A Multi-Domain Adaptive Graph Convolutional Network for EEG-based Emotion Recognition
The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Among all solutions of emotion recognition tasks, electroencephalogram (EEG) is a very effective tool and has received broad attention from researchers. In addition, information across multimedia in EEG often provides a more complete picture of emotions. However, few of the existing studies concurrently incorporate EEG information from temporal domain, frequency domain and functional brain connectivity. In this paper, we propose a Multi-Domain Adaptive Graph Convolutional Network (MD-AGCN), fusing the knowledge of both the frequency domain and the temporal domain to fully utilize the complementary information of EEG signals. MD-AGCN also considers the topology of EEG channels by combining the inter-channel correlations with the intra-channel information, from which the functional brain connectivity can be learned in an adaptive manner. Extensive experimental results demonstrate that our model exceeds state-of-the-art methods in most experimental settings. At the same time, the results show that MD-AGCN could extract complementary domain information and exploit channel relationships for EEG-based emotion recognition effectively.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“φ (1 × 1) in Figure 3 corresponds to the weight vectorW in Equation 3, and the residual branch [6] achieved by the 1 × 1 convolution operation is introduced to ensure the stability of the network.”
BackgroundHämäläinen, M., Hari, R., Ilmoniemi, R. J., Knuutila, J., & Lounasmaa, O. V. (1993) · Reviews of Modern Physics · doi:10.1103/revmodphys.65.413 · Cited by 4,684 · cited 1×
“It has been proven that EEG signals have the ability to reveal delicate changes in emotions with high time resolution [5], which is more objective and precise when analyzing emotion states [37].”
BackgroundZheng, W.-L., & Lu, B.-L. (2015) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2015.2431497 · Cited by 2,595 · cited 7×
“• DBN[36]: The deep belief network is a probabilistic generative model with a deep architecture.”
BackgroundMethodInfluentialSelf-citationMauss, I. B., & Robinson, M. D. (2009) · Cognition and Emotion · doi:10.1080/02699930802204677 · Cited by 2,078 · cited 1×
“Mauss [19] proposed that emotional procedures should be recognized as involving distributed circuits instead of specific brain regions in isolation.”
BackgroundTwo-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
Shi, L., Zhang, Y., Cheng, J., & Lu, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01230 · Cited by 2,071 · cited 2×
“[24] proposed an adaptive graph convolutional network for skeleton-based action recognition that achieves significant improvement in the field by adding adaptive graph convolutional layers and second-order information.”
BackgroundMethodEEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks
Song, T., Zheng, W., Song, P., & Cui, Z. (2020) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2018.2817622 · Cited by 1,597 · cited 7×
“For SparseDGCNN [31], they perform leave-one-clip-out validation which take only one clip as test set.”
BackgroundMethodInfluentialEmotionMeter: A Multimodal Framework for Recognizing Human Emotions
Zheng, W.-L., Liu, W., Lu, Y., Lu, B.-L., & Cichocki, A. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2797176 · Cited by 1,276 · cited 4×
“Model SEED[36] SEED-IV[35] SEED-V[12] SVM[12, 36, 38] 83.”
MethodInfluentialSelf-citationDifferential entropy feature for EEG-based emotion classification
Duan, R.-N., Zhu, J.-Y., & Lu, B.-L. (2013) · 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER) · doi:10.1109/ner.2013.6695876 · Cited by 1,100 · cited 1×
“Due to the non-stationary characteristics of EEG signals as well as the interference of noise and artifacts of raw EEG data, frequency domain features such as Power Spectral Density (PSD) [4] and Differential Entropy (DE) [3] , and time-frequency domain features such as Hilbert-Huang Spectrum (HHS) [8] have shown good…”
BackgroundSelf-citationFeature Extraction and Selection for Emotion Recognition from EEG
Jenke, R., Peer, A., & Buss, M. (2014) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2014.2339834 · Cited by 1,081 · cited 2×
“In the time domain, the most widely used EEG features are Hjorth Features, Fractal Dimension (FD) and Higher Order Crossings (HOC) [8].”
BackgroundMethodIdentifying Stable Patterns over Time for Emotion Recognition from EEG
Zheng, W.-L., Zhu, J.-Y., & Lu, B.-L. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2712143 · Cited by 990 · cited 2×
“It has been proven that EEG signals have the ability to reveal delicate changes in emotions with high time resolution [5], which is more objective and precise when analyzing emotion states [37].”
BackgroundSelf-citation
Research works printed but not linked: 5
- Yann LeCun , Yoshua Bengio , and Geoffrey Hinton . 2015 . Deep learning . Nature , Vol. 521 , 7553 (2015), 436--444. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature, Vol. 521, 7553 (2015), 436--444.
- Yang Li , Wenming Zheng , Lei Wang , Yuan Zong , and Zhen Cui . 2019 b. From regional to global brain: A novel hierarchical spatial-temporal neural network model for EEG emotion recognition . IEEE Transactions on Affective Computing ( 2019 ). Yang Li, Wenming Zheng, Lei Wang, Yuan Zong, and Zhen Cui. 2019 b. From regional to global brain: A novel hierarchical spatial-temporal neural network model for EEG emotion recognition. IEEE Transactions on Affective Computing (2019).
- Yifei Lu , Wei-Long Zheng , Binbin Li , and Bao-Liang Lu . 2015 . Combining eye movements and EEG to enhance emotion recognition . In Twenty-Fourth International Joint Conference on Artificial Intelligence. Yifei Lu, Wei-Long Zheng, Binbin Li, and Bao-Liang Lu. 2015. Combining eye movements and EEG to enhance emotion recognition. In Twenty-Fourth International Joint Conference on Artificial Intelligence.
- P MatLab . 2018. 9.7. 0.1190202 (R2019b). MathWorks Inc Natick MA USA ( 2018 ). P MatLab. 2018. 9.7. 0.1190202 (R2019b). MathWorks Inc Natick MA USA (2018).
- 10.1080/02699930126048 · doi:10.1080/02699930126048 · Paper page
Cited by
Feng, L., Cheng, C., Zhao, M., Deng, H., & Zhang, Y. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3198688 · Cited by 164
“For the hand-crafted features, they can separate into time-domain features [16], [17], frequency-domain features [18], [19] and time-frequency domain features [20], [21].”
BackgroundPGCN: Pyramidal Graph Convolutional Network for EEG Emotion Recognition
Jin, M., Du, C., He, H., Cai, T., & Li, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3385676 · Cited by 191
“In the subject-dependent experiments, following the previous experimental settings [52], [53], we performed three-fold cross-validation.”
BackgroundMethodGraph Neural Network-Based EEG Classification: A Survey
Klepl, D., Wu, M., & He, F. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3355750 · Cited by 185
Multimodal Emotion Recognition From EEG Signals and Facial Expressions
Wang, S., Qu, J., Zhang, Y., & Zhang, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3263670 · Cited by 124
“For example, Li et al. [8] used various deep learning models to extract features from EEG signals for emotion recognition.”
BackgroundMethodYe, M., Chen, C. L. P., & Zhang, T. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3225855 · Cited by 134
“Li et al. [49] developed MD-AGCN to learn the topology of EEG channels in an adaptive manner.”
Li, J., Pan, W., Huang, H., Pan, J., & Wang, F. (2023) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2023.1169949 · Cited by 93
“…(MD-AGCN), fusing the knowledge of both the frequency domain and the temporal domain to fully utilize the complementary information of EEG signals (Li R. et al., 2021) designed a model called ST-GCLSTM, which utilizes spatial attention to modify adjacency matrices to adaptively learn the…”
MethodResearch Progress of EEG-Based Emotion Recognition: A Survey
Wang, Y., Zhang, B., & Di, L. (2024) · ACM Computing Surveys · doi:10.1145/3666002 · Cited by 88
“Li et al. [ 49 ] modeled the temporal-and frequency-domain features based on the relationships between brain regions.”
Self-citationLi, R., Wang, Y., Zheng, W., & Lu, B. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548243 · Cited by 87
“Inthe case of only few labeled data for calibration, the proposed MV-SSTMA is evaluated with the self-supervised method MAE and the supervised method MD-AGCN.”
BackgroundMethodInfluentialSelf-citationCheng, C., Yu, Z., Zhang, Y., & Feng, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3319315 · Cited by 72
“This observation is consistent with previous studies [48], [51], which have found that neutral and sad emotions are generally easier to classify accurately using EEG-based emotion recognition models.”
Klepl, D., He, F., Wu, M., Blackburn, D. J., & Sarrigiannis, P. G. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3321634 · Cited by 74
“However, such an approach largely ignores brain connectivity information.”
BackgroundMethodInfluentialBi-Branch Vision Transformer Network for EEG Emotion Recognition
Lu, W., Tan, T.-P., & Ma, H. (2023) · IEEE Access · doi:10.1109/access.2023.3266117 · Cited by 59
“In general, EEG signal features can be divided into: temporal domain features of EEG signals, frequency domain features of EEG signals, and spatial domain features of EEG signals [28], [29].”
BackgroundEEG emotion recognition based on differential entropy feature matrix through 2D-CNN-LSTM network
Wang, T., Huang, X., Xiao, Z., Cai, W., & Tai, Y. (2024) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-024-01146-y · Cited by 62
“Li et al. [13] proposed an innovative approach a multi-domain adaptive graph convolutional network (MD-AGCN) that utilizes differential entropy (DE) as a feature extraction method.”
BackgroundLiu, F., Yang, P., Shu, Y., Liu, N., Sheng, J., Luo, J., Wang, X., & Liu, Y. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3336531 · Cited by 59
“Similarly, Li et al. [33] also leverages multi-domain (i.e. temporal, frequency, and topology of channels) EEG information to classify emotions.”
BackgroundSTRFLNet: Spatio-Temporal Representation Fusion Learning Network for EEG-Based Emotion Recognition
Hu, F., He, K., Wang, C., Zheng, Q., Zhou, B., Li, G., & Sun, Y. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3611173 · Cited by 65
“Furthermore, SOTA methods based on spatio-temporal fusion-based methods [48], [49], [50], [51] fail to fully leverage feature fusion strategies, resulting in ineffective utilization of deep associations and complementary information across multiple domains.”
InfluentialGong, P., Jia, Z., Wang, P., Zhou, Y., & Zhang, D. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612208 · Cited by 60
Gao, D., Liu, M., Zhang, H., Wang, M., Chang, H., Ouyang, G., Liu, S., & Li, P. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107457 · Cited by 42
Graph Neural Networks in EEG-Based Emotion Recognition: A Survey
Liu, C., Deng, Y., Wu, Y., Yang, R., Wang, Z., Zhang, L., Chen, S., Zhang, T., Liu, Y., Ding, Y., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1947-6_46 · Cited by 37
Neuro-BERT: Rethinking Masked Autoencoding for Self-Supervised Neurological Pretraining
Wu, D., Li, S., Yang, J., & Sawan, M. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3415959 · Cited by 50
“3) Encoder Architecture: Similar to the field of vision, convolution-based architectures [19], [37], [38] are dominant in the existing domain of neurological applications.”
Physiological signal analysis using explainable artificial intelligence: A systematic review
Shen, J. G., Wu, J., Liang, H., Zhao, Z., Li, K., Zhu, K., Wang, K., Ma, Y., Hu, W., Guo, C., et al. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128920 · Cited by 39
Elastic Graph Transformer Networks for EEG-Based Emotion Recognition
Jiang, W.-B., Yan, X., Zheng, W., & Lu, B. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096511 · Cited by 38
“Some variants of GCN have been applied on EEG to explore the inter-channel information, taking the regularized graph neural network proposed by Zhong et al. [11], Song et al. [12], and Li et al. [13] as examples.”
MethodSelf-citationMulti-Domain Based Dynamic Graph Representation Learning for EEG Emotion Recognition
Tang, H., Xie, S., Xie, X., Cui, Y., Li, B., Zheng, D., Hao, Y., Wang, X., Jiang, Y., & Tian, Z. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3415163 · Cited by 36
“The research results of [21] and [22] indicate that EEG features in different domains can provide multiple insights into understanding the relationship between brain regions and emotions.”
BackgroundMulti-Domain Encoding of Spatiotemporal Dynamics in EEG for Emotion Recognition
Cheng, C., Zhang, Y., Liu, L., Liu, W., & Feng, L. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3232497 · Cited by 29
“The SEED dataset provides results that agree with the findings obtained by previous works[26],whichrevealthatthemodelrecognitionperformance ofthehappyemotionoutperformsthatofthesademotion.”
BackgroundResultSpatiotemporal Gated Graph Transformer for EEG-Based Emotion Recognition
Chang, Y., Zheng, X., Chen, Y., Li, X., & Miao, Q. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3410044 · Cited by 31
LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-Based Emotion Recognition
Liu, H., Yang, S., Zhang, Y., Wang, M., Gong, F., Xie, C., Liu, G., Liu, Z., Liu, Y., Lu, B., et al. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3605833 · Cited by 38
“Others develop unique preprocessing methods, including customized filtering, artifact removal [29], [49], [50], denoising [51], [52], normalization techniques [29], [52], and extracting other types of features [33], [34], [53].”
Self-citationWang, Y., Yan, J., Yang, Z., Qi, Z., Wang, J., & Geng, Y. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3160543 · Cited by 27
Self-citationChen, J., Min, C., Wang, C., Tang, Z., Liu, Y., & Hu, X. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.878146 · Cited by 25
Graph to Grid: Learning Deep Representations for Multimodal Emotion Recognition
Jin, M., & Li, J. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612074 · Cited by 31
“SVM-based SVM [31] 69.50 ± 10.28 GCN-based MD-AGCN [15] 80.77 ± 6.61 MD-GCN [5] 81.9 ± – PGCN [10] 81.69 ± 10.57 On MPED, previous work has also achieved the best results with GCN as the main backbone.”
MethodInfluentialFunctional Emotion Transformer for EEG-Assisted Cross-Modal Emotion Recognition
Jiang, W.-B., Li, Z., Zheng, W., & Lu, B. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446937 · Cited by 28
“We adapt the Functional Emotion Transformer (FET) and a critical subnetwork selection approach for self-supervised pre-training to incorporate functional brain connectivity (FBC) into FET [11, 12].”
MethodSelf-citationCIT-EmotionNet: convolution interactive transformer network for EEG emotion recognition
Lu, W., Xia, L., Tan, T.-P., & Ma, H. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2610 · Cited by 22
Peng, D., Zheng, W., Liu, L., Jiang, W.-B., Li, Z., Lu, Y., & Lu, B. (2023) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad085a · Cited by 21
“ASGC [68, 69] takes the multiple EEG channels as graph nodes and the connections of channels as edges.”
Self-citationE2SGAN: EEG-to-SEEG translation with generative adversarial networks
Hu, M., Chen, J., Jiang, S., Ji, W., Mei, S., Chen, L., & Wang, X. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.971829 · Cited by 17
“To better characterize brain signals, we employ STFT, which transforms the original signal into the frequency domain for the generation task.”
BackgroundInfluentialA multi-task hybrid emotion recognition network based on EEG signals
Zhou, Q., Shi, C., Du, Q., & Ke, L. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105136 · Cited by 15
Emotion recognition of EEG signals based on contrastive learning graph convolutional model
Zhang, Y., Liao, Y., Chen, W., Zhang, X., & Huang, L. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad7060 · Cited by 15
“Li et al [15] combined the theory of graph convolution and brain functional connectivity, proposing a multi-domain fusion feature input deep graph CNN.”
Brain Region Knowledge-Based Dual-Stream Transformer for EEG Emotion Recognition
Lin, Y., Xu, G.-X., Liang, H., Wang, Y., Wan, F., & Li, Y. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3552801 · Cited by 19
“We selected four GNN-based methods (RGNN [26], MD-AGCN [47], GMSS [24], BGAGCN-MT [48]), two CNN-based methods (sst-emotionnet [29], 4D-aNN [39]), and two transformer-based methods (Conformer [33], AMDET [18]).”
Self-citationMTRT: Motion Trajectory Reconstruction Transformer for EEG-Based BCI Decoding
Wang, P., Li, Z., Gong, P., Zhou, Y., Chen, F., & Zhang, D. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3275172 · Cited by 17
“Compared with general deep learning [36], [37], the advantages of the Transformer model lie in the feature learning representation and attention mechanism [38].”
MethodA Knowledge-Enhanced and Topic-Guided Domain Adaptation Model for Aspect-Based Sentiment Analysis
Zeng, Y., Wang, G., Ren, H., Cai, Y., Leung, H.-F., Li, Q., & Huang, Q. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3292213 · Cited by 13
“To solve this problem, domain adaptation methods on sentiment or emotion analysis are proposed in both the computer vision field [28], [29], [30], [31] and the natural language field [9], [32].”
MethodWu, F., Liu, J., Yang, J., Zhang, L., He, Y., & Lin, Z. (2024) · IEEE Access · doi:10.1109/access.2024.3460393 · Cited by 15
“Li et al. [27], Song et al. [28], and Zhong et al. [29] proposed using each channel as a node to construct the graph structure, and then use variants of GCN to learn the relationship between each channel.”
MethodYu, M., He, Q., Wang, Y., & Du, N. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106986 · Cited by 13
Self-citationWang, P., Zheng, H., Dai, S., Wang, Y., Gu, X., Wu, Y., & Wang, X. (2024) · Chinese journal of information fusion. · doi:10.62762/cjif.2024.876830 · Cited by 13
“MD-AGCN[88] constructs temporal domain functional brain connectivity and frequency domain functional brain connectivity, respectively.”
Self-citationMoGE: Mixture of Graph Experts for Cross-subject Emotion Recognition via Decomposing EEG
Liu, X.-H., Jiang, W.-B., Zheng, W., & Lu, B. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822354 · Cited by 24
“092 MoGE ( Ours ) 0.880 ± 0.045 0.743 ± 0.061 0.818 ± 0.100 GNN-based models [29] already have decent generalization ability, and better results are acquired by combining GNN and Transformer [14].”
InfluentialSelf-citationZheng, F., Hu, B., Zheng, X., & Zhang, Y. (2023) · Physiological Measurement · doi:10.1088/1361-6579/acd675 · Cited by 16
Ma, W., Li, Y., Li, T., Yang, H., Li, Z., Wang, L., & Xuan, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130309 · Cited by 17
TAHAG: Two-Stage Domain Adaptation With Hybrid Adaptive Graph Learning for EEG Emotion Recognition
Gong, P., Zhou, Y., Huang, S., Wang, P., & Zhang, D. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3580787 · Cited by 13
“The visualization reveals that our model learns distinct connectivity patterns across layers, aligning with findings from existing studies [21], [28].”
Cross-Modality Domain Adaptation for Freespace Detection: A Simple yet Effective Baseline
Wang, Y., Zhu, L., Huang, S., Hui, T., Li, X., Wang, F., & Liu, S. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547752 · Cited by 13
“Domain adaptation is widely used in classification [14, 17, 21, 64], object detection [8, 33, 52, 65, 66], semantic segmentation [20, 27, 57, 71, 78] and many other fields [39, 72, 74, 75].”
BackgroundSelf-citationEmotion Recognition in EEG Based on Multilevel Multidomain Feature Fusion
Li, Z. L., Cao, H., & Zhang, J. S. (2024) · IEEE Access · doi:10.1109/access.2024.3417525 · Cited by 10
“Li et al. proposed a Multi-Domain Adaptive Graph Convolutional Network (MD-AGCN) [14], illustrating that combining frequency and time-domain knowledge can enhance feature learning.”
BackgroundJoint Contrastive Learning with Feature Alignment for Cross-Corpus EEG-based Emotion Recognition
Liu, Q., Zhou, Z., Wang, J., & Liang, Z. (2024) · doi:10.1145/3688862.3689112 · Cited by 17
“Therefore, researchers from diverse fields have increasingly focused on EEG-based emotion recognition in recent years [12, 18, 19, 23, 37].”
Chen, K., Yang, Z., Cai, M., Liu, Q., Ai, Q., & Ma, L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128183 · Cited by 12
Self-Supervised EEG Representation Learning for Robust Emotion Recognition
Liu, H., Zhang, Y., Chen, X., Zhang, D., Li, R., & Qin, T. (2024) · ACM Transactions on Sensor Networks · doi:10.1145/3674975 · Cited by 11
“Li et al. [22] proposed a Multi-Domain Adaptive Graph Convolutional Network ( MD-AGCN ), which combined frequency and temporal data from EEG signals with channel connectivity for adaptive learning of brain functions.”
Self-citationWang, B., Miao, M., Zhang, K., Liu, W., Sheng, Z., Xu, B., & Hu, W. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad9135 · Cited by 8
“This phenomenon is consistent with the findings in existing research [60].”
Li, Z., Tao, L.-Y., Ma, R.-X., Zheng, W., & Lu, B. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3572504 · Cited by 12
“The tuned hyper-parameters, including the hidden dimensions, learning rate, weight decay, and others, were selected based on [52], [53].”
Self-citationMVGT: A Multi-view Graph Transformer Based on Spatial Relations for EEG Emotion Recognition
Cui, Y., Liu, X., Liang, J., & Fu, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4378-6_1 · Cited by 8
“Li et al. [14] also utilized adaptive GCNs that integrate multi-domain information to learn relationships between channels.”
BackgroundMethodInfluentialBrain Topography Adaptive Network for Satisfaction Modeling in Interactive Information Access System
Ye, Z., Xie, X., Liu, Y., Wang, Z., Chen, X., Zhang, M., & Ma, S. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548258 · Cited by 11
“It is widely used in researches involving motion imaginary [25, 28], emotion recognition [20, 29, 61], and sleep stage scoring [21, 48].”
BackgroundMethodInfluentialTowards Adaptable Graph Representation Learning: An Adaptive Multi-Graph Contrastive Transformer
Li, Y., Zhang, L., Lan, X., & Jiang, D. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612358 · Cited by 11
“…models (SVM [34] and DBN [43]), graph representation learning without temporal information (DGCNN [33], RGNN [44], BiHDM [21]), graph representation learning with decoupled spatial-temporal modeling (BiDANN [23],R2G-STNN[24],MD-AGCN[19]),theself-supervised contrastive learning (MV-SSTMA [20]).”
BackgroundGu, J., Xiong, F., & Gong, X. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822614 · Cited by 6
FourierMask: Explain EEG-Based End-to-End Deep Learning Models in the Frequency Domain
Wang, H., Zhang, J., Yang, K., Xiong, J., Liu, X., Chen, T., & Song, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3610742 · Cited by 8
“First, extensive research has established that certain frequency components within EEG signals are associated with specific cognitive states [13], [14], [15], [16].”
Global Context MambaVision for EEG-based Emotion Recognition
Wang, H., Li, X., Yu, Y., Ding, W., & Xu, Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890602 · Cited by 4
“In the current era of deep learning, convolutional neural networks (CNNs) and transformers are widely used to handle emotion recognition tasks [1]–[10].”
Zhou, Z., Zhang, L., Liu, Q., Huang, G., Yu, Z., & Liang, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130951 · Cited by 6
Tagging Continuous Labels for EEG-based Emotion Classification
Gu, R.-F., Zhao, L.-M., Zheng, W., & Lu, B. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10341022 · Cited by 5
“We also employ specific models that apply to EEG-based tasks including EEGNet [14] and GCN [15].”
MethodSelf-citationCheng, C., Liu, W., Jia, Z., & He, W. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129222 · Cited by 6
Real-time EEG-based emotion recognition using Riemannian quantification learning
Lv, B., Yu, Y., Zhuo, F., & Tang, F. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109223 · Cited by 3
A dual-branch multiscale model based on Bi-Mamba for EEG emotion recognition
Feng, L., Huo, Y., Kong, Y., & Cheng, C. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109623 · Cited by 3
Xu, X., Li, Z., Lu, J., & Wu, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681570 · Cited by 6
Li, C., Wang, F., & Bian, N. (2024) · International Conference on Cryptography, Network Security and Communication Technology (CNSCT) · doi:10.1145/3673277.3673384 · Cited by 2
“Innovations, including dynamic graph convolutional neural networks and hierarchical dynamic GCNs, have yielded new insights into the emotion feature extraction and the integration of spatial and temporal domains of EEG signals [6], [7], [8].”
Zhang, Y., Xie, C., Liu, H., Shi, Y., Liu, G., & Zhang, D. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3608571 · Cited by 6
“…our method with a variety of graph-based deep learning models, including traditional classic models: DGCNN [12], RGNN [7], IAG [27], MD-AGCN [38], and V-IAG [13], and the latest SOTA approaches: Siam-GCAN [39], PR-PL [40], GMSS [41], MSFR-GCN [42], PGCN [33], DS-AGC [43], BGAGCN-MT [44],…”
InfluentialReal-Time EEG Emotion Recognition from Dynamic Mixed Spatiotemporal Graph Learning
Pan, Y., Li, C., Li, P., Li, F., Wan, F., Yao, D., Cao, Z., & Xu, P. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755389 · Cited by 2
“For example, MD-AGCN [27] uses the Pearson correlation coefficient as a prior graph for GNNs, while BF-GCN [23] employs phase-locking values as cognitive prior graphs to learn EEG topological patterns.”
A simple algorithm for primary emotion recognition from dual channel EEG signals
Paul, A., Pal, S., & Mitra, M. (2025) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2025.104316 · Cited by 3
Echo-GRU: Emotion Recognition Using Wearable EEG Supporting Early Alzheimer’s Disease Detection
Nguyen, Q.-T. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-87657-8_1 · Cited by 1
Anusha, J. A., & Reddy, S. C. (2026) · Smart Health · doi:10.1016/j.smhl.2026.100650 · Cited by 1
Multi-source-Domain Adaptation for TMS-EEG Based Depression Detection
Zhou, J., Li, N., Lian, C., Yang, Y., Wang, L., Guo, Y. M., Yan, N., & Su, R. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1151-5_26
A Multi-task Emotion Recognition Model Based on Continuously Labeled EEG Signals
Gu, R.-F., Zhao, Y.-D., Zhao, L.-M., Zheng, W., & Lu, B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6588-4_26 · Cited by 2
Self-citationDAVG-ViT: a domain-adaptive Vision Transformer with GA-BiLSTM for EEG emotion recognition
Gu, W., Li, J., Peng, J., Xiao, X., & Yin, Y. (2025) · Computer Methods in Biomechanics & Biomedical Engineering · doi:10.1080/10255842.2025.2605574
Liu, Y.-K., Liu, X., Zhao, Y.-D., Lu, B., & Zheng, W. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356923
“Many deep learning models, such as LSTM [8], RNN [9], RGNN [10], and MD-AGCN [11], have achieved good performance in this field.”
Self-citationA Study of EEG Emotion Classification Based on a Channel-Temporal Fusion Attention CNN
Xia, C., Yang, B., Liu, S., Li, Y., & Sun, J. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-6841-3_24
Melinda, M., Away, Y., Gazali, S., Wong, W. K., Marisa, K., & Rahmat, M. M. (2025) · International Conference on Applied Artificial Intelligence, Data Engineering and Sciences (ICAIDES) · doi:10.1109/icaides67265.2025.11404044
“For example, ATGAN [24] reported a 7.78% improvement, while MD-AGCN [25] achieved up to 94.81% accuracy in emotion recognition.”
InfluentialAngkan, P., Jalali, A., Hungler, P. C., & Etemad, A. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462985
Pan, W., Yang, H., Liu, J., Hu, X., & Zhu, Q. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6833132
Shishupal, R. (2026) · Journal of Intelligent Decision Making and Information Science · doi:10.59543/jidmis.v3.1418
“As a result, models trained on specific subjects often fail to generalize effectively, making cross-subject emotion recognition a critical and unresolved challenge [8],[9],[10],[11].”
Zilong, L., & song, Z. (2026) · Research Square · doi:10.21203/rs.3.rs-11043508/v1
Metadata
- Authors
- Li, R., Wang, Y., & Lu, B.-L.
- Affiliations
- Shanghai Jiao Tong University (CN)
- Venue
- Proceedings of the 29th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2021-10-17
- Pages
- 5565-5573
- OpenAlex
- W3205895886
- Cited by
- 73
- References
- 32
- Citations by year
- 2026: 5 · 2025: 22 · 2024: 21 · 2023: 16 · 2022: 9
- FWCI
- 12.79
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Multimedia (ACM MM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
- Keywords
- EEG-based emotion recognition, graph convolutional networks, frequency domain, time domain, brain functional connectivity, adaptive graph learning, inter-channel correlation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.