Dahua Lin

  • PhD.
  • Assistant Professor
  • Department of Information Engineering
  • The Chinese University of Hong Kong
Curriculum Vitae

Dahua Lin is an Assistant Professor at the department of Information Engineering, the Chinese University of Hong Kong. He received the B.Eng. degree from the University of Science and Technology of China (USTC) in 2004, the M. Phil. degree from the Chinese University of Hong Kong (CUHK) in 2006, and the Ph.D. degree from Massachusetts Institute of Technology (MIT) in 2012. Prior to joining CUHK, he served as a Research Assistant Professor at Toyota Technological Institute at Chicago, from 2012 to 2014.

His research interest covers computer vision and machine learning. In recent years, he primarily focused on deep learning and its applications on high-level visual understanding, probabilistic inference, and big data analytics. He has published about sixty papers on top conferences and journals, e.g. ICCV, CVPR, ECCV, NIPS, and T-PAMI. His seminal work on a new construction of Bayesian nonparametric models has won the best student paper award in NIPS, the most prestigious conference on machine learning, in year 2010. He also received the outstanding reviewer award in ICCV 2009 and ICCV 2011. He has supervised or co-supervised the CUHK team in international competitions and won multiple awards in ImageNet 2016, ActivityNet 2016, and ActivityNet 2017.

Research Interests

  • Deep learning technologies in large-scale applications
  • High level visual understanding in connection with linguistic analysis
  • Efficient modeling and analytics of videos and movies
  • The use of deep networks in general probabilistic inference

Educations

2012
2006

M.Phil.

in Information Engineering
The Chinese University of Hong Kong (CUHK)

2004

B.Eng.

in Information Science and Electronic Engineering
University of Science and Technology of China (USTC)

Positions

2014

Assistant Professor

in Information Engineering
The Chinese University of Hong Kong (CUHK)

2012

Research Assistant Professor

Selected Honors & Awards

2017

ActivityNet 2017

Supervised the CUHK team in ActivityNet 2017, who won No.2 in three tracks, untrimmed video classification, trimmed classification on Kinetics, and temporal action localization.

2017

ActivityNet 2016

Supervised the CUHK team in ActivityNet 2016, who won No.1 in the track of untrimmed video classification. Later in the same year, the Structured Segmental Network (SSN) gets No.1 in the track of temporal action localization.

2016

ImageNet 2016

Co-supervised the CUHK teams in ImageNet 2016, who won No.1 in two tracks, DET and VID, and No.3 in image classification. Particularly, I supervised the development of PolyNet, which achieves the best single-network performance. It remains the best-performing network until June 2017.

2010

NIPS 2010 Best Student Paper

I proposed a new construction of Dirichlet processes, which fundamentally differs from previous constructions and makes it easy to build a sequence of dependent DPs. This work won the best student paper award at NIPS 2010, the most prestigious conference on machine learning.

2006

Best Master Thesis

I graduated as an M.Phil. student of CUHK in year 2006. My master thesis on face recognition won the best master thesis award of the faculty of Engineering, CUHK.