Research map / Label-efficient and robust learning / Recognition and long-tail
Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally
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 local low-rank label correlations rather than global correlations | EDL-LRL · s-JAFFE | Chebyshev: 0.1211±0.008 -> 0.0806±0.006 | Helped |
| Use local low-rank label correlations rather than global correlations | EDL-LRL · s-JAFFE | Cosine: 0.9297±0.007 -> 0.9660±0.004 | Helped |
| Use local low-rank label correlations rather than global correlations | EDL-LRL · SBU 3DFE | Chebyshev: 0.1377±0.002 -> 0.0951±0.002 | Helped |
| Use local low-rank label correlations rather than global correlations | EDL-LRL · SBU 3DFE | Cosine: 0.9185±0.001 -> 0.9626±0.002 | Helped |
| Use local low-rank label correlations rather than global correlations | EDL-LRL · s-JAFFE | K-L: 0.0361±0.004; top 2 among compared methods | Mixed |
| Increase the training data size | EDL-LRL · s-JAFFE | Chebyshev | Helped |
| Use EDL-LRL with training data size greater than 40% | EDL-LRL · s-JAFFE | Chebyshev | Helped |
| Increase the number of clusters m (ablation) | EDL-LRL · s-JAFFE | Chebyshev | Helped |
| Increase the number of clusters m beyond the stable range (ablation) | EDL-LRL · s-JAFFE | Chebyshev | No clear effect |
Closest papers by meaning
- Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition (CVPR 2020 · similarity 0.89)
- A Circular-Structured Representation for Visual Emotion Distribution Learning (CVPR 2021 · similarity 0.88)
- When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework (AAAI 2022 · similarity 0.86)
- Navigating Label Ambiguity for Facial Expression Recognition in the Wild (AAAI 2025 · similarity 0.85)
- Distribution Matching for Multi-Task Learning of Classification Tasks: A Large-Scale Study on Faces & Beyond (AAAI 2024 · similarity 0.84)
- MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation (CVPR 2024 · 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.