HyperAI超神経

Facial Expression Recognition On Affectnet

評価指標

Accuracy (8 emotion)

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Accuracy (8 emotion)
Paper TitleRepository
VGG-FACE60.40Deep Neural Network Augmentation: Generating Faces for Affect Analysis-
PSR (VGG-16)60.68Pyramid With Super Resolution for In-the-Wild Facial Expression Recognition
EfficientFace59.89Robust Lightweight Facial Expression Recognition Network with Label Distribution Training
ResEmoteNet-ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition
SL (B0)60.34Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation-
Vit-base + MAE62.42Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers-
FerNeXt-FerNeXt: Facial Expression Recognition Using ConvNeXt with Channel Attention
CNNs and BOVW + local SVM59.58Local Learning with Deep and Handcrafted Features for Facial Expression Recognition-
Distilled student61.60Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition-
LFNSB63.12A Lightweight Model Enhancing Facial Expression Recognition with Spatial Bias and Cosine-Harmony Loss
PAENet-Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning
Ad-Corre-Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild-
Facial Motion Prior Network-Facial Motion Prior Networks for Facial Expression Recognition
Ada-DF-A Dual-Branch Adaptive Distribution Fusion Framework for Real-World Facial Expression Recognition
POSTER++63.77POSTER++: A simpler and stronger facial expression recognition network
SL + SSL puzzling (B0)61.09Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation-
Ensemble with Shared Representations (ESR-9)59.3Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networks
S2D63.06From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos
EAC-Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition
QCS64.4QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition
0 of 49 row(s) selected.