TY - GEN AU - Meng-Hao Guo AU - Tian-Xing Xu AU - Jiang-Jiang Liu AU - Zheng-Ning Liu AU - Peng-Tao Jiang AU - Tai-Jiang Mu AU - Song-Hai Zhang AU - Ralph R. Martin AU - Ming-Ming Cheng AU - Shi-Min Hu TI - Attention mechanisms in computer vision: A survey PY - 2022/// CY - [Place of publication not identified] PB - Springer Nature KW - attention mechanism KW - visual attention KW - channel attention KW - spatial attention KW - temporal attention KW - image classification KW - B. Sc. Artificial Intelligence KW - UMUN open access collection KW - computer vision KW - Journal articles N1 - Publication type: Journal article; Linked open-access copy: published version; Open access; no subscription required for the linked open-access version N2 - Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image. Attention mechanisms have achieved great success in many visual tasks, including image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multimodal tasks, and self-supervised learning. In this survey, we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention, and branch attention; a related repository https://github.com/MenghaoGuo/Awesome-Vision-Attentions is dedicated to collecting related work. We also suggest future directions for attention mechanism research UR - https://link.springer.com/content/pdf/10.1007/s41095-022-0271-y.pdf ER -