Research map / Vision-language and multimodal / Cross-modal learning
VividListener: Expressive and Controllable Listener Dynamics Modeling for Multi-Modal Responsive Interaction
Shiying Li, Xingqun Qi, Bingkun Yang, Weile Chen, Zezhao Tian, Muyi Sun, Qifeng Liu, Man Zhang, Zhenan Sun
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 Temporal Semantic Interaction (ablation) | VividListener · ListenerX | FD: 6.38 -> 3.79 | Improved |
| add Emotional Control layer (ablation) | VividListener · ListenerX | FD: SID 4.72 -> 4.80; rPCC 0.05 -> 0.04; FD 4.00 -> 3.79 | Improved |
| add emotional intensity predictor loss (ablation) | VividListener · ListenerX | Var: Var 0.09 -> 0.21; FD 5.95 -> 3.79 | Improved |
| add text descriptions as input (ablation) | VividListener · ListenerX | FD: FD 4.83 -> 3.79 | Improved |
| add emotional intensity tags (ablation) | VividListener · ListenerX | Var: Var 0.10 -> 0.21; SID 4.34 -> 4.80 | Improved |
| VividListener vs RLHG/L2L/DIM on full ListenerX | VividListener · ListenerX | FD: FD expression 5.842 -> 3.792, but rPCC expression 0.033 (RLHG) vs 0.040 | Mixed |
| VividListener vs baselines cross-scenario (DailyX train, InterviewX test) | VividListener · ListenerX cross-scenario | FD: FD expression 41.510 -> 16.309 | Improved |
| VividListener vs baselines on L2L and ViCo datasets | VividListener · L2L / ViCo | FD: ViCo FD 5.37 (RLHG) vs 5.39 (ours) | Mixed |
Closest papers by meaning
- CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation (CVPR 2024 · similarity 0.89)
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.86)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.86)
- MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation (CVPR 2025 · similarity 0.86)
- OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions (NeurIPS 2025 · similarity 0.86)
- GLARE: Generating Listening Heads with Appropriate REactions (NeurIPS 2026 · similarity 0.86)
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.
