Research map / Label-efficient and robust learning / Recognition and long-tail
Joint Representation and Estimator 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 |
|---|---|---|---|
| Add label-ranking constraints (ablation) | Joint representation and estimator learning for AU intensity estimation · FERA 2015, 6% annotated frames | PCC: .54 -> .58 | Helped |
| Add temporal label-smoothness regularization (ablation) | Joint representation and estimator learning for AU intensity estimation · FERA 2015, 6% annotated frames | PCC: .54 -> .57 | Helped |
| Add temporal feature-smoothness regularization (ablation) | Joint representation and estimator learning for AU intensity estimation · FERA 2015, 6% annotated frames | PCC: .54 -> .55 | Helped |
| Add positive-intensity constraints (ablation) | Joint representation and estimator learning for AU intensity estimation · FERA 2015, 6% annotated frames | PCC: .54 -> .56 | Helped |
| Combine label ranking, label smoothness, feature smoothness, and positive-intensity constraints (ablation) | Joint representation and estimator learning for AU intensity estimation · FERA 2015, 6% annotated frames | PCC: .54 -> .62 | Helped |
| Combine label ranking, label smoothness, feature smoothness, and positive-intensity constraints (ablation) | Joint representation and estimator learning for AU intensity estimation · DISFA, 6% annotated frames | PCC: .26 -> .37 | Helped |
| Jointly learn representation and estimator and incorporate weak human-knowledge supervision | AU intensity estimation · FERA 2015, 2%–10% annotation ratios | PCC | Helped |
Closest papers by meaning
- Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation (CVPR 2018 · similarity 0.93)
- Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation (CVPR 2018 · similarity 0.92)
- AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement (CVPR 2024 · similarity 0.91)
- Copula Ordinal Regression for Joint Estimation of Facial Action Unit Intensity (CVPR 2016 · similarity 0.90)
- Trend-Aware Supervision: On Learning Invariance for Semi-supervised Facial Action Unit Intensity Estimation (AAAI 2024 · similarity 0.90)
- Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution (AAAI 2020 · similarity 0.90)
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.