Facial Expression Recognition On Fer2013
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| a-novel-facial-emotion-recognition-model | 75.97 |
| facial-expression-recognition-using-residual | 76.82 |
| convolutional-neural-network-hyperparameters | 72.16 |
| resemotenet-bridging-accuracy-and-loss | 79.79 |
| ad-corre-adaptive-correlation-based-loss-for | 72.03 |
| mini-resemotenet-leveraging-knowledge | 70.20 |
| local-learning-with-deep-and-handcrafted | 75.42 |
| local-multi-head-channel-self-attention-for | 74.42 |
| emonext-an-adapted-convnext-for-facial-1 | 76.12 |
| mini-resemotenet-leveraging-knowledge | 76.33 |
| regularized-xception-for-facial-expression | 94.34 |
| fer2013-recognition-resnet18-with-tricks | 73.70 |
| challenges-in-representation-learning-a | 67.48 |
| facial-emotion-recognition-state-of-the-art | 73.28 |
| facial-expression-recognition-using-residual | 74.14 |
| deep-emotion-facial-expression-recognition | 70.02 |