Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Region and Multi-Label Learning for Facial Action Unit 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 |
|---|---|---|---|
| Use DRML instead of JPML | AU detection · BP4D | F1-frame (Avg.): 45.9 -> 48.3 | Helped |
| Use DRML instead of LCN | AU detection · BP4D | AUC (Avg.): 54.4 -> 56.0 | Helped |
| Use DRML instead of LCN | AU detection · DISFA | F1-frame (Avg.): 24.0 -> 26.7 | Helped |
| Use DRML instead of AlexNet | AU detection · DISFA | AUC (Avg.): 49.1 -> 52.3 | Helped |
| Add the region layer to ConvNet (ablation) | DRML · BP4D, AU 1 | F1-frame: 40.4 -> 36.4 | Hurt |
| Add the region layer to ConvNet (ablation) | DRML · DISFA, AU 4 | F1-frame: 28.9 -> 37.4 | Helped |
Closest papers by meaning
- Action Unit Detection With Region Adaptation, Multi-Labeling Learning and Optimal Temporal Fusing (CVPR 2017 · similarity 0.92)
- Knowledge-Driven Self-Supervised Representation Learning for Facial Action Unit Recognition (CVPR 2022 · similarity 0.89)
- Facial Action Unit Detection With Transformers (CVPR 2021 · similarity 0.89)
- Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition (NeurIPS 2019 · similarity 0.88)
- Self-Supervised Facial Representation Learning with Facial Region Awareness (CVPR 2024 · similarity 0.86)
- Distribution Matching for Multi-Task Learning of Classification Tasks: A Large-Scale Study on Faces & Beyond (AAAI 2024 · similarity 0.85)
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.