Electroencephalography (EEG) signal decoding is a key technology that translates brain activity into executable commands, laying the foundation for direct brain-machine interfacing and intelligent interaction. To address the inherent spatiotemporal heterogeneity of EEG signals, this paper proposes a multi-branch parallel architecture, where each temporal scale is equipped with an independent spatial feature extraction module. To further enhance multi-branch feature fusion, we propose a Fusion of Multiscale Features via Centralized Sparse-attention Network (EEG-CSANet), a centralized sparse-attention network. It employs a main-auxiliary branch architecture, where the main branch models core spatiotemporal patterns via multiscale self-attention, and the auxiliary branch facilitates efficient local interactions through sparse cross-attention. Experimental results show that EEG-CSANet achieves state-of-the-art (SOTA) performance across five public datasets (BCIC-IV-2A, BCIC-IV-2B, HGD, SEED, and SEED-VIG), with accuracies of 88.54%, 91.09%, 97.15%, 96.03%, and 90.56%, respectively. Such performance demonstrates its strong adaptability and robustness across various EEG decoding tasks. Moreover, extensive ablation studies are conducted to enhance the interpretability of EEG-CSANet. In the future, we hope that EEG-CSANet could serve as a promising baseline model in the field of EEG signal decoding. The source code is publicly available at: https://github.com/Xiangrui-Cai/EEG-CSANet

翻译：脑电图信号解码是将大脑活动转化为可执行指令的关键技术，为直接脑机接口与智能交互奠定基础。针对脑电信号固有的时空异质性，本文提出一种多分支并行架构，其中每个时间尺度均配备独立的空间特征提取模块。为进一步增强多分支特征融合，我们提出基于集中式稀疏注意力网络的多尺度特征融合方法，即EEG-CSANet。该网络采用主-辅分支架构：主分支通过多尺度自注意力建模核心时空模式，辅分支则通过稀疏交叉注意力实现高效的局部交互。实验结果表明，EEG-CSANet在五个公开数据集上均取得最先进性能，在BCIC-IV-2A、BCIC-IV-2B、HGD、SEED和SEED-VIG数据集上的准确率分别达到88.54%、91.09%、97.15%、96.03%和90.56%。这一性能证明了其在各类脑电解码任务中具有强大的适应性与鲁棒性。此外，通过系统的消融实验增强了EEG-CSANet的可解释性。未来，我们希望EEG-CSANet能成为脑电信号解码领域具有潜力的基线模型。源代码已公开于：https://github.com/Xiangrui-Cai/EEG-CSANet