An emotion state recognition method based on Squeeze-and-Excitation Networks is proposed. Firstly, time-domain features are extracted from EEG signals of different channels, and a three-dimensional feature matrix is constructed according to the relative position of electrode channels. Then, the Squeeze-and-Excitation Networks is constructed by combining the Squeeze-and-Excitation block with 3D convolutional neural network for high-level abstract feature extraction. Finally, fully connected layers is used for emotional state classification. The experiment is carried out on DEAP data set. The experimental results show that Squeeze-and-Excitation Networks can adaptively correct the attention of features and optimize the weight of each feature based on the time-domain saliency information and electrode spatial position information in EEG signal. Meanwhile, the Squeeze-and-Excitation Networks can also strengthen important features and improve the recognition accuracy by using the complementary information of different features. In addition, the squeeze operation of Squeeze-and-Excitation Networks can obtain the global information of the input data and have a faster convergence speed.