Research map / Video / Video segmentation and tracking
Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild
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 GCA and IAL to the ResNet18-based baseline (ablation) | DFER model · DFEW | UAR: 53.56 -> 55.71 | Helped |
| add GCA and IAL to the ResNet18-based baseline (ablation) | DFER model · FERV39k | UAR: 32.79 -> 35.82 | Helped |
| add GCA without IAL (ablation) | ResNet18-based DFER baseline · DFEW | UAR: 53.56 -> 54.12 | Helped |
| add IAL without GCA (ablation) | ResNet18-based DFER baseline · DFEW | UAR: 53.56 -> 54.58 | Helped |
| add GCA without IAL (ablation) | ResNet18-based DFER baseline · FERV39k | UAR: 32.79 -> 34.67 | Helped |
| add IAL without GCA (ablation) | ResNet18-based DFER baseline · FERV39k | UAR: 32.79 -> 34.96 | Helped |
| replace SE channel attention with GCA (ablation) | ResNet18-based DFER model · DFEW | UAR: 53.47 -> 54.12 | Helped |
| replace SE channel attention with GCA (ablation) | ResNet18-based DFER model · FERV39k | UAR: 33.16 -> 34.67 | Helped |
| replace CBAM channel attention with GCA (ablation) | ResNet18-based DFER model · DFEW | UAR: 53.78 -> 54.12 | Helped |
| increase the IAL loss coefficient from 0.1 to 0.3 with r=16 (ablation) | GCA+IAL · DFEW | UAR: 55.71 -> 54.82 | Hurt |
| increase the IAL loss coefficient from 0.1 to 0.3 with r=16 (ablation) | GCA+IAL · FERV39k | UAR: 35.56 -> 35.21 | Hurt |
| increase GCA reduction ratio from 8 to 16 with λ=0.1 (ablation) | GCA+IAL · DFEW | UAR: 54.58 -> 55.71 | Helped |
Closest papers by meaning
- Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition (CVPR 2023 · similarity 0.90)
- Lifting Scheme-Based Implicit Disentanglement of Emotion-Related Facial Dynamics in the Wild (AAAI 2025 · similarity 0.89)
- D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition. (CVPR 2025 · similarity 0.87)
- OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem (AAAI 2025 · similarity 0.87)
- Open-Set Facial Expression Recognition (AAAI 2024 · similarity 0.85)
- Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition (AAAI 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.