@article{Guo2022, 
author = {Meng-Hao Guo and Tian-Xing Xu and Jiang-Jiang Liu and Zheng-Ning Liu and Peng-Tao Jiang and Tai-Jiang Mu and Song-Hai Zhang and Ralph R. Martin and Ming-Ming Cheng and Shi-Min Hu},
title = {Attention mechanisms in computer vision: A survey},
year = {2022},
journal = {Computational Visual Media},
volume = {8},
number = {3},
pages = {331-368},
keywords = {attention, computer vision, deep learning, transformer, salience},
url = {https://www.sciopen.com/article/10.1007/s41095-022-0271-y},
doi = {10.1007/s41095-022-0271-y},
abstract = {Humans can naturally and effectively find salient regions in complex scenes. Motivated by thisobservation, 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, multi-modal 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.}
}