Research map / Image generation / Editing and style transfer
Joint Pose and Expression Modeling for Facial Expression Recognition
Read the paperCheck 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 |
|---|---|---|---|
| Jointly model pose and expression, synthesize labeled training faces, and train FER end to end | Pose-invariant FER · Multi-PIE | accuracy: 90.60 -> 91.80 | Helped |
| Jointly model pose and expression, synthesize labeled training faces, and train FER end to end | Pose-invariant FER · BU-3DFE | accuracy: 80.1 -> 81.20 | Helped |
| Train on generated and original faces synthesized from BU-3DFE | FER classifier evaluated on SFEW Set 2 · SFEW Set 2 | accuracy: 24.70 -> 26.58 | Helped |
| Increase the number of generated training images (ablation) | FER classifier on Multi-PIE · Multi-PIE | accuracy | Helped |
Closest papers by meaning
- ExprGAN: Facial Expression Editing With Controllable Expression Intensity (AAAI 2018 · similarity 0.88)
- A 3D GAN for Improved Large-Pose Facial Recognition (CVPR 2021 · similarity 0.87)
- Facial Expression Recognition by De-Expression Residue Learning (CVPR 2018 · similarity 0.86)
- Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition (CVPR 2021 · similarity 0.86)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.85)
- Open-Set Facial Expression Recognition (AAAI 2024 · similarity 0.84)
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.