SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis

[2412.16563] SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2412.16563 (cs) [Submitted on 21 Dec 2024 ( v1 ), last revised 16 Aug 2026 (this version, v4)] Title: SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis Authors: Xiangyue Zhang , Jianfang Li , Jiaxu Zhang , Ziqiang Dang , Jianqiang Ren , Liefeng Bo , Zhigang Tu View a PDF of the paper titled SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis, by Xiangyue Zhang and 6 other authors View PDF HTML (experimental) Abstract: Co-speech gesture generation must carefully integrate common rhythmic motion with rare yet essential semantic gestures. In this work, we propose SemTalk for holistic co-speech gesture 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, semantic emphasis learning is designed to generate semantic-aware sparse motion, focusing on frame-level semantic cues. Finally, to integrate sparse motion into the base motion and generate semantic-emphasized co-speech gestures, we further leverage a learned semantic score for adaptive synthesis. Qualitative and quantitative comparisons on two public datasets demonstrate that our method outperforms the state-of-the-art, delivering high-quality co-speech motion with enhanced semantic richness over a stable base motion. Comments: 11 pages, 8 figures. Accepted to ICCV 2025. Project page: this https URL code and pretrained models: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2412.16563 [cs.CV] (or arXiv:2412.16563v4 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2412.16563 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025, pp. 13761-13771 Related DOI : https://doi.org/10.1109/ICCV51701.2025.01277 Focus to learn more DOI(s) linking to related resources Submission history From: Xiangyue Zhang [ view email ] [v1] Sat, 21 Dec 2024 10:16:07 UTC (42,278 KB) [v2] Wed, 15 Jan 2025 13:34:12 UTC (29,441 KB) [v3] Tue, 11 Mar 2025 13:04:35 UTC (39,155 KB) [v4] Sun, 16 Aug 2026 15:36:15 UTC (39,154 KB) Full-text links: Access Paper: View a PDF of the paper titled SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis, by Xiangyue Zhang and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2024-12 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis#611275
• Vorch-Human: Unified Multi-Task Human-Centric Generation via Long-Horizon Continuation#1062020
• EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation#1110408
• EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation#612774
• EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation#611297