Visual Computing Research Group

 

Lab Name and Affiliation

Visual Computing Research Group

School of Computer Engineering, Nanyang Technological University


Lab Director (or Principal Investigator)

Dong Xu received the B.Eng. and PhD degrees from University of Science and Technology of China, in 2001 and 2005, respectively. While pursuing the PhD degree, he worked at Microsoft Research Asia and The Chinese University of Hong Kong for more than two years. He also worked at Columbia University for one year as a postdoctoral research scientist. In May 2007, he joined Nanyang Technological University in Singapore, where he is currently an associate professor with School of Computer Engineering.
His research focuses on new theories, algorithms and systems for intelligent processing and understanding of visual data such as images and videos. He has published more than 50 papers in IEEE Transactions (including 8 papers in T-PAMI) and more than 30 papers in top tier conferences CVPR, ICCV, ECCV, ICML, ACM MM and MICCAI. He was the co-author (with his former PhD student Lixin Duan) of a paper that won the Best Student Paper Award in CVPR 2010. His publications have been cited more than 2000 times in Scopus. Since 2008, he has received over S$3.5M in research grant funding, from Singapore National Research Foundation (NRF), A*STAR, Ministry of Education (MOE), Rolls-Royce Singapore Pte Ltd (RRSPL) and Microsoft Research Asia (MSRA). The former PhD students Yi Huang and Lixin Duan in his research group were awarded the prestigious MSRA Fellowship Awards in 2008 and 2009, respectively.
He is on the editorial boards of IEEE Transactions on Neural Networks and Learning Systems and Machine Vision and Applications (Springer). He is currently serving as a guest editor of a special issue on Domain Adaptation for Vision Applications in IJCV and a program co-chair of ICME 2014. He has served as an area chair of CVPR 2012, a program co-chair of PCM 2012, and guest editors of five special issues in T-CSVT, T-SMC-B, ACM TOMCCAP, CVIU and IEEE Multimedia.


Lab Introduction

Our research focuses on new theories, algorithms and systems for intelligent processing and understanding of visual data such as images and videos. Our current research activities focus on four areas:
Internet Vision and Social Media, including Large Scale Image and Video Search and Retrieval, Social Context-based Media Content Analysis.
Event Analysis from various video sources including Surveillance, News Videos and User-generated Videos.
Biometrics, including face recognition and tagging, human gait recognition.
Machine Learning for Vision, including Manifold Learning, Bilinear and Tensor Subspace Learning, Transfer Learning, Semi-supervised Learning.


Lab Contact E-mail

dongxu@ntu.edu.sg


Lab URL

http://vc.sce.ntu.edu.sg