at":"2024-01-09T11:38:18Z","abstract_excerpt":"We propose DiffSHEG, a Diffusion-based approach for Speech-driven Holistic 3D Expression and Gesture generation with arbitrary length. While previous works focused on co-speech gesture or expression generation individually, the joint generation of synchronized expressions and gestures remains barely explored. To address this, our diffusion-based co-speech motion generation transformer enables uni-directional information flow from expression to gesture, facilitating improved matching of joint expression-gesture distributions. Furthermore, we introduce an outpainting-based sampling strategy for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04747","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/2401.04747/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":"2401.04747","created_at":"2026-07-05T08:05:08.550310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04747v2","created_at":"2026-07-05T08:05:08.550310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04747","created_at":"2026-07-05T08:05:08.550310+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KTNSVVGQYCF","created_at":"2026-07-05T08:05:08.550310+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KTNSVVGQYCFUEU3","created_at":"2026-07-05T08:05:08.550310+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KTNSVVG","created_at":"2026-07-05T08:05:08.550310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON","json":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON.json","graph_json":"https://pith.science/api/pith-number/6KTNSVVGQYCFUEU3THLQUOG2ON/graph.json","events_json":"https://pith.science/api/pith-number/6KTNSVVGQYCFUEU3THLQUOG2ON/events.json","paper":"https://pith.science/paper/6KTNSVVG"},"agent_actions":{"view_html":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON","download_json":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON.json","view_paper":"https://pith.science/paper/6KTNSVVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04747&json=true","fetch_graph":"https://pith.science/api/pith-number/6KTNSVVGQYCFUEU3THLQUOG2ON/graph.json","fetch_events":"https://pith.science/api/pith-number/6KTNSVVGQYCFUEU3THLQUOG2ON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON/action/storage_attestation","attest_author":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON/action/author_attestation","sign_citation":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON/action/citation_signature","submit_replication":"https://pith.science/pith/6KTNSVVGQYCFUEU3THLQUOG2ON/action/replication_record"}},"created_at":"2026-07-05T08:05:08.550310+00:00","updated_at":"2026-07-05T08:05:08.550310+00:00"}