Intelligent Video Analysis with Deep Learning

Analyzing videos is one of the fundamental problems of computer vision and multimedia analysis for decades. The task is very challenging as video is an information-intensive media with large variations and complexities. Thanks to the recent development of deep learning techniques, researchers in both computer vision and multimedia communities are now able to boost the performance of video analysis significantly and initiate new research directions to analyze video content. This tutorial will present recent advances under the umbrella of video understanding, which start from basic networks that are widely adopted in state-of-the-art deep learning frameworks, to fundamental challenges of video representation learning and video classification/recognition, finally to an emerging area of vision and language.

Tao Mei is a Senior Researcher with Microsoft Research Asia. His current research interests include multimedia analysis and understanding, computer vision, and machine learning. He is leading a team working on image and video analysis, vision and language, and multimedia search. Tao has shipped a dozen inventions and technologies to Microsoft products, such as Windows Photo, Bing, Office, Azure, OneDrive, Cognitive Services, Chat Bot, Cognitive Services, etc. He has authored or co-authored over 100 papers (with an h-index of 44) in journals and conferences, 10 book chapters, and edited four books. He holds over 40 US and international patents (with 18 granted). Tao was the recipient of a number of paper awards from prestigious multimedia journals and conferences, including the Best Paper Awards from ACM Trans. on Multimedia Computing, Communications, and Applications (2017),  IEEE Trans. on Circuits and Systems for Video Technology (2014), IEEE Trans. on Multimedia (2013), ACM International Conference on Multimedia (2009 and 2007), and so on. He is an Editorial Board Member of IEEE Trans. on Multimedia (TMM), ACM Trans. on Multimedia Computing, Communications, and Applications (TOMM), ACM Trans. on Intelligent Systems and Technology (TIST),  Pattern Recognition (PR), and so on. He is the General Co-chair of IEEE ICME 2019 and ICIMCS 2013, the Program Co-chair of ACM Multimedia 2018, CBMI 2017, IEEE ICME 2015, IEEE MMSP 2015 and MMM 2013, and the Area Chair for a dozen international conferences.
Tao received B.E. (1996-2001) and Ph.D. (2001-2006) degrees from the University of Science and Technology of China, Hefei, China, in 2001 and 2006, respectively. He is an Adjunct Professor (PhD supervisor) of the University of Science and Technology of China and the Sun Yat-Sen University, and a Guest Professor of Fudan University. Tao was elected as a Fellow of IAPR and a Distinguished Scientist of ACM in 2016, for his contributions to large-scale video analysis and applications.