SOTAVerified

Emotion Classification

Emotion classification, or emotion categorization, is the task of recognising emotions to classify them into the corresponding category. Given an input, classify it as 'neutral or no emotion' or as one, or more, of several given emotions that best represent the mental state of the subject's facial expression, words, and so on. Some example benchmarks include ROCStories, Many Faces of Anger (MFA), and GoEmotions. Models can be evaluated using metrics such as the Concordance Correlation Coefficient (CCC) and the Mean Squared Error (MSE).

Papers

Showing 125 of 458 papers

TitleStatusHype
EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion RecognitionCode2
MARLIN: Masked Autoencoder for facial video Representation LearnINgCode2
MELLM: Exploring LLM-Powered Micro-Expression Understanding Enhanced by Subtle Motion PerceptionCode1
A novel Fourier Adjacency Transformer for advanced EEG emotion recognitionCode1
VANPY: Voice Analysis FrameworkCode1
EmoNeXt: an Adapted ConvNeXt for Facial Emotion RecognitionCode1
EmoVIT: Revolutionizing Emotion Insights with Visual Instruction TuningCode1
Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression RecognitionCode1
VLLMs Provide Better Context for Emotion Understanding Through Common Sense ReasoningCode1
GiMeFive: Towards Interpretable Facial Emotion ClassificationCode1
Learning Arousal-Valence Representation from Categorical Emotion Labels of SpeechCode1
EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature TemplateCode1
Label-Aware Hyperbolic Embeddings for Fine-grained Emotion ClassificationCode1
Evaluating Emotion Arcs Across Languages: Bridging the Global Divide in Sentiment AnalysisCode1
StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time SeriesCode1
Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across CorporaCode1
GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion RecognitionCode1
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep LearningCode1
Nkululeko: A Tool For Rapid Speaker Characteristics DetectionCode1
None Class Ranking Loss for Document-Level Relation ExtractionCode1
Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?Code1
PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion RecognitionCode1
Domain-Invariant Representation Learning from EEG with Private EncodersCode1
Few-Shot Emotion Recognition in Conversation with Sequential Prototypical NetworksCode1
Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text ClassificationCode1
Show:102550
← PrevPage 1 of 19Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MARLIN (ViT-L)Accuracy80.63Unverified
2MARLIN (ViT-B)Accuracy80.6Unverified
3MARLIN (ViT-S)Accuracy80.38Unverified
4ConCluGenAccuracy66.48Unverified
#ModelMetricClaimedVerifiedStatus
1SpanEmoAccuracy0.6Unverified
2BERT+DKAccuracy0.59Unverified
3BERT-GCNAccuracy0.59Unverified
4Transformer (finetune)Macro-F10.56Unverified
#ModelMetricClaimedVerifiedStatus
1ProxEmo (ours)Accuracy82.4Unverified
2STEP [bhattacharya2019step]Accuracy78.24Unverified
3Baseline (Vanilla LSTM) [Ewalk]Accuracy55.47Unverified
#ModelMetricClaimedVerifiedStatus
1MLKNNF-F1 score (Comb.)0.34Unverified
2CC - XGBF-F1 score (Comb.)0.33Unverified
#ModelMetricClaimedVerifiedStatus
1Semi-supervisionF165.88Unverified
2NPN + Explanation TrainingF130.29Unverified
#ModelMetricClaimedVerifiedStatus
1Deep ParsBERTMacro F10.65Unverified
#ModelMetricClaimedVerifiedStatus
1CAERNetAccuracy77.04Unverified
#ModelMetricClaimedVerifiedStatus
1ERANN-0-4Top-1 Accuracy74.8Unverified
#ModelMetricClaimedVerifiedStatus
1Deep ParsBERTMacro F10.71Unverified