20180815-25 杨巍:Human pose estimation with deep learning

报告嘉宾：杨巍（香港中文大学）

报告时间：2018年08月15日（星期三）晚上20:00（北京时间）

报告题目：Human pose estimation with deep learning

主持人：欧阳万里（香港中文大学）

报告人简介：

Wei Yang is currently a final year Ph.D. student at the Electronic Engineering, the Chinese University of Hong Kong, advised by Prof. Xiaogang Wang. He also works with the Multimedia Laboratory, CUHK. He was a visiting student at CMU working on visual navigation with Prof. Abhinav Gupta from November 2017 to April 2018. He achieved the master's degree in Computer Science under the supervision of Prof. Liang Lin at Sun Yat-sen University. He achieved my BEng in Software Engineering, Sun Yat-sen University. His research interests include computer vision, deep learning, and deep reinforcement learning. 

个人主页：

http://www.ee.cuhk.edu.hk/~wyang/

报告摘要：

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The goal is to estimate 2D or 3D locations of human body joints given an image or a video sequence. It serves as informative knowledge for higher-level applications, such as activity recognition, human-computer interaction, robotics vision, and autonomous driving. Although promising progress has been achieved by deep neural networks, obtaining accurate human pose estimation is still nontrivial due to the highly articulated human body limbs, occlusion, cluttered background, scale variation, and foreshortening. On the other hand, 3D human pose estimation for RGB images in the wild is still a challenge due to the limitation of annotated data. In this talk, I will present our recent research work to tackle these challenges with deep learning methods. pose estimation with deep learning method enhanced by incorporating these three key ingredients.

参考文献：

[1] End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation. Wei Yang, Wanli Ouyang, Hongsheng Li, and Xiaogang Wang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[2] Multi-Context Attention for Human Pose Estimation. Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma, Alan L. Yuille, Xiaogang Wang。 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

[3] Learning Feature Pyramids for Human Pose Estimation. Wei Yang, Shuang Li, Wanli Ouyang, Hongsheng Li, Xiaogang Wang. International Conference on Computer Vision (ICCV), 2017.

[4] 3D Human Pose Estimation in the Wild by Adversarial Learning. Wei Yang, Wanli Ouyang, Xiaolong Wang, Jimmy Ren, Hongsheng Li, Xiaogang Wang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

18-25期VALSE在线学术报告参与方式：

长按或扫描下方二维码，关注”VALSE“微信公众号（valse_wechat），后台回复”25期“，获取直播地址。

特别鸣谢本次Webinar主要组织者：

VOOC责任委员：欧阳万里（香港中文大学）

活动参与方式：

1、VALSE Webinar活动依托在线直播平台进行，活动时讲者会上传PPT或共享屏幕，听众可以看到Slides，听到讲者的语音，并通过聊天功能与讲者交互；

2、为参加活动，请关注VALSE微信公众号：valse_wechat 或加入VALSE QQ群（目前A、B、C、D、E、F、G群已满，除讲者等嘉宾外，只能申请加入VALSE H群，群号：701662399）；

*注：申请加入VALSE QQ群时需验证姓名、单位和身份，缺一不可。入群后，请实名，姓名身份单位。身份：学校及科研单位人员T；企业研发I；博士D；硕士M。

3、在活动开始前5分钟左右，讲者会开启直播，听众点击直播链接即可参加活动，支持安装Windows系统的电脑、MAC电脑、手机等设备；

4、活动过程中，请不要说无关话语，以免影响活动正常进行；

5、活动过程中，如出现听不到或看不到视频等问题，建议退出再重新进入，一般都能解决问题；

6、建议务必在速度较快的网络上参加活动，优先采用有线网络连接；

7、VALSE微信公众号会在每周一推送上一周Webinar报告的总结及视频（经讲者允许后），每周四发布下一周Webinar报告的通知及直播链接。

[slides]