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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 458 papers

TitleStatusHype
MARLIN: Masked Autoencoder for facial video Representation LearnINgCode2
EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion RecognitionCode2
Modeling Label Semantics for Predicting Emotional ReactionsCode1
Perception for Autonomous Systems (PAZ)Code1
VLLMs Provide Better Context for Emotion Understanding Through Common Sense ReasoningCode1
Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression RecognitionCode1
GoEmotions: A Dataset of Fine-Grained EmotionsCode1
Efficient Speech Emotion Recognition Using Multi-Scale CNN and AttentionCode1
BERT-like Pre-training for Symbolic Piano Music Classification TasksCode1
PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion RecognitionCode1
StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time SeriesCode1
VANPY: Voice Analysis FrameworkCode1
Real-Time Emotion Classification Using EEG Data Stream in E-Learning ContextsCode1
Nkululeko: A Tool For Rapid Speaker Characteristics DetectionCode1
CTAL: Pre-training Cross-modal Transformer for Audio-and-Language RepresentationsCode1
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep LearningCode1
Emotion Classification in a Resource Constrained Language Using Transformer-based ApproachCode1
GiMeFive: Towards Interpretable Facial Emotion ClassificationCode1
Label-Aware Hyperbolic Embeddings for Fine-grained Emotion ClassificationCode1
MELLM: Exploring LLM-Powered Micro-Expression Understanding Enhanced by Subtle Motion PerceptionCode1
Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across CorporaCode1
Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text ClassificationCode1
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment SemanticsCode1
Speech Emotion Recognition with Multi-Task LearningCode1
Twitter Sentiment AnalysisCode1
Understanding the Role of Affect Dimensions in Detecting Emotions from Tweets: A Multi-task ApproachCode1
EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature TemplateCode1
SpanEmo: Casting Multi-label Emotion Classification as Span-predictionCode1
ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot NavigationCode1
None Class Ranking Loss for Document-Level Relation ExtractionCode1
DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in ConversationCode1
EmoNeXt: an Adapted ConvNeXt for Facial Emotion RecognitionCode1
DialogueRNN: An Attentive RNN for Emotion Detection in ConversationsCode1
Domain-Invariant Representation Learning from EEG with Private EncodersCode1
GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion RecognitionCode1
EmoVIT: Revolutionizing Emotion Insights with Visual Instruction TuningCode1
Few-Shot Emotion Recognition in Conversation with Sequential Prototypical NetworksCode1
Evaluating Emotion Arcs Across Languages: Bridging the Global Divide in Sentiment AnalysisCode1
A novel Fourier Adjacency Transformer for advanced EEG emotion recognitionCode1
Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?Code1
Learning Arousal-Valence Representation from Categorical Emotion Labels of SpeechCode1
PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English PoetryCode1
An Empirical Analysis of the Role of Amplifiers, Downtoners, and Negations in Emotion Classification in Microblogs—0
An Emotional Comfort Framework for Improving User Satisfaction in E-Commerce Customer Service Chatbots—0
AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text—0
An Analysis of Annotated Corpora for Emotion Classification in Text—0
Analysing the Greek Parliament Records with Emotion Classification—0
AffecThor at SemEval-2018 Task 1: A cross-linguistic approach to sentiment intensity quantification in tweets—0
A Comprehensive Analysis of Preprocessing for Word Representation Learning in Affective Tasks—0
An adversarial learning framework for preserving users' anonymity in face-based emotion recognition—0
Show:102550
← PrevPage 1 of 10Next →
All datasetsCMU-MOSEISemEval 2018 Task 1E-cEWALKMFAROCStoriesArmanEmoCAER-DynamicRAVDESSShortPersianEmo

Benchmark Results

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