SOTAVerified

Facial Expression Recognition (FER)

Facial Expression Recognition (FER) is a computer vision task aimed at identifying and categorizing emotional expressions depicted on a human face. The goal is to automate the process of determining emotions in real-time, by analyzing the various features of a face such as eyebrows, eyes, mouth, and other features, and mapping them to a set of emotions such as anger, fear, surprise, sadness and happiness.

( Image credit: DeXpression )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 492 papers

TitleStatusHype
Multimodal Prompt Alignment for Facial Expression Recognition—0
EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression RecognitionCode1
TKFNet: Learning Texture Key Factor Driven Feature for Facial Expression Recognition—0
Achieving 3D Attention via Triplet Squeeze and Excitation Block—0
SDAFE: A Dual-filter Stable Diffusion Data Augmentation Method for Facial Expression Recognition—0
Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target DataCode0
Evaluating Facial Expression Recognition Datasets for Deep Learning: A Benchmark Study with Novel Similarity Metrics—0
V-NAW: Video-based Noise-aware Adaptive Weighting for Facial Expression RecognitionCode0
Biased Heritage: How Datasets Shape Models in Facial Expression RecognitionCode0
Rank-O-ToM: Unlocking Emotional Nuance Ranking to Enhance Affective Theory-of-Mind—0
Faces of Fairness: Examining Bias in Facial Expression Recognition Datasets and ModelsCode0
Navigating Label Ambiguity for Facial Expression Recognition in the WildCode0
Mini-ResEmoteNet: Leveraging Knowledge Distillation for Human-Centered Design—0
Uncertainty-Aware Label Refinement on Hypergraphs for Personalized Federated Facial Expression RecognitionCode0
A novel deep learning approach for facial emotion recognition: application to detecting emotional responses in elderly individuals with Alzheimer’s diseaseCode1
Unimodal and Multimodal Static Facial Expression Recognition for Virtual Reality Users with EmoHeVRDBCode0
Swin Transformer with Enhanced Dropout and Layer-wise Unfreezing for Facial Expression Recognition in Mental Health DetectionCode1
Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation—0
Prior-based Objective Inference Mining Potential Uncertainty for Facial Expression RecognitionCode0
A survey on Graph Deep Representation Learning for Facial Expression Recognition—0
Smile upon the Face but Sadness in the Eyes: Emotion Recognition based on Facial Expressions and Eye Behaviors—0
QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression RecognitionCode1
AffectNet+: A Database for Enhancing Facial Expression Recognition with Soft-Labels—0
Balancing the Scales: Enhancing Fairness in Facial Expression Recognition with Latent Alignment—0
Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression RecognitionCode0
GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution—0
Regularized Xception for facial expression recognition with extra training data and step decay learning rateCode0
EmojiHeroVR: A Study on Facial Expression Recognition under Partial Occlusion from Head-Mounted DisplaysCode0
Spatial Action Unit Cues for Interpretable Deep Facial Expression RecognitionCode1
Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation—0
ExpLLM: Towards Chain of Thought for Facial Expression RecognitionCode1
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion RecognitionCode0
A Survey on Facial Expression Recognition of Static and Dynamic EmotionsCode1
From Bias to Balance: Detecting Facial Expression Recognition Biases in Large Multimodal Foundation Models—0
EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction TuningCode0
Generalizable Facial Expression RecognitionCode1
LLDif: Diffusion Models for Low-light Emotion Recognition—0
A Lightweight Model Enhancing Facial Expression Recognition with Spatial Bias and Cosine-Harmony LossCode0
Norface: Improving Facial Expression Analysis by Identity NormalizationCode1
Representation Learning and Identity Adversarial Training for Facial Behavior UnderstandingCode2
Learning with Alignments: Tackling the Inter- and Intra-domain Shifts for Cross-multidomain Facial Expression RecognitionCode1
Batch Transformer: Look for Attention in Batch—0
Real Time Emotion Analysis Using Deep Learning for Education, Entertainment, and Beyond—0
GCF: Graph Convolutional Networks for Facial Expression RecognitionCode0
Less can be more: representational vs. stereotypical gender bias in facial expression recognition—0
Multi-threshold Deep Metric Learning for Facial Expression Recognition—0
FaceMixup: Enhancing Facial Expression Recognition through Mixed Face Regularization—0
Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge TransferCode2
FER-YOLO-Mamba: Facial Expression Detection and Classification Based on Selective State SpaceCode2
Ada-DF: An Adaptive Label Distribution Fusion Network For Facial Expression RecognitionCode1
Show:102550
← PrevPage 1 of 10Next →
All datasetsAffectNetRAF-DBFER2013FER+Acted Facial Expressions In The Wild (AFEW)CK+FERPlusJAFFESFEWAff-Wild2BP4DDISFA

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResEmoteNetAccuracy (7 emotion)72.93—Unverified
2NorfaceAccuracy (8 emotion)68.69—Unverified
3EmoAffectNetAccuracy (7 emotion)66.49—Unverified
4Emotion-GCNAccuracy (7 emotion)66.46—Unverified
5FaceBehaviorNetAccuracy (7 emotion)65.4—Unverified
6Ada-DFAccuracy (7 emotion)65.34—Unverified
7EACAccuracy (7 emotion)65.32—Unverified
8PAENetAccuracy (7 emotion)65.29—Unverified
9DACLAccuracy (7 emotion)65.2—Unverified
10DDAMFN++Accuracy (8 emotion)65.04—Unverified
#ModelMetricClaimedVerifiedStatus
1ResEmoteNetOverall Accuracy94.76—Unverified
2FMAEOverall Accuracy93.45—Unverified
3QCSOverall Accuracy93.02—Unverified
4NorfaceOverall Accuracy92.97—Unverified
5S2DOverall Accuracy92.57—Unverified
6BTNOverall Accuracy92.54—Unverified
7GReFELOverall Accuracy92.47—Unverified
8DDAMFN++Overall Accuracy92.34—Unverified
9DCJTOverall Accuracy92.24—Unverified
10POSTER++Overall Accuracy92.21—Unverified
#ModelMetricClaimedVerifiedStatus
1EfficientFERAccuracy82.47—Unverified
2FERNeXt-SDAFEAccuracy81.33—Unverified
3ResEmoteNetAccuracy79.79—Unverified
4Ensemble ResMaskingNet with 6 other CNNsAccuracy76.82—Unverified
5Mini-ResEmoteNet (A)Accuracy76.33—Unverified
6EmoNeXtAccuracy76.12—Unverified
7Segmentation VGG-19Accuracy75.97—Unverified
8Local Learning Deep+BOWAccuracy75.42—Unverified
9LHC-NetAccuracy74.42—Unverified
10Residual Masking NetworkAccuracy74.14—Unverified
#ModelMetricClaimedVerifiedStatus
1PAtt-LiteAccuracy95.55—Unverified
2GReFELAccuracy93.09—Unverified
3QCSAccuracy91.85—Unverified
4ResNet18 Dense ArchitectureAccuracy91.41—Unverified
5DDAMFNAccuracy90.74—Unverified
6KTNAccuracy90.49—Unverified
7Vit-base + MAEAccuracy90.18—Unverified
8FER-VTAccuracy90.04—Unverified
9EACAccuracy89.64—Unverified
10LResNet50E-IRAccuracy89.26—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy(on validation set)65.5—Unverified
2LResNet50E-IR (5 models with augmentation)Accuracy(on validation set)65.5—Unverified
3EACAccuracy(on validation set)65.32—Unverified
4LResNet50E-IR (1 model with augmentation)Accuracy(on validation set)63.7—Unverified
5LResNet50E-IR (1 model)Accuracy(on validation set)61.1—Unverified
6Multi-task EfficientNet-B0Accuracy(on validation set)59.27—Unverified
7resnet18_noisyAccuracy(on validation set)55.17—Unverified
8resnet18Accuracy(on validation set)51.18—Unverified
#ModelMetricClaimedVerifiedStatus
1EmoNeXtAccuracy (8 emotion)100—Unverified
2PAtt-LiteAccuracy (7 emotion)100—Unverified
3ViT + SEAccuracy (7 emotion)99.8—Unverified
4FANAccuracy (7 emotion)99.7—Unverified
5Nonlinear eval on SL + SSL puzzling (B0)Accuracy (7 emotion)98.23—Unverified
6DeepEmotionAccuracy (7 emotion)98—Unverified
7FN2ENAccuracy (8 emotion)96.8—Unverified
#ModelMetricClaimedVerifiedStatus
1KTNAccuracy(pretrained)90.49—Unverified
2RAN (VGG-16)Accuracy(pretrained)89.16—Unverified
3SENet TeacherAccuracy(pretrained)88.88—Unverified
4Local Learning Deep + BOWAccuracy(pretrained)87.76—Unverified
#ModelMetricClaimedVerifiedStatus
1TLAccuracy99.52—Unverified
2GReFELAccuracy96.67—Unverified
3ViTAccuracy94.83—Unverified
4DeepEmotionAccuracy92.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Ada-DFAccuracy60.46—Unverified
2RAN (VGG16+ResNet18)Accuracy56.4—Unverified
3ViT + SEAccuracy54.29—Unverified
4Island LossAccuracy52.52—Unverified
#ModelMetricClaimedVerifiedStatus
1GReFELAccuracy72.48—Unverified
2EmoAffectNet LSTMUAR52.9—Unverified
#ModelMetricClaimedVerifiedStatus
1NorfaceICC0.74—Unverified
2Ours (VGG-F)ICC0.72—Unverified
#ModelMetricClaimedVerifiedStatus
1NorfaceICC0.67—Unverified
2Ours (VGG-F)ICC0.6—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepEmotionAccuracy99.3—Unverified
2GReFELAccuracy98.18—Unverified
#ModelMetricClaimedVerifiedStatus
1DeXpressionAccuracy98.63—Unverified
2Facial Motion Prior NetworkAccuracy82.74—Unverified
#ModelMetricClaimedVerifiedStatus
1Dynamic MTLAccuracy (10-fold)89.6—Unverified
2PPDNAccuracy (10-fold)84.59—Unverified
#ModelMetricClaimedVerifiedStatus
1Covariance PoolingAccuracy87—Unverified
2Multi Label OutputAccuracy79.26—Unverified
#ModelMetricClaimedVerifiedStatus
1Covariance PoolingAccuracy58.14—Unverified
2VGG-VD-16Accuracy54.82—Unverified
#ModelMetricClaimedVerifiedStatus
1EfficientFaceAccuracy 85.87—Unverified
#ModelMetricClaimedVerifiedStatus
1Sequential forward selectionAccuracy88.7—Unverified
#ModelMetricClaimedVerifiedStatus
1EmoAffectNet LSTMUAR79—Unverified
#ModelMetricClaimedVerifiedStatus
1ResEmoteNetAccuracy75.67—Unverified
#ModelMetricClaimedVerifiedStatus
1ViT + SEAccuracy87.22—Unverified
#ModelMetricClaimedVerifiedStatus
1EmoAffectNet LSTMUAR69.7—Unverified
#ModelMetricClaimedVerifiedStatus
1EmoAffectNet LSTMUAR82.8—Unverified