Facial Expression Recognition on AffectNet-8
64.79AccuracyFMAE
Evaluation Results
| Method | Links | |
|---|---|---|
| FMAEContrastive=false, MIM=true2024.07 | 64.79 | |
| LaCoVL-FERYear=2026, Vision Backbone=CLIP-ViT-B/162026.05 | 64.75 | |
| LA-NetContrastive=true, MIM=false2024.07 | 64.54 | |
| DCSYear=AAAI25, Vision Backbone=IR50+ViT2026.05 | 64.4 | |
| QCSYear=AAAI25, Vision Backbone=IR50+ViT2026.05 | 64.3 | |
| POSTER++Year=PR25, Vision Backbone=IR50+ViT2026.05 | 63.77 | |
| POSTERYear=ICCV23, Vision Backbone=IR50+ViT2026.05 | 63.34 | |
| ICoCOYear=TAC26, Vision Backbone=CLIP-ViT-B/162026.05 | 62.98 | |
| ExpLLMYear=TMM25, Vision Backbone=ViT-L/142026.05 | 62.86 | |
| TPRDYear=TAC25, Vision Backbone=CLIP-ViT-B/162026.05 | 62.85 | |
| CLEFContrastive=true, MIM=false2024.07 | 62.77 | |
| CEPromptYear=TCSVT24, Vision Backbone=CLIP-ViT-B/162026.05 | 62.74 | |
| SOFTYear=ECCV22, Vision Backbone=ResNet-182026.05 | 62.69 | |
| PIDVITYear=TAC22, Vision Backbone=ViT2026.05 | 62.52 | |
| MRANYear=TCSVT23, Vision Backbone=ResNet-182026.05 | 62.48 | |
| CLIPERYear=ICME24, Vision Backbone=CLIP-ViT-B/162026.05 | 61.98 | |
| VLCAYear=ESWA25, Vision Backbone=CLIP-ViT-B/322026.05 | 61.96 | |
| VTFFYear=TAC21, Vision Backbone=ResNet18+ViT-B2026.05 | 61.85 | |
| CMNetClasses=82026.05 | 61.29 | |
| LAENet-SAClasses=82026.05 | 61.22 | |
| MCFContrastive=true, MIM=false2024.07 | 60.98 | |
| FG-AGRClasses=82026.05 | 60.69 | |
| FG-AGRYear=TCSVT23, Vision Backbone=ResNet-182026.05 | 60.69 | |
| MA-NetClasses=82026.05 | 60.29 | |
| SCNClasses=82026.05 | 60.23 | |
| SCNYear=CVPR20, Vision Backbone=ResNet-182026.05 | 60.23 | |
| EfficientFaceClasses=82026.05 | 59.89 | |
| EfficientFaceYear=AAAI21, Vision Backbone=ResNet-502026.05 | 59.89 | |
| RANClasses=82026.05 | 59.5 | |
| ESR-9Classes=82026.05 | 59.3 | |
| AlexNet-WLClasses=82026.05 | 58 | |
| IPA2LTClasses=82026.05 | 57.31 | |
| VGG-NetClasses=82026.05 | 56 | |
| PhaNetClasses=82026.05 | 54.82 | |
| RANYear=TIP20, Vision Backbone=ResNet-182026.05 | 52.97 |