.png){kind=icon}
D
Dahua Lin
H指数:89
被引数:4.3万
个人简介
I am an Associate Professor at the department of Information Engineering, the Chinese University of Hong Kong, and the Director of CUHK-SenseTime Joint Laboratory. I 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, I served as a Research Assistant Professor at Toyota Technological Institute at Chicago, from 2012 to 2014. My research interest covers computer vision and machine learning. In recent years, I primarily focused on deep learning and its applications on high-level visual understanding, cross-domain modeling, and big data analytics. I have published over 120 papers on top conferences and journals, e.g. CVPR, ICCV, ECCV, ICML, NeurIPS, and T-PAMI. My 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. I also received the outstanding reviewer awards in ICCV 2009 and ICCV 2011. I supervised or co-supervised CUHK teams in international competitions and won multiple awards in ImageNet 2016, ActivityNet 2016 & 2017, COCO 2018 & 2019.
教育背景
2004.12
University of Science and Technology of China (USTC) B.Eng.
2006.12
Chinese University of Hong Kong (CUHK) M. Phil.
2012.12
Massachusetts Institute of Technology (MIT) Ph.D.
工作经历
2012.01 – 2014.12
Toyota Technological Institute at Chicago
Research Assistant Professor
荣誉奖项
- best student paper award in NIPS（2010）
- outstanding reviewer awards in ICCV（2009）
- outstanding reviewer awards in ICCV（2011）
- COCO 2019（2019）
- COCO 2018（2018）
- ActivityNet 2017（2017）
- ActivityNet 2016（2017）
- ImageNet 2016（2016）
- NIPS 2010 Best Student Paper（2010）
- Best Master Thesis（2006）
CrossViewDiff：一种用于卫星视图到街景合成的交叉视图扩散模型
Pattern Recognition
IF7.6
低比特大规模语言模型的调查：基础、系统和算法
Neural Networks
IF6.3
SwinTextSpotter v2：迈向场景文本识别更好协同的方向
LaVie: 具有级联潜在扩散模型的高质量视频生成
我们离GPT-4V还有多远？利用开源套件缩小与商业多模式模型的差距
IEEE NETWORK
IF6.3
联合学习镜头的属性和组成，以进行视频中的边界检测
基于结构化分段网络的时序动作检测
