Research map / Label-efficient and robust learning / Recognition and long-tail
Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection
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 |
|---|---|---|---|
| add the AU–landmark relationship constraint to landmark prediction (ablation) | CJCRF · CK+ | normalized landmark detection error: 5.13 -> 4.86 | Helped |
| add the AU–landmark relationship constraint to landmark prediction (ablation) | CJCRF · CK+ | AU F1 (%): 70.80 -> 72.02 | Helped |
| add the face-shape relationship constraint to AU prediction (ablation) | CJCRF · CK+ | normalized landmark detection error: 5.13 -> 5.18 | Hurt |
| add the face-shape relationship constraint to AU prediction (ablation) | CJCRF · CK+ | AU F1 (%): 70.80 -> 78.72 | Helped |
| constrain both landmark and AU prediction using their learned joint relationships (ablation) | CJCRF · CK+ | AU F1 (%): 70.80 -> 78.74 | Helped |
| constrain both landmark and AU prediction using their learned joint relationships (ablation) | CJCRF · CK+ | AU AUC: 89.86 -> 94.28 | Helped |
| jointly estimate landmarks and AU activations with the learned relationship constraint | CJCRF · CK+ | normalized landmark detection error: 4.96 -> 4.66 | Helped |
| jointly estimate landmarks and AU activations with the learned relationship constraint | CJCRF · FERA | AU F1 (%): 56.58* -> 59.66 | Helped |
Closest papers by meaning
- Facial Landmarks Detection by Self-Iterative Regression Based Landmarks-Attention Network (AAAI 2018 · similarity 0.88)
- Dynamic Attention-Controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-Set Sample Weighting (CVPR 2017 · similarity 0.87)
- Self-Reinforced Cascaded Regression for Face Alignment (AAAI 2018 · similarity 0.87)
- Towards Accurate Facial Landmark Detection via Cascaded Transformers (CVPR 2022 · similarity 0.86)
- Simultaneous Facial Landmark Detection, Pose and Deformation Estimation Under Facial Occlusion (CVPR 2017 · similarity 0.86)
- Generalizable Face Landmarking Guided by Conditional Face Warping (CVPR 2024 · similarity 0.82)
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.