# TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition

arXiv: https://arxiv.org/abs/2104.02935 · HTML: https://mlsanity.com/paper/2104.02935/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 63 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Identifying Stable Patterns over Time for Emotion Recognition from EEG](https://mlsanity.com/paper/1601.02197/) (2016)
- [Spatial-Temporal Recurrent Neural Network for Emotion Recognition](https://mlsanity.com/paper/1705.04515/) (2017)
- [TSception: A Deep Learning Framework for Emotion Detection Using EEG](https://mlsanity.com/paper/2004.02965/) (2020)

## Built on by (most cited first, 30 of 52)

- [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024)
- [Transformer-based Spatial-Temporal Feature Learning for EEG Decoding](https://mlsanity.com/paper/2106.11170/) (2021)
- [EEG-Deformer: A Dense Convolutional Transformer for Brain-computer Interfaces](https://mlsanity.com/paper/2405.00719/) (2024)
- [EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion Recognition](https://mlsanity.com/paper/2406.18345/) (2024)
- [Interpretable and Robust AI in EEG Systems: A Survey](https://mlsanity.com/paper/2304.10755/) (2023)
- [MASA-TCN: Multi-anchor Space-aware Temporal Convolutional Neural Networks for Continuous and Discrete EEG Emotion Recognition](https://mlsanity.com/paper/2308.16207/) (2023)
- [DeeperBrain: A Neuro-Grounded EEG Foundation Model Towards Universal BCI](https://mlsanity.com/paper/2601.06134/) (2026)
- [LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-based Emotion Recognition](https://mlsanity.com/paper/2410.09767/) (2024)
- [Temporal Aware Mixed Attention-based Convolution and Transformer Network (MACTN) for EEG Emotion Recognition](https://mlsanity.com/paper/2305.18234/) (2023)
- [BrainGPT: Unleashing the Potential of EEG Generalist Foundation Model by Autoregressive Pre-training](https://mlsanity.com/paper/2410.19779/) (2024)
- [MSGM: A Multi-Scale Spatiotemporal Graph Mamba for EEG Emotion Recognition](https://mlsanity.com/paper/2507.15914/) (2025)
- [ConTraNet: A single end-to-end hybrid network for EEG-based and EMG-based human machine interfaces](https://mlsanity.com/paper/2206.10677/) (2022)
- [PhysioSync: Temporal and Cross-Modal Contrastive Learning Inspired by Physiological Synchronization for EEG-Based Emotion Recognition](https://mlsanity.com/paper/2504.17163/) (2025)
- [LMDA-Net:A lightweight multi-dimensional attention network for general EEG-based brain-computer interface paradigms and interpretability](https://mlsanity.com/paper/2303.16407/) (2023)
- [Interpretable Dual-Filter Fuzzy Neural Networks for Affective Brain-Computer Interfaces](https://mlsanity.com/paper/2502.17445/) (2025)
- [Decoding Covert Speech from EEG Using a Functional Areas Spatio-Temporal Transformer](https://mlsanity.com/paper/2504.03762/) (2025)
- [Evaluation in EEG Emotion Recognition: State-of-the-Art Review and Unified Framework](https://mlsanity.com/paper/2505.18175/) (2025)
- [BrainPro: Towards Large-scale Brain State-aware EEG Representation Learning](https://mlsanity.com/paper/2509.22050/) (2025)
- [LEAF: Language-EEG Aligned Foundation Model for Brain-Computer Interfaces](https://mlsanity.com/paper/2509.24302/) (2025)
- [HEEGNet: Hyperbolic Embeddings for EEG](https://mlsanity.com/paper/2601.03322/) (2026)
- [Emotion recognition based on multi-modal electrophysiology multi-head attention Contrastive Learning](https://mlsanity.com/paper/2308.01919/) (2023)
- [Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer based Dim Object Detection](https://mlsanity.com/paper/2407.01894/) (2024)
- [Protecting Intellectual Property of EEG-based Neural Networks with Watermarking](https://mlsanity.com/paper/2502.05931/) (2025)
- [Spatial-Temporal Transformer with Curriculum Learning for EEG-Based Emotion Recognition](https://mlsanity.com/paper/2507.14698/) (2025)
- [Modified TSception for Analyzing Driver Drowsiness and Mental Workload from EEG](https://mlsanity.com/paper/2512.21747/) (2025)
- [NAKUL-Med: Spectral-Graph State Space Models with Dynamics Kernels for Medical Signals](https://mlsanity.com/paper/2605.00871/) (2026)
- [Rethinking Saliency Map: An Context-aware Perturbation Method to Explain EEG-based Deep Learning Model](https://mlsanity.com/paper/2205.14976/) (2022)
- [A Lightweight Domain Adversarial Neural Network Based on Knowledge Distillation for EEG-based Cross-subject Emotion Recognition](https://mlsanity.com/paper/2305.07446/) (2023)
- [Wearable Device-Based Real-Time Monitoring of Physiological Signals: Evaluating Cognitive Load Across Different Tasks](https://mlsanity.com/paper/2406.07147/) (2024)
- [LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring](https://mlsanity.com/paper/2407.05749/) (2024)

## Abstract (arXiv)

The high temporal resolution and the asymmetric spatial activations are essential attributes of electroencephalogram (EEG) underlying emotional processes in the brain. To learn the temporal dynamics and spatial asymmetry of EEG towards accurate and generalized emotion recognition, we propose TSception, a multi-scale convolutional neural network that can classify emotions from EEG. TSception consists of dynamic temporal, asymmetric spatial, and high-level fusion layers, which learn discriminative representations in the time and channel dimensions simultaneously. The dynamic temporal layer consists of multi-scale 1D convolutional kernels whose lengths are related to the sampling rate of EEG, which learns the dynamic temporal and frequency representations of EEG. The asymmetric spatial layer takes advantage of the asymmetric EEG patterns for emotion, learning the discriminative global and hemisphere representations. The learned spatial representations will be fused by a high-level fusion layer. Using more generalized cross-validation settings, the proposed method is evaluated on two publicly available datasets DEAP and MAHNOB-HCI. The performance of the proposed network is compared with prior reported methods such as SVM, KNN, FBFgMDM, FBTSC, Unsupervised learning, DeepConvNet, ShallowConvNet, and EEGNet. TSception achieves higher classification accuracies and F1 scores than other methods in most of the experiments. The codes are available at https://github.com/yi-ding-cs/TSception