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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 391–400 of 458 papers

Title	Date	Tasks	Status
Automatically augmenting an emotion dataset improves classification using audio	Mar 30, 2018	ClassificationEmotion Classification	—Unverified
EEG emotion recognition using dynamical graph convolutional neural networks	Mar 21, 2018	EEGEEG Emotion Recognition	—Unverified
Pop Music Highlighter: Marking the Emotion Keypoints	Feb 28, 2018	Emotion Classification	CodeCode Available
Joint Binary Neural Network for Multi-label Learning with Applications to Emotion Classification	Feb 3, 2018	ClassificationComputational Efficiency	—Unverified
Transfer Learning for Improving Speech Emotion Classification Accuracy	Jan 19, 2018	ClassificationCross-corpus	CodeCode Available
Variational Autoencoders for Learning Latent Representations of Speech Emotion: A Preliminary Study	Dec 23, 2017	Emotion ClassificationEmotion Recognition	—Unverified
A Novel Approach for Effective Learning in Low Resourced Scenarios	Dec 15, 2017	BIG-bench Machine LearningClassification	—Unverified
IITP at IJCNLP-2017 Task 4: Auto Analysis of Customer Feedback using CNN and GRU Network	Dec 1, 2017	Document ClassificationEmotion Classification	—Unverified
Convolutional neural networks pretrained on large face recognition datasets for emotion classification from video	Nov 13, 2017	Emotion ClassificationEmotion Recognition	—Unverified
Data Augmentation in Emotion Classification Using Generative Adversarial Networks	Nov 2, 2017	ClassificationData Augmentation	—Unverified

Show:10 25 50

← PrevPage 40 of 46Next →

All datasets CMU-MOSEI SemEval 2018 Task 1E-c EWALK MFA ROCStories ArmanEmo CAER-Dynamic RAVDESS ShortPersianEmo

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MARLIN (ViT-L)	Accuracy	80.63	—	Unverified
2	MARLIN (ViT-B)	Accuracy	80.6	—	Unverified
3	MARLIN (ViT-S)	Accuracy	80.38	—	Unverified
4	ConCluGen	Accuracy	66.48	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SpanEmo	Accuracy	0.6	—	Unverified
2	BERT+DK	Accuracy	0.59	—	Unverified
3	BERT-GCN	Accuracy	0.59	—	Unverified
4	Transformer (finetune)	Macro-F1	0.56	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ProxEmo (ours)	Accuracy	82.4	—	Unverified
2	STEP [bhattacharya2019step]	Accuracy	78.24	—	Unverified
3	Baseline (Vanilla LSTM) [Ewalk]	Accuracy	55.47	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MLKNN	F-F1 score (Comb.)	0.34	—	Unverified
2	CC - XGB	F-F1 score (Comb.)	0.33	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Semi-supervision	F1	65.88	—	Unverified
2	NPN + Explanation Training	F1	30.29	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Deep ParsBERT	Macro F1	0.65	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CAERNet	Accuracy	77.04	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ERANN-0-4	Top-1 Accuracy	74.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Deep ParsBERT	Macro F1	0.71	—	Unverified