mlsanityData to 14 Oct 2026

EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition

arXiv 2102.03777 ↗First posted 7 Feb 2021cs.HC cs.LG eess.SPcited by 15

Not on the map. Why?

Abstract (arXiv)

How to effectively and efficiently extract valid and reliable features from high-dimensional electroencephalography (EEG), particularly how to fuse the spatial and temporal dynamic brain information into a better feature representation, is a critical issue in brain data analysis. Most current EEG studies work in a task driven manner and explore the valid EEG features with a supervised model, which would be limited by the given labels to a great extent. In this paper, we propose a practical hybrid unsupervised deep convolutional recurrent generative adversarial network based EEG feature characterization and fusion model, which is termed as EEGFuseNet. EEGFuseNet is trained in an unsupervised manner, and deep EEG features covering both spatial and temporal dynamics are automatically characterized. Comparing to the existing features, the characterized deep EEG features could be considered to be more generic and independent of any specific EEG task. The performance of the extracted deep and low-dimensional features by EEGFuseNet is carefully evaluated in an unsupervised emotion recognition application based on three public emotion databases. The results demonstrate the proposed EEGFuseNet is a robust and reliable model, which is easy to train and performs efficiently in the representation and fusion of dynamic EEG features. In particular, EEGFuseNet is established as an optimal unsupervised fusion model with promising cross-subject emotion recognition performance. It proves EEGFuseNet is capable of characterizing and fusing deep features that imply comparative cortical dynamic significance corresponding to the changing of different emotion states, and also demonstrates the possibility of realizing EEG based cross-subject emotion recognition in a pure unsupervised manner.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 19 of its 125 references that are in the map. First posted on arXiv 7 Feb 2021.

Builds on

19 of 125 references.

References · 19

  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  2. 2014Going Deeper with Convolutionscited by 4,241
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  6. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
  7. 2018Object Detection with Deep Learning: A Reviewcited by 528
  8. 2015Adversarial Autoencoderscited by 364
  9. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  10. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  11. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  12. 2018Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approachcited by 58
7 more
  1. 2018An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videoscited by 45
  2. 2017Unsupervised Learning of Long-Term Motion Dynamics for Videoscited by 37
  3. 2017Deep Recurrent Generative Decoder for Abstractive Text Summarizationcited by 19
  4. 2019Understanding Geometry of Encoder-Decoder CNNscited by 13
  5. 2016Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decodercited by 8
  6. 2018Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generationcited by 5
  7. 2018Adversarial Auto-encoders for Speech Based Emotion Recognitioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 4; 2025: 3; 2026: 2.

15 papers.

Sort:

  1. 2023EEGMatch: Learning with Incomplete Labels for Semi-Supervised EEG-based Cross-Subject Emotion Recognitioncited by 10
  2. 2023Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognitioncited by 10
  3. 2026Let EEG Models Learn EEGcited by 7
  4. 2023Temporal Aware Mixed Attention-based Convolution and Transformer Network (MACTN) for EEG Emotion Recognitioncited by 4
  5. 2024M3D: Manifold-based Domain Adaptation with Dynamic Distribution for Non-Deep Transfer Learning in Cross-subject and Cross-session EEG-based Emotion Recognitioncited by 3
  6. 2025Geometric Machine Learning on EEG Signalscited by 3
  7. 2023Semi-Supervised End-To-End Contrastive Learning For Time Series Classificationcited by 2
  8. 2024DuA: Dual Attentive Transformer in Long-Term Continuous EEG Emotion Analysiscited by 2
  9. 2024NSSI-Net: A Multi-Concept GAN for Non-Suicidal Self-Injury Detection Using High-Dimensional EEG in a Semi-Supervised Frameworkcited by 2
  10. 2022Locally temporal-spatial pattern learning with graph attention mechanism for EEG-based emotion recognitioncited by 1
  11. 2025Removing Neural Signal Artifacts with Autoencoder-Targeted Adversarial Transformers (AT-AT)cited by 1
  12. 2022Rethinking Saliency Map: An Context-aware Perturbation Method to Explain EEG-based Deep Learning Modelcited by 0
3 more
  1. 2024Emotion-Agent: Unsupervised Deep Reinforcement Learning with Distribution-Prototype Reward for Continuous Emotional EEG Analysiscited by 0
  2. 2025Learning Domain- and Class-Disentangled Prototypes for Domain-Generalized EEG Emotion Recognitioncited by 0
  3. 2026Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognitioncited by 0