Research map / Video / Video generation
Audio-Driven Emotional Video Portraits
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 EVP instead of the strongest reported baseline | Audio-driven emotional video portrait generation · MEAD | M-LD: 2.52 -> 2.45 | Helped |
| Use EVP instead of the strongest reported baseline | Audio-driven emotional video portrait generation · MEAD | M-LVD: 1.99 -> 1.78 | Helped |
| Use EVP instead of the strongest reported baseline | Audio-driven emotional video portrait generation · MEAD | F-LD: 3.16 -> 3.01 | Helped |
| Use EVP instead of the strongest reported baseline | Audio-driven emotional video portrait generation · MEAD | F-LVD: 1.71 -> 1.56 | Helped |
| Use EVP instead of the strongest reported baseline | Audio-driven emotional video portrait generation · MEAD | SSIM: 0.68 -> 0.71 | Helped |
| Use EVP instead of the strongest reported baseline | Audio-driven emotional video portrait generation · MEAD | PSNR: 29.11 -> 29.53 | Helped |
| Use EVP instead of the strongest reported baseline | Audio-driven emotional video portrait generation · MEAD | FID: 22.52 -> 7.99 | Helped |
| Add emotion classification loss (ablation) | EVP cross-reconstructed emotion disentanglement · MEAD | M-LD: 2.72 -> 2.45 | Helped |
| Add content loss (ablation) | EVP cross-reconstructed emotion disentanglement · MEAD | M-LD: 2.65 -> 2.45 | Helped |
| Add self-reconstruction loss (ablation) | EVP cross-reconstructed emotion disentanglement · MEAD | M-LD: 2.47 -> 2.45 | Helped |
| Add cross-reconstruction loss (ablation) | EVP cross-reconstructed emotion disentanglement · MEAD | M-LD: 2.54 -> 2.45 | Helped |
| Add cross-reconstruction training (ablation) | EVP emotion representation and synthesized portraits · MEAD test set | emotion accuracy: 69.79% -> 83.58% | Helped |
Closest papers by meaning
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.90)
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (CVPR 2025 · similarity 0.90)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.89)
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (NeurIPS 2024 · similarity 0.89)
- FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization (CVPR 2024 · similarity 0.88)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (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.