Dr. Yonghong Tian is currently dean of school of electronic and computer engineering，a Boya Distinguished Professor with the Department of Computer Science and Technology, Peking University, China, and is also the deputy director of Artificial Intelligence Research Center, PengCheng Laboratory, Shenzhen, China. His research interests include neuromorphic vision, brain-inspired computation and multimedia big data. He has co-authored over 200 technical articles in refereed journals such as IEEE TPAMI/TNNLS/TIP/TMM/TCSVT/TKDE/ TPDS/TCYB, ACM CSUR/TOIS/TOMM and conferences such as NeurIPS/CVPR/ICCV/AAAI/ACMMM/WWW. Meanwhile, he has owned more than 85 US and China Invention Patents, and won the Award for National Excellent Patent of China in 2016. He was the recipient of the Chinese National Science Foundation for Distinguished Young Scholars in 2018, two National Science and Technology Awards and three ministerial-level awards in China, and obtained the 2015 EURASIP Best Paper Award for Journal on Image and Video Processing, and the best paper award of IEEE BigMM 2018. He is also the main technical contributor of IEEE Standard 1857.6-2018 and 1857a-2014, and the Co-Editor of ISO/IEC DIS 39794-16.
His main contributions are summarized as follows: 1) He has made a milestone contribution to analysis-friendly video coding technology. By creatively embedding a low-complexity and high-efficiency background modeling module into the video coding loop, he established a novel scene-based video coding framework that can achieve approximately twice the coding efficiency on surveillance videos while remarkably reducing the encoding complexity. It then became the IEEE Std. 1857 surveillance video profile in 2014. 2) He has made a seminal contribution to developing innovative video analytic algorithms and systems for visual big data applications. He pioneered the visual saliency computation approach uniquely from a machine learning perspective and creatively designed a fine-grained object recognition scheme at the very early stage, both inspired by the neurobiological mechanisms of human vision system. This work promoted the learning-based visual saliency computing and fine-grained object recognition to become the mainstream research topics in this field. 3) He pioneered a high-efficient compression framework of visual spike streams for biologically-inspired event cameras, and more importantly, his team invented a retina-like visual sensing chip with the extra-high sampling frequency of 40,000 Hz, even with the same common photosensitive devices as traditional cameras. Currently, he is also the Chief Architector of the Pengcheng CloudBrain, the Rank-1 AI Supercomputer in the IO500 list announced by Supercomputing 2020 and 2021.
He was/is an Associate Editor of IEEE TCSVT (2018.1-), IEEE TMM (2014.8-2018.8), IEEE Multimedia Mag. (2018.1-), and IEEE Access (2017.1-2019.12), and received the Best Associate Editor Award of IEEE TCSVT in 2020. He co-initiated IEEE Int’l Conf. on Multimedia Big Data (BigMM), served as the General Co-chair of IEEE MIPR 2020 and ICME2021, and the Technical Program Co-chair of IEEE ICME 2015, IEEE ISM 2015, IEEE BigMM 2015 and IEEE MIPR 2018/2019. He is the steering member of IEEE ICME (2018-2020) and IEEE BigMM (2015-), and is a TPC Member of more than ten conferences such as NeurIPS, CVPR, ICCV, ACM KDD, AAAI, ACM MM and ECCV. He Led the guest editor team of the IEEE TMM SI in 2019, 2015, and the IEEE Multimedia SI in 2016. Currently, he is the Vice Chair of IEEE Standard Committee for Data Compression, and the Chair of IEEE 2941 and China Standard Working Group for AI Model Representation and Compression. He is a Fellow of IEEE, a senior member of CIE and CCF, a member of ACM, and serves as the Vice Chair of IEEE CASS Beijing Chapter.
