Multimedia Laboratory
The Chinese University of Hong Kong
Deep Learning
Deep learning is one of the most fascinating learning technologies. MMLAB formulates novel deep models for various vision tasks such as face parsing and pedestrian detection. Read More
Crowd Analysis
Automatically understanding the behaviors of crowd from video sequences is of great interest to the computer vision community, and has drawn more and more attentions in recent years. It has important applications to event recognition, traffic flow estimation, behavior prediction, abnormality detection, and crowd simulation. Read More
Face Sketch Synthesis and Recognition
Artists have a fascinating ability to capture the most distinctive characteristics of human faces and depict them on sketches. Although sketches are very different from photos in style and appearance, human beings often can easily recognize a person from his sketch. We design computer programs to also have such amazing abilities. Read More
Photo Quality Assessment based on Aesthetic Perception
MMLAB develops fast and effective computing algorithms which can automatically conduct aesthetic assessment of large scale photo datasets inspired by the criteria and skills adopted by professional photographers. Read More
One-Click Internet Image Search
We target on greatly improving user experience of web-based image search engines with extremely simple user interaction. It interprets users’ search intention with the minimum feedback effort: only one click on the query image from a pool retrieved by text-based search. Read More
Face Detection, Alignment, and Recognition
MMLAB develops novel algorithms for automatically locating facial keypoints, aligning face images, and identifying or verifying a person from a digital image or a video stream. Read More
A Quick Glance
- The Multimedia Laboratory of the Department of Information Engineering is established in July 2001.
- We won the CVPR 2009 Best Paper Award. This is the first one ever from Asia. Read more
K. He, J. Sun, and X. Tang, "Single Image Haze Removal Using Dark Channel Prior ," CVPR, 2009 - Best paper awards by our lab's alumni:
- Dahua Lin with his paper "Construction of Dependent Dirichlet Processes based on Poisson Processes", NIPS, 2010
- Dong Xu with his paper "Visual Event Recognition in Videos by Learning from Web Data", CVPR, 2010
- Shuicheng Yan with his paper "Dynamic Captioning: Video Accessibility Enhancement for Hearing Impairment" in ACM MM, 2010, and his paper "Automated Assembly of Shredded Pieces from Multiple Photos" in ICME, 2010
- Lab members that pursue oversea studies: MIT (4 students), Standford (2 students), Cambridge (1 student), Columbia (2 students), CMU (2 students).
- 13 Hong Kong PhD fellows. Read more
- Our work with Microsoft Research Asia (MSRA) are now being used by two major Microsoft products.
Recent Papers
Representative Papers
Demos
Latest News
10/05/13
New website launched!
A completely new look & feel!
Site Credits
23/03/13
Outstanding Thesis Award
Bolei Zhou's Mphil thesis titled "Modeling Crowd Behaviors in Video",
supervised by Prof. Tang and Prof. Wang,
is selected as the winner of Faculty's Outstanding Thesis Award 2012, congratulations!
Read more
24/02/13
CVPR 2013
We have eight papers (one oral) accepted to the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13, Oregon). This year CVPR received 1870 paper submissions, of which 60 were selected for oral presentation, with 472 posters. The oral acceptance rate is 3.2% and the overall acceptance rate is 25.2%.
Read more
11/01/13
Outstanding Fellow of the Faculty of Engineering
Prof. Tang was granted by the Chinese University of Hong Kong as the Outstanding Fellow of the Faculty of Engineering (工程學院傑出學人)
Read more
2012
Teaching Award
Congratulations to Wei Zhang for winning the Best Teaching Assistant Award for 2011-2012 academic year!