GAMES Webinar 2018-32期(ICCV 2017论文报告)| 周星壹( 德克萨斯大学奥斯汀分校),季梦奇(香港科技大学)

【GAMES Webinar 2018-32期(ICCV 2017论文报告)】
报告嘉宾1: 周星壹,德克萨斯大学奥斯汀分校
报告时间:2018年1月25日(星期四)晚20:00 – 20:45(北京时间)
报告题目:Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
We study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images with 2D pose or in the lab images with 3D pose. We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure. Our network augments a state-of-the-art 2D pose estimation sub-network with a 3D depth regression sub-network. Unlike previous two-stage approaches that train the two sub-networks sequentially and separately, our training is end-to-end and fully exploits the correlation between the 2D pose and depth estimation sub-tasks. The deep features are better learned through shared representations. In doing so, the 3D pose labels in controlled lab environments are transferred to in the wild images. In addition, we introduce a 3D geometric constraint to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels. Our method achieves competitive results on both 2D and 3D benchmarks.
讲者简介:Xingyi Zhou is a fresh Computer Science Ph.D. student at The University of Texas at Austin, working with Prof. Qixing Huang. Before coming to Austin, he graduated from School of Computer Science at Fudan University, advised by Prof. Wei Zhang and Prof. Xiangyang Xue. He has spent 6 months as a research intern at Microsoft Research Asia, working with Dr. Yichen Wei. His research focuses on computer vision and machine learning, especially for object keypoints estimation.


报告时间:2018年1月25日(星期四)晚20:45 – 21:30(北京时间)
报告题目:SurfaceNet: An End-To-End 3D Neural Network for Multiview Stereopsis


GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播?”及“如何加入GAMES微信群?”的信息;




You may also like...