Z-Domain Entropy Adaptable Flex for Semi-Supervised Action Recognition in the Dark

Zhi Chen, Zijun Fan, Yongjie Li, Huaien Gao, Shan Lin; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 4259-4266

The subtask of Human Action Recognition (AR) in the dark is gaining a lot of traction nowadays, which takes a significant place in the field of computer vision. The implementation of its application includes self-driving at night, human-pose estimation, night surveillance, etc. Currently, solutions such as DLN for AR have emerged. However, due to the poor accuracy even when leveraging on large amounts of datasets and complex architectures, the development of AR in the dark has been slow to progress. In this paper, we propose a novel and straightforward method: Z-Domain Entropy Adaptable Flex. This constructs a neural network architecture R(2+1)D, including (i) a self- attention mechanism, which combines and extracts corresponding and complementary features from the dual path- ways; (ii) Zero-DCE low light image enhancement, which improves enhanced quality; and (iii) FlexMatch method, which can generates the pseudo-labels flexibly. With the help of pseudo-labels from FlexMatch, our proposed Z- DEAF method facilitates the process of gaining desired classification boundaries. This works by repeating Expand- ing Entropy and Shrinking Entropy. It aims to solve the problem of unclear classification boundaries between the categories. Our model obtains superior performance in experiments, and achieves state-of-the-art results on ARID.