Multimedia Laboratory
The Chinese University of Hong Kong
OpenMMLab Project
The OpenMMLab project aims at building high-quality open-source toolboxes for several important research areas, including object detection, action recognition, etc. Read More
Face Analysis
MMLAB develops novel algorithms for automatically detecting faces, locating facial keypoints, aligning face images, and identifying or verifying a person from a digital image or a video stream. Read More
Person 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
Video Understanding
Placeholder. Read More
Detection and Segmentation
Our research includes object detection, semantic segmentation, instance segmentation. Read More
Low-level Vision
MMLAB develops efficient and effective algorithms that improve image and video qualities. We dedicate to enhance the world we see. Read More
Architecture and Learning
Placeholder. Read More
The CUHK Multimedia Lab (MMLab) is one of the pioneering institutes on deep learning. In GPU
Technology Conference (GTC)
2016, a world-wide technology summit, our lab is recognized as one of the top ten AI
pioneers,
and listed together with top research groups in the world (e.g. MIT, Stanford, Berkeley, and
Univ. of Toronto). Today, we remain one of the most active research labs in computer vision
and
deep learning, publishing over 40 papers on top conferences (CVPR/ICCV/ECCV/NIPS) every
year.
Our lab has a large group of talented students, plenty of computational resources, and
steady
financial support, and free research environment.
A Quick Glance
- The Multimedia Laboratory of the Department of Information Engineering is established by Prof. Xiaoou Tang 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 Outstanding Student Paper Award
- Dong Xu with his paper "Visual Event Recognition in Videos by Learning from Web Data", CVPR, 2010 Best Student Paper Award
- Huan Wang with his paper "Exact Recovery of Sparsely-Used Dictionaries", COLT, 2012 Best Paper Award
- Shuicheng Yan with his papers "Dynamic Captioning: Video Accessibility Enhancement for Hearing Impairment" in ACM MM, 2010 Best paper Award; "Automated Assembly of Shredded Pieces from Multiple Photos" in ICME, 2010; "Wow! You Are So Beautiful Today!", ACM MM, 2013 Best Paper Award; "Attributes-augmented Semantic Hierarchy for Image Retrieval", ACM MM, 2013 Best Student Paper Award
- Kai Kang with his paper "T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos", IEEE TCSVT 2018, 2020 IEEE Circuits and System Society Outstanding Young Author Award
Latest News
05/2019
WIDER Face and Person Challenge
We organize the second WIDER Face and Person
Challenge in conjunction with ICCV 2019. There
are four exciting tracks with great prizes. Deadline of challenge: July 25, 2019.
05/2019
NTIRE 2019 winner
Our new video restoration method, EDVR, won all four tracks in the
NTIRE 2019 video
restoration and enhancement challenges.
02/2019
CVPR 2019
We have 33 papers (7 oral) accepted to CVPR 2019.
12/2018
ICLR 2019
Our lab have 3 papers accepted to ICLR 2019.
11/2018
AAAI 2019
Our lab have 6 papers (4 oral and 1 spotlight) accepted to AAAI 2019.
09/2018
COCO 2018 Challenge Winner
Our team MMDet wins the COCO
2018 Challenge (object detection/instance segmentation track). Codebase is released.
09/2018
NeurIPS 2018
Our lab have 5 papers accepted to NeurIPS 2018.
07/2018
ECCV 2018
Our lab have 26 papers accepted to ECCV 2018.
02/2018
CVPR 2018
Our lab have 28 papers (1 oral and 7 spotlight) accepted to CVPR 2018.