Gait recognition, which refers to the recognition or identification of a person based on their body shape and walking styles, derived from video data captured from a distance, is widely used in crime prevention, forensic identification, and social security. However, to the best of our knowledge, most of the existing methods use appearance, posture and temporal feautures without considering a learned temporal attention mechanism for global and local information fusion. In this paper, we propose a novel gait recognition framework, called Temporal Attention and Keypoint-guided Embedding (GaitTAKE), which effectively fuses temporal-attention-based global and local appearance feature and temporal aggregated human pose feature. Experimental results show that our proposed method achieves a new SOTA in gait recognition with rank-1 accuracy of 98.0% (normal), 97.5% (bag) and 92.2% (coat) on the CASIA-B gait dataset; 90.4% accuracy on the OU-MVLP gait dataset.
@article{arxiv.2207.03608,
title = {GaitTAKE: Gait Recognition by Temporal Attention and Keypoint-guided Embedding},
author = {Hung-Min Hsu and Yizhou Wang and Cheng-Yen Yang and Jenq-Neng Hwang and Hoang Le Uyen Thuc and Kwang-Ju Kim},
journal= {arXiv preprint arXiv:2207.03608},
year = {2022}
}
Comments
IEEE International Conference on Image Processing 2022