Research map / Video / Video generation
SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis
Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Ziqiang Dang, Jianqiang Ren, Liefeng Bo, Zhigang Tu
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 sem-gate (ablation) | SemTalk · BEAT2 | FGD: 4.893 -> 4.278 | Improved |
| add sem-gate with learned scores instead of random scores (ablation) | SemTalk · BEAT2 | FGD: 4.634 -> 4.278 | Improved |
| use sem-gate instead of LivelySpeaker SAG (ablation) | SemTalk · BEAT2 | FGD: 4.618 -> 4.278 | Improved |
| add feature and loss weighting to sem-gate (ablation) | SemTalk · BEAT2 | Acc(%): 72.32 -> 82.76 | Improved |
| add feature weighting to sem-gate (ablation) | SemTalk · BEAT2 | Acc(%): 72.32 -> 78.52 | Improved |
| add loss weighting to sem-gate (ablation) | SemTalk · BEAT2 | FGD: 4.495 -> 4.366 | Improved |
| add rhythmic consistency learning (ablation) | SemTalk · BEAT2 | FGD: 5.484 -> 4.867 | Improved |
| add rhythmic consistency learning (ablation) | SemTalk · BEAT2 | MSE: 13.882 -> 6.201 | Improved |
| add semantic emphasis learning to RC + RVQ (ablation) | SemTalk · BEAT2 | DIV: 12.38 -> 12.83 | Improved |
| add Coarse2Fine cross-attention to RC + SE + RVQ (ablation) | SemTalk · BEAT2 | FGD: 4.526 -> 4.278 | Improved |
| add RVQ-VAE (ablation) | SemTalk · BEAT2 | FGD: 6.234 -> 5.484 | Improved |
| add RVQ-VAE (ablation) | SemTalk · BEAT2 | MSE: 8.239 -> 13.882 | Hurt |
Later papers that compared with this method
4 later accepted papers report SemTalk as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching (ECCV 2026 · better on 6 of 6 shared results)
- RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction (ECCV 2026 · better on 5 of 5 shared results)
- StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring (ECCV 2026 · better on 2 of 2 shared results)
- Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion Generation (NeurIPS 2026 · better on 1 of 1 shared result)
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
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · similarity 0.90)
- Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis (CVPR 2025 · similarity 0.89)
- Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement (CVPR 2025 · similarity 0.89)
- ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis (CVPR 2024 · similarity 0.89)
- 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.
