{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C7Q2QV5TPPDXHYWJ54BJCV4Y2W","short_pith_number":"pith:C7Q2QV5T","schema_version":"1.0","canonical_sha256":"17e1a857b37bc773e2c9ef02915798d584b92255785f74b98074473a756de83a","source":{"kind":"arxiv","id":"2403.02905","version":3},"attestation_state":"computed","paper":{"title":"MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chengjie Wang, Jiangning Zhang, Lizhuang Ma, Sen Wang, Xin Tan, Zhifeng Xie","submitted_at":"2024-03-05T12:13:18Z","abstract_excerpt":"The body movements accompanying speech aid speakers in expressing their ideas. Co-speech motion generation is one of the important approaches for synthesizing realistic avatars. Due to the intricate correspondence between speech and motion, generating realistic and diverse motion is a challenging task. In this paper, we propose MMoFusion, a Multi-modal co-speech Motion generation framework based on the diffusion model to ensure both the authenticity and diversity of generated motion. We propose a progressive fusion strategy to enhance the interaction of inter-modal and intra-modal, efficiently"},"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":"2403.02905","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-03-05T12:13:18Z","cross_cats_sorted":[],"title_canon_sha256":"1775a4242f2b8d4d83384371bc0939ae50faebe8170e3f2cbabc20ad16fecbdc","abstract_canon_sha256":"1ebc39b877eac720c22d91315edac24526a304ad61bc6a2f4219de876251d81c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:26.416562Z","signature_b64":"r869q2jxAq/GIKLO3/uBk01YH/9bcmcOBs7sCTV9jc7/tnpudMSod/HqFWFaWzTbYGrN+s9KBjlQmKskLJTdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17e1a857b37bc773e2c9ef02915798d584b92255785f74b98074473a756de83a","last_reissued_at":"2026-07-05T08:59:26.416046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:26.416046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chengjie Wang, Jiangning Zhang, Lizhuang Ma, Sen Wang, Xin Tan, Zhifeng Xie","submitted_at":"2024-03-05T12:13:18Z","abstract_excerpt":"The body movements accompanying speech aid speakers in expressing their ideas. Co-speech motion generation is one of the important approaches for synthesizing realistic avatars. Due to the intricate correspondence between speech and motion, generating realistic and diverse motion is a challenging task. In this paper, we propose MMoFusion, a Multi-modal co-speech Motion generation framework based on the diffusion model to ensure both the authenticity and diversity of generated motion. We propose a progressive fusion strategy to enhance the interaction of inter-modal and intra-modal, efficiently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02905","kind":"arxiv","version":3},"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/2403.02905/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":"2403.02905","created_at":"2026-07-05T08:59:26.416116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02905v3","created_at":"2026-07-05T08:59:26.416116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02905","created_at":"2026-07-05T08:59:26.416116+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7Q2QV5TPPDX","created_at":"2026-07-05T08:59:26.416116+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7Q2QV5TPPDXHYWJ","created_at":"2026-07-05T08:59:26.416116+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7Q2QV5T","created_at":"2026-07-05T08:59:26.416116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01077","citing_title":"TRiMM: Transformer-Based Rich Motion Matching for Real-Time multi-modal Interaction in Digital Humans","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W","json":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W.json","graph_json":"https://pith.science/api/pith-number/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/graph.json","events_json":"https://pith.science/api/pith-number/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/events.json","paper":"https://pith.science/paper/C7Q2QV5T"},"agent_actions":{"view_html":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W","download_json":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W.json","view_paper":"https://pith.science/paper/C7Q2QV5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02905&json=true","fetch_graph":"https://pith.science/api/pith-number/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/graph.json","fetch_events":"https://pith.science/api/pith-number/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/action/storage_attestation","attest_author":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/action/author_attestation","sign_citation":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/action/citation_signature","submit_replication":"https://pith.science/pith/C7Q2QV5TPPDXHYWJ54BJCV4Y2W/action/replication_record"}},"created_at":"2026-07-05T08:59:26.416116+00:00","updated_at":"2026-07-05T08:59:26.416116+00:00"}