Research map / Video / Video generation
MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation
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 |
|---|---|---|---|
| use generated videos instead of captured videos for human emotion recognition | MEAD baseline · MEAD user study (mean accuracy) | emotion recognition accuracy: 0.85 -> 0.74 | Hurt |
| use generated videos instead of captured videos for the neutral class | MEAD baseline · MEAD user study (neutral) | emotion recognition accuracy: 0.65 -> 0.52 | Hurt |
| evaluate generated videos with a classifier trained on captured data | MEAD baseline · MEAD emotion classification | accuracy (%): 86.29 -> 86.26 | No clear effect |
| train baselines (ATVGnet, ADAVR, CycleGAN) per emotion instead of using the conditional emotion model | ATVGnet / ADAVR / CycleGAN · MEAD emotion intensity manipulation | qualitative intensity distinction | Hurt |
| use the proposed intensity manipulation across all emotion categories | MEAD baseline · MEAD user study, intensity ranking | participant agreement: about 20% | Hurt |
Closest papers by meaning
- FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization (CVPR 2024 · similarity 0.89)
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.89)
- MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation (CVPR 2025 · similarity 0.89)
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (NeurIPS 2024 · similarity 0.88)
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (CVPR 2025 · similarity 0.88)
- TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation (NeurIPS 2025 · similarity 0.87)
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.
