In spite of Convolutional Neural Network (CNN) has dominated in the area of Person Re-Identification, Transformer-based methods have emerged with their advantages in computer vision for processing long sequences in recent two years. In this work, for the purpose of reinforcing complementary advantages of Transformer and CNN in computer vision, a concise method combining Convolution and Transformer is proposed to boost the performance. Firstly, a convolutional network with attention mechanism is employed to generate features with channel and inter-channel relationship information. Moreover, a f...
