Research map / Probabilistic and scientific modeling / Molecules and proteins
Deep Structured Learning for Facial Action Unit Intensity Estimation
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 ordinal unary potentials instead of softmax outputs | CNN AU-intensity estimation · DISFA | ICC(3,1): average difference is 7% | Helped |
| Use ordinal unary potentials instead of softmax outputs | CNN AU-intensity estimation · FERA2015 | ICC(3,1): average difference is 3% | Helped |
| Add copula pairwise dependencies to the ordinal CNN (ablation) | OCNN · DISFA | ICC(3,1): average improvement of 4% | Helped |
| Use balanced-batch iterative training (ablation) | CCNN · DISFA | ICC(3,1): another 3% | Helped |
| Use balanced-batch iterative training (ablation) | CCNN · FERA2015 | ICC(3,1) | No clear effect |
| Augment training with data from other datasets (ablation) | CCNN-IT · DISFA | ICC(3,1): increases by 7% | Helped |
| Augment training with data from other datasets (ablation) | CCNN-IT · DISFA | ICC(3,1) | Mixed |
| Use copula instead of linear pairwise potentials (ablation) | Structured CNN · DISFA, especially AU1-AU2 and AU6-AU12 | ICC(3,1) | Helped |
Closest papers by meaning
- Copula Ordinal Regression for Joint Estimation of Facial Action Unit Intensity (CVPR 2016 · similarity 0.91)
- Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation (CVPR 2018 · similarity 0.90)
- Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition (NeurIPS 2020 · similarity 0.90)
- Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation (CVPR 2019 · similarity 0.90)
- Dynamic Probabilistic Graph Convolution for Facial Action Unit Intensity Estimation (CVPR 2021 · similarity 0.89)
- AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement (CVPR 2024 · similarity 0.87)
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.