Research map / Video / Video generation
HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching
Lanmiao Liu, Esam Ghaleb, asli ozyurek, Zerrin Yumak
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add SACM (ablation) | HolisticSemGes · BEAT2 (25 speakers) | FGD: 4.125 -> 2.247 | Improved |
| add SACM (ablation) | HolisticSemGes · BEAT2 (25 speakers) | BC: 0.592 -> 0.780 | Improved |
| add SACM (ablation) | HolisticSemGes · BEAT2 (25 speakers) | Diversity: 102 -> 120 | Improved |
| add SACM (ablation) | HolisticSemGes · SHOW (4 speakers) | FGD: 24.28 -> 18.92 | Improved |
| add SACM (ablation) | HolisticSemGes · SHOW (4 speakers) | BC: 0.726 -> 0.831 | Improved |
| add audio alignment to text-only SACM (ablation) | HolisticSemGes · BEAT2 (25 speakers) | FGD: 3.216 -> 2.247 | Improved |
| add text alignment to audio-only SACM (ablation) | HolisticSemGes · BEAT2 (25 speakers) | FGD: 3.849 -> 2.247 | Improved |
| add text alignment to audio-only SACM (ablation) | HolisticSemGes · SHOW (4 speakers) | FGD: 22.85 -> 18.92 | Improved |
| add contrastive flow matching instead of standard FM (ablation) | HolisticSemGes · BEAT2 (25 speakers) | FGD: 4.269 -> 2.247 | Improved |
| add contrastive flow matching instead of standard FM (ablation) | HolisticSemGes · SHOW (4 speakers) | FGD: 22.86 -> 18.92 | Improved |
| add contrastive flow matching instead of standard FM (ablation) | HolisticSemGes · BEAT2 (25 speakers) | BC: 0.776 -> 0.780 | No clear effect |
| add contrastive flow matching instead of standard FM (ablation) | HolisticSemGes · SHOW (4 speakers) | Diversity: 101 -> 112 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SemTalk — SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis (ICCV 2025) · better on 6 of 6 shared results
- GestureLSM — GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling (ICCV 2025) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis (CVPR 2024 · similarity 0.90)
- Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis (CVPR 2025 · similarity 0.89)
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · similarity 0.89)
- DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation (CVPR 2024 · similarity 0.88)
- Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model (CVPR 2024 · similarity 0.88)
- HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
