University of Technology, Sydney

Staff directory | Webmail | Maps | Newsroom | What's on

QCIS Seminar: Deep Learning in Object Detection, Segmentation and Recognition - Prof Xiaogang Wang, Chinese University of Hong Kong, China

Presenter: Prof Xiaogang Wang, The Chinese University of Hong Kong, China (invited by Prof Dacheng Tao)

Abstract: A major breakthrough in artificial intelligence is deep learning,which has achieved amazing success in solving grand challenges in many fields, including computer vision. In this seminar, I will introduce our recent work to develop deep models to solve several computer vision problems, including pedestrian detection, facial keypoint detection, face parsing, pedestrian parsing, face recognition, and face attribute recognition. Deep models significantly advance the state-of-the-art for these challenges because of their capability to automatically learn hierarchical feature representations from data, disentangle hidden features, jointly optimise key components in a computer vision system, and their learning capacity. I will share our experience on how to formulate a vision problem with deep learning with examples, and how to effectively train a deep neural network. Instead of treating a deep model as a black box, we investigate the connection between deep models and existing vision systems, so that a lot of insights and experience accumulated from vision research can be used to develop new deep models and effective training strategies. The large learning capacity of deep models also enables us to recast some classical computer vision challenges as high-dimensional data transformation problems and solve them from new perspectives.

Short Bio:  Prof Xiaogang Wang received his Bachelor degree in Electrical Engineering and Information Science from the Special Class of Gifted Young at the University of Science and Technology of China in 2001, an MA Phil degree in Information Engineering from the Chinese University of Hong Kong in 2004, and his PhD degree in Computer Science from Massachusetts Institute of Technology in 2009. He has been an Assistant Professor in the Department of Electronic Engineering at the Chinese University of Hong Kong since August 2009. He received the Outstanding Young Researcher Award in Automatic Human Behaviour Analysis in 2011, the Hong Kong RGC Early Career Award in 2012, and the Young Researcher Award of the Chinese University of Hong Kong. He is the associate editor of the Image and Visual Computing Journal. He was the area chair for ICCV 2011, ECCV 2014 and ACCV 2014. His research interests include computer vision, deep learning, crowd video surveillance, object detection, and face recognition.


1 December 2013
14:00 - 15:30
City - Broadway CB10 Level 4, Room 460
All Welcome
Barbara Munday

Back to list of Past Events