特別講演

MIRU2018では，海外の著名研究者による特別講演（2件）を企画しました．ぜひ，ご参加下さい．

Abstract: This talk will have two parts. Firstly, I will introduce some recent achievements at the Chinese University of Hong Kong and SenseTime. We experienced great challenges and also discovered interesting problems when applying deep learning and computer vision research to industry. In the second part, several works on structured deep learning and applications in computer vision will be introduced. Different from classical deep neural networks, which only pass information feedforward, we have designed sophisticated message passing schemes to model interactions among neurons and they substantially increased the learning capacity of networks. Information can pass horizontally within the same intermediate layers controlled with gates, is first resolved within small groups of neurons and then propagated across groups. Various message passing schemes on neural networks can be unified under a new a CRF-CNN framework in a probabilistic way. With this technology, the SenseTime-CUHK team won three championships in ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2016. Instead of manually designing network structures through extensive experiments, we also developed new technologies automatically learn network structures from data with low computation cost.

Bio: Xiaogang Wang received his Bachelor degree in Electronic Engineering and Information Science from the Special Class of Gifted Young at the University of Science and Technology of China in 2001, M. Phil. degree in Information Engineering from the Chinese University of Hong Kong in 2004, and PhD degree in Computer Science from Massachusetts Institute of Technology in 2009. He is an associate professor in the Department of Electronic Engineering at the Chinese University of Hong Kong since August 2009. He received PAMI Young Research Award Honorable Mention in 2016, the Outstanding Young Researcher in Automatic Human Behaviour Analysis Award in 2011, Hong Kong RGC Early Career Award in 2012, and Young Researcher Award of the Chinese University of Hong Kong. The SenseTime-CUHK team led by him won three championships in object detection, object detection/tracking from videos, and scene parsing in ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2016. He is the associate editor of the Image and Visual Computing Journal, Computer Vision and Image Understanding, IEEE Transactions on Circuit Systems and Video Technology. He was the area chair of CVPR 2017, ICCV 2011, ICCV 2015, ICCV 2017, ECCV 2014, ECCV 2016, ACCV 2014, and ACCV 2015. His research interests include computer vision and deep learning.

Abstract: Humans are probably the most important subject in the many hours of video that are recorded and consumed every minute. Computer vision technology for automatic recognition of human activities and actions has the potential to enable many applications by understanding the semantics of events and activities depicted in such videos. In this talk, I'll give an overview of our work towards the next generation of activity understanding algorithms that are capable of recognizing a large number of activities, localizing them within long video sequences, parsing and describing complex events and even anticipating and predicting actions before they occur.

Bio: Juan Carlos Niebles received an Engineering degree in Electronics from Universidad del Norte (Colombia) in 2002, an M.Sc. degree in Electrical and Computer Engineering from University of Illinois at Urbana-Champaign in 2007, and a Ph.D. degree in Electrical Engineering from Princeton University in 2011. He is a Senior Research Scientist at the Stanford AI Lab and Associate Director of Research at the Stanford-Toyota Center for AI Research since 2015. He is also an Assistant Professor of Electrical and Electronic Engineering in Universidad del Norte (Colombia) since 2011. His research interests are in computer vision and machine learning, with a focus on visual recognition and understanding of human actions and activities, objects, scenes, and events. He is a recipient of a Google Faculty Research award (2015), the Microsoft Research Faculty Fellowship (2012), a Google Research award (2011) and a Fulbright Fellowship (2005).