{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L3XQMTKNOGDHNHTCIFELBX44U4","short_pith_number":"pith:L3XQMTKN","schema_version":"1.0","canonical_sha256":"5eef064d4d7186769e624148b0df9ca725e856628364c1f2b7ad3777752d4771","source":{"kind":"arxiv","id":"2412.16563","version":3},"attestation_state":"computed","paper":{"title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfang Li, Jianqiang Ren, Jiaxu Zhang, Liefeng Bo, Xiangyue Zhang, Zhigang Tu, Ziqiang Dang","submitted_at":"2024-12-21T10:16:07Z","abstract_excerpt":"A good co-speech motion generation cannot be achieved without a careful integration of common rhythmic motion and rare yet essential semantic motion. In this work, we propose SemTalk for holistic co-speech motion generation with frame-level semantic emphasis. Our key insight is to separately learn base motions and sparse motions, and then adaptively fuse them. In particular, coarse2fine cross-attention module and rhythmic consistency learning are explored to establish rhythm-related base motion, ensuring a coherent foundation that synchronizes gestures with the speech rhythm. Subsequently, sem"},"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":"2412.16563","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T10:16:07Z","cross_cats_sorted":[],"title_canon_sha256":"912706b767a1884aaaa1b5c1306b4b14e4ebcdb0265fec64690215cfc239bba0","abstract_canon_sha256":"3c483109fb07c593a100a3c1351794c5bea8efb652f3ff91287b5f2098f7a987"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:31.408004Z","signature_b64":"scIW43/ZA3h06dW1VOaCG/7ApyvsDlvYyZmExRmxunKzPtfRk5+T+CXoEP6tLn1b/Rn5+gumb2dRAA5gYlDnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eef064d4d7186769e624148b0df9ca725e856628364c1f2b7ad3777752d4771","last_reissued_at":"2026-07-05T10:28:31.407299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:31.407299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfang Li, Jianqiang Ren, Jiaxu Zhang, Liefeng Bo, Xiangyue Zhang, Zhigang Tu, Ziqiang Dang","submitted_at":"2024-12-21T10:16:07Z","abstract_excerpt":"A good co-speech motion generation cannot be achieved without a careful integration of common rhythmic motion and rare yet essential semantic motion. In this work, we propose SemTalk for holistic co-speech motion generation with frame-level semantic emphasis. Our key insight is to separately learn base motions and sparse motions, and then adaptively fuse them. In particular, coarse2fine cross-attention module and rhythmic consistency learning are explored to establish rhythm-related base motion, ensuring a coherent foundation that synchronizes gestures with the speech rhythm. Subsequently, sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16563","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/2412.16563/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":"2412.16563","created_at":"2026-07-05T10:28:31.407392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16563v3","created_at":"2026-07-05T10:28:31.407392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16563","created_at":"2026-07-05T10:28:31.407392+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3XQMTKNOGDH","created_at":"2026-07-05T10:28:31.407392+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3XQMTKNOGDHNHTC","created_at":"2026-07-05T10:28:31.407392+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3XQMTKN","created_at":"2026-07-05T10:28:31.407392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08729","citing_title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08729","citing_title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4","json":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4.json","graph_json":"https://pith.science/api/pith-number/L3XQMTKNOGDHNHTCIFELBX44U4/graph.json","events_json":"https://pith.science/api/pith-number/L3XQMTKNOGDHNHTCIFELBX44U4/events.json","paper":"https://pith.science/paper/L3XQMTKN"},"agent_actions":{"view_html":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4","download_json":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4.json","view_paper":"https://pith.science/paper/L3XQMTKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16563&json=true","fetch_graph":"https://pith.science/api/pith-number/L3XQMTKNOGDHNHTCIFELBX44U4/graph.json","fetch_events":"https://pith.science/api/pith-number/L3XQMTKNOGDHNHTCIFELBX44U4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4/action/storage_attestation","attest_author":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4/action/author_attestation","sign_citation":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4/action/citation_signature","submit_replication":"https://pith.science/pith/L3XQMTKNOGDHNHTCIFELBX44U4/action/replication_record"}},"created_at":"2026-07-05T10:28:31.407392+00:00","updated_at":"2026-07-05T10:28:31.407392+00:00"}