20161130-39 初晓：Structured feature learning for pose estimation

、

报告嘉宾1：初晓 (The Chinese University of Hong Kong)

报告时间：2016年11月30日（星期三）上午10：00（北京时间）

报告题目：Structured feature learning for pose estimation

主持人：沈为（上海大学）

报告摘要：

In this paper, we propose a structured feature learning framework to reason the correlations among body joints at the feature level in human pose estimation. Different from existing approaches of modelling structures on score maps or predicted labels, feature maps preserve substantially richer descriptions of body joints. The relationships between feature maps of joints are captured with the introduced geometrical transform kernels, which can be easily implemented with a convolution layer. Features and their relationships are jointly learned in an end-to-end learning system. A bi-directional tree structured model is proposed, so that the feature channels at a body joint can well receive information from other joints. The proposed framework improves feature learning substantially

参考文献：

[1] Xiao Chu, Wanli Ouyang, Wei Yang, Xiaogang Wang. Multi-task Recurrent Neural Network for Immediacy Prediction. ICCV 2015

[2] Xiao Chu, Wanli Ouyang, Hongsheng Li, Xiaogang Wang. CRF-CNN: Modelling Structured Information in Human Pose Estimation.”NIPS, 2016

[3] Xiao Chu, Wanli Ouyang, Hongsheng Li, Xiaogang Wang. CVPR 2015..

报告人简介：

Xiao Chu is currently a final year Ph.D. student at the Chinese University of Hong Kong working on computer vision, advised by Professor Xiaogang Wang. Her research interest is in computer vision and machine learning, especially human pose estimation and human interaction analysis. She is a member of both Multimedia Lab and Image and Video Processing Lab. Before that, She received my B.E. degree from Shandong University, in 2013.