Research map / Label-efficient and robust learning / Recognition and long-tail
Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition
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 FDN to the ResNet-18 baseline (ablation) | FDRL · MMI | accuracy: 79.69 -> 81.23 | Helped |
| Add FDN to the ResNet-18 baseline (ablation) | FDRL · RAF-DB | accuracy: 86.93 -> 87.71 | Helped |
| Add Intra-RM to FDN (ablation) | FDRL · MMI | accuracy: 81.23 -> 84.74 | Helped |
| Add Inter-RM to FDN (ablation) | FDRL · MMI | accuracy: 81.23 -> 83.44 | Helped |
| Add both Intra-RM and Inter-RM to FDN (ablation) | FDRL · MMI | accuracy: 81.23 -> 85.23 | Helped |
| Add Intra-RM to FDN (ablation) | FDRL · RAF-DB | accuracy: 87.71 -> 89.34 | Helped |
| Add Inter-RM to FDN (ablation) | FDRL · RAF-DB | accuracy: 87.71 -> 88.76 | Helped |
| Add both Intra-RM and Inter-RM to FDN (ablation) | FDRL · RAF-DB | accuracy: 87.71 -> 89.47 | Helped |
| Add compactness loss with λ1=0.0001 rather than omit it (ablation) | FDRL · MMI | accuracy: 84.64 -> 85.23 | Helped |
| Add compactness loss with λ1=0.0001 rather than omit it (ablation) | FDRL · RAF-DB | accuracy: 88.75 -> 89.47 | Helped |
| Use balance loss with λ2=1.0 rather than omit it (ablation) | FDRL · MMI | accuracy: 82.66 -> 85.23 | Helped |
| Use balance loss with λ2=1.0 rather than omit it (ablation) | FDRL · RAF-DB | accuracy: 88.23 -> 89.47 | Helped |
Closest papers by meaning
- When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework (AAAI 2022 · similarity 0.88)
- Multi-Label Compound Expression Recognition: C-EXPR Database & Network (CVPR 2023 · similarity 0.87)
- Open-Set Facial Expression Recognition (AAAI 2024 · similarity 0.86)
- QCS:Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition (AAAI 2025 · similarity 0.86)
- Lifting Scheme-Based Implicit Disentanglement of Emotion-Related Facial Dynamics in the Wild (AAAI 2025 · similarity 0.85)
- Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.85)
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.