Knowledge Commons of Institute of Automation,CAS
Occlusion-Aware Siamese Network for Human Pose Estimation | |
Zhou Lu1,2![]() ![]() ![]() ![]() | |
2020 | |
会议名称 | European Conference on Computer Vision |
会议日期 | 8.23-8.28 |
会议地点 | 英国(在线会议) |
摘要 | Pose estimation usually suffers from varying degrees of performance degeneration owing to occlusion. To conquer this dilemma, we propose an occlusion-aware siamese network to improve the performance. Specifically, we introduce scheme of feature erasing and reconstruction. Firstly, we utilize attention mechanism to predict the occlusion-aware attention map which is explicitly supervised and clean the feature map which is contaminated by different types of occlusions. Nevertheless, the cleaning procedure not only removes the useless information but also erases some valuable details. To overcome the defects caused by the erasing operation, we perform feature reconstruction to recover the information destroyed by occlusion and details lost in cleaning procedure. To make reconstructed features more precise and informative, we adopt siamese network equipped with OT divergence to guide the features of occluded images towards those of the un-occluded images. Algorithm is validated on MPII, LSP and COCO benchmarks and we achieve promising results. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44607 |
专题 | 紫东太初大模型研究中心 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.ObjectEye Inc. 4.NEXWISE Co., Ltd. |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhou Lu,Chen Yingying,Gao Yunze,et al. Occlusion-Aware Siamese Network for Human Pose Estimation[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Occlusion-Aware Siam(1420KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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