【报告题目】Recent Developments of Deep Learning in Computer Vision

【主讲人】Dr. Junliang Xing (兴军亮) Institute of Automation, Chinese Academy of Sciences

【时 间】2016年4月20日（周三）下午15:00-17:00

【地 点】北京大学 计算机所大楼 106报告厅

Abstract:

Deep Learning is currently the hottest research topic in machine learning and has been studied and applied to solve many problems in the areas like audio & speech, text & languages, as well as computer vision. In this report, I will introduce some recent developments of deep learning in the field of computer vision. Specifically, I will introduce some recent developments on model architectures, learning algorithms and new applications. I will also introduce some of my recent work on deep learning. The aim of this talk is to provide some more recent research on the deep learning models for computer vision tasks.

Biography:

Junliang Xing received his B.E. degrees in Computer Science and Technology as well as Applied Mathematics from Xi'an Jiaotong university in 2007, and his PhD degree in Computer Science and Technology from Tsinghua university, 2012. After that, he became an assistant professor within the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences. During his PhD study, he was the recipient of first-class scholarship, distinguished PhD thesis award in Tsinghua University, Google PhD fellowship, etc. His main research areas lie in computer vision, pattern recognition and machine learning, with current focus on vison problems related to object detection, tracking, segmentation, and models related to Sparse Coding, Boosting, and Deep Learning. He has published over 40 journal and conference papers in these fields, on