时间：2021-11-09
本文（Extreme low-resolution activity recognition using a super-resolution-oriented generative adversarial network）原载Micromachines，由四川大学计算机学院张意教授等科研人员创作，系四川大学“智慧法治”超前部署学科系列学术成果。后续会持续分享四川大学“智慧法治”超前部署学科系列学术成果，欢迎大家阅读。
Activity recognition is a fundamental and crucial task in computer vision. Impressive results have been achieved for activity recognition in high-resolution videos, but for extreme low-resolution videos, which capture the action information at a distance and are vital for preserving privacy, the performance of activity recognition algorithms is far from satisfactory. The reason is that extreme low-resolution (e.g., 12 x 16 pixels) images lack adequate scene and appearance information, which is needed for efficient recognition. To address this problem, we propose a super-resolution-driven generative adversarial network for activity recognition. To fully take advantage of the latent information in low-resolution images, a powerful network module is employed to super-resolve the extremely low-resolution images with a large scale factor. Then, a general activity recognition network is applied to analyze the super-resolved video clips. Extensive experiments on two public benchmarks were conducted to evaluate the effectiveness of our proposed method. The results demonstrate that our method outperforms several state-of-the-art low-resolution activity recognition approaches.
Mingzheng Hou#, Song Liu#, Jiliu Zhou*, Yi Zhang*, and Ziliang Feng. Extreme low-resolution activity recognition using a super-resolution-oriented generative adversarial network. Micromachines, pp. 670, vol. 12, no. 6, 2021.（论文下载）
