On the Robustness of 3D Human Pose Estimation | |
Chen, Zerui1,3; Huang, Yan1; Wang, Liang1,2,3,4 | |
2021-03 | |
会议名称 | International Conference on Pattern Recognition |
会议日期 | 2021.1.10-2021.1.15 |
会议地点 | Online |
摘要 | It is widely shown that Convolutional Neural Networks (CNNs) are vulnerable to adversarial examples on most recognition tasks, such as image classification and segmentation. However, few work studies the more complicated task -- 3D human pose estimation. This task often requires large-scale datasets, specialized network architectures, and it can be solved either from single-view RGB images or from multi-view RGB images. In this paper, we make the first attempt to investigate the robustness of current state-of-the-art 3D human pose estimation methods. To this end, we build four representative baseline models, where most of the current methods can be generally classified as one of them. Furthermore, we design targeted adversarial attacks to detect whether 3D pose estimators are robust to different camera parameters. For different types of methods, we present a comprehensive study of their robustness on the large-scale Human3.6M benchmark. Our work shows that different methods vary significantly in their resistance to adversarial attacks. Through extensive experiments, we show that multi-view 3D pose estimators can be more vulnerable to adversarial examples. We believe that our efforts can shed light on future works to design more robust 3D human pose estimators. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44426 |
专题 | 模式识别实验室 |
作者单位 | 1.Center for Research on Intelligent Perception and Computing, NLPR, CASIA 2.Center for Excellence in Brain Science and Intelligence Technology, CAS 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.Chinese Academy of Sciences, Artificial Intelligence Research (CAS-AIR) |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Chen, Zerui,Huang, Yan,Wang, Liang. On the Robustness of 3D Human Pose Estimation[C],2021. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
On the Robustness of(3841KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论