Research map / Label-efficient and robust learning / Recognition and long-tail
Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation
Read the paperCheck 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 relevance and intensity smoothness (ablation) | BORMIR · FERA 2015 | MAE: 1.079 -> .852 | Helped |
| add relevance and intensity smoothness (ablation) | BORMIR · DISFA | MAE: 1.820 -> .789 | Helped |
| add ordinal relevance constraints (ablation) | BORMIR · FERA 2015 | MAE: .887 -> .852 | Helped |
| add ordinal relevance constraints (ablation) | BORMIR · DISFA | MAE: .901 -> .789 | Helped |
| add a valley bag label alongside the peak label (ablation) | BORMIR · FERA 2015 | MAE: 1.046 -> .852 | Helped |
| add a valley bag label alongside the peak label (ablation) | BORMIR · DISFA | MAE: .932 -> .789 | Helped |
| use relevance learning, two bag labels, and temporal domain constraints instead of MIR | frame-level AU intensity estimation · FERA 2015 | PCC: .460 -> .635 | Helped |
| use relevance learning, two bag labels, and temporal domain constraints instead of MI-DORF | pain intensity estimation · PAIN | PCC: .460 -> .605 | Helped |
| use continuous predictions rather than MI-DORF's discrete intensity output | pain intensity estimation · PAIN | MAE: .510 -> .821 | Hurt |
Closest papers by meaning
- Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation (CVPR 2019 · similarity 0.92)
- Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation (CVPR 2018 · similarity 0.90)
- 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 0.89)
- Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution (AAAI 2020 · similarity 0.89)
- AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement (CVPR 2024 · similarity 0.88)
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.