Research map / Detection and segmentation / CNN features
Action Unit Detection With Region Adaptation, Multi-Labeling Learning and Optimal Temporal Fusing
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 adaptive ROI Nets instead of fine-tuned VGG (ablation) | AU detection on BP4D · BP4D | average F1: 43.8 -> 56.4; 12.4% | Helped |
| Use multi-label learning instead of single-AU learning (ablation) | ROI Nets · BP4D | average F1: 1.3% | Helped |
| Add one LSTM layer for temporal fusion (ablation) | ROI Nets · BP4D | average F1: 56.4 -> 66.1; 9.7% | Helped |
| Use two stacked LSTM layers instead of one (ablation) | ROI Nets with temporal fusion · BP4D | average F1: 66.1 -> 61.4 | Hurt |
| Use one LSTM layer for temporal fusion (ablation) | ROI Nets · DISFA | average F1: 48.5 -> 51.3 | Helped |
Closest papers by meaning
- Deep Region and Multi-Label Learning for Facial Action Unit Detection (CVPR 2016 · similarity 0.92)
- Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition (NeurIPS 2019 · similarity 0.89)
- Facial Action Unit Detection With Transformers (CVPR 2021 · similarity 0.88)
- Knowledge-Driven Self-Supervised Representation Learning for Facial Action Unit Recognition (CVPR 2022 · similarity 0.88)
- Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation (CVPR 2018 · similarity 0.88)
- DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer (CVPR 2025 · 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.