Research map / Label-efficient and robust learning / Recognition and long-tail
Facial Expression Intensity Estimation Using Ordinal Information
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 within-sequence ordinal information to fully supervised regression | OSVR-L1 vs SVR on PAIN · PAIN, fully supervised | PCC: 0.5659 -> 0.5999 | Helped |
| Use squared hinge loss instead of hinge loss (ablation) | OSVR on PAIN · PAIN, fully supervised | MAE: 1.0252 -> 0.8095 | Helped |
| Add ordinal information to weakly supervised regression | OSVR-L2 vs RVR on PAIN · PAIN, weakly supervised | MAE: 1.1122 -> 0.9519 | Helped |
| Use squared hinge loss instead of hinge loss (ablation) | OSVR on PAIN · PAIN, weakly supervised | PCC: 0.4981 -> 0.5441 | Helped |
| Add ordinal regression constraints without intensity labels | OSVR-L2 vs OR on PAIN · PAIN, unsupervised | PCC: 0.4572 -> 0.5101 | Helped |
| Use squared hinge loss instead of hinge loss (ablation) | OSVR on PAIN · PAIN, unsupervised | MAE: 2.6399 -> 1.1180 | Helped |
| Set temporal smoothness coefficients to 1 rather than 1/|i-j| (ablation) | OSVR on CK+ and BU-4DFE · CK+ and BU-4DFE | PCC | Helped |
| Use OSVR-L2 rather than the best competing method | OSVR-L2 on CK+ · CK+ | PCC: +3.5% | Helped |
| Use OSVR-L2 rather than the second-best method | OSVR-L2 on BU-4DFE · BU-4DFE | MAE: 33.8% | Helped |
Closest papers by meaning
- Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation (CVPR 2019 · similarity 0.87)
- Multi-Dimensional, Nuanced and Subjective - Measuring the Perception of Facial Expressions (CVPR 2022 · similarity 0.86)
- EmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of a Million Facial Expressions in the Wild (CVPR 2016 · similarity 0.85)
- AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement (CVPR 2024 · similarity 0.85)
- Trend-Aware Supervision: On Learning Invariance for Semi-supervised Facial Action Unit Intensity Estimation (AAAI 2024 · similarity 0.85)
- Navigating Label Ambiguity for Facial Expression Recognition in the Wild (AAAI 2025 · similarity 0.84)
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.