Course Instructor

Li Yali

Dr. Li Ya-Li is currently the Assistant Professor of Tsinghua University. She received the PhD from Tsinghua University. Her research interests include: visual understanding, object detection, few-shot recognition, image captioning. She has published more than 50 papers. She won the ICPR best paper per track award in 2018.

Dai Jifeng

Dr. Dai Jifeng serves as Executive Research Director at SenseTime Research. His current research focus is on deep learning algorithms, especially for semantic segmentation and object detection in computer vision. He has published more than 30 papers in world-renowned journals and conferences with more than 16000 citations. He won the 1st place in COCO challenge in 2015 and 2016. He is an Editorial Board Member of the IJCV, and Area Chair of ECCV 2020 and CVPR 2021. He got his B.S. degree and Ph.D. degree from the Department of Automation, Tsinghua University in 2009 and 2014. During his Ph.D. study, he visited the VCLA lab of University of California, Los Angeles (UCLA) between 2012 and 2013.

Li Hongyang

Dr. Li Hongyang is working as senior R&D manager of SenseTime. He is responsible for autonomous driving R&D related business. He received his PhD from Multimedia Lab (MMLab), the Chinese University of Hong Kong in 2020, and received a full scholarship from the Hong Kong government.
His research interests includes computer vision and deep learning, focusing on object detection, pose estimation, CNN structure research, and few-sample learning. He has published 13 papers with more than 1000 citations in top conferences (ICCV/CVPR/ECCV, ICML/ICLR/NeurIPS) and journals (PAMI/IJCV) in the fields of CV, ML, etc., including the first author of 6 papers and 1 CVPR oral report.

Guest Speaker

Shi Jianping

Dr. Shi Jianping is the Research Executive Director of SenseTime. She has led the autonomous driving R&D team in SenseTime, and promoted the long term cooperation of SenseTime with Honda. She also has launched algorithms to multiple product line including mobile applications, remote sensing etc.
Jianping graduated with her B. Eng degree from Computer Science and Technology Department and Chu KoChen Honors College in Zhejiang University in 2011. She got her Ph.D. degree in Computer Science and Engineering Department in the Chinese University of Hong Kong in 2015. Jianping is an expert in deep learning and computer vision. She led SenseTime team to win multiple championships including ImageNet Scene Parsing Challenge 2016, COCO Instance Segmentation Challenge 2017, 2018, to name a few. Jianping has published over 40 papers on top conferences and journals including SIGGRAPH Asia, CVPR, ICCV, ECCV, NIPS, MM, TPAMI, TIP, etc. Her publications received over 3400 citations on Google Scholar. Jianping received Microsoft Research Asia Fellowship in 2013, HK-ACM Best Junior Research Award in 2013, and Hong Kong PhD Fellowship in 2011.

Qian Chen

Qian Chen, currently the Research Director of SenseTime, is responsible for leading the team in 3D vision and human analysis. Its technology is widely used in the Top 4 mobile companies in China, APPs both home and abroad in augmented realtity, video sharing and live streaming. He has published several papers on top conferences and journals, e.g. CVPR, AAAI, ECCV and IJCA, including two oral presentations and one spotlight presentation.He has also led the team to achive the 1st place in the competition of Face Identification and Face Verification in Megaface Challenge.
Prior to joining SenseTime, he was a software engineer in Google and has organized the Chinese googler technical forum.
Mr. Qian received his Mphil degree from the Chinese University of Hong Kong, during which time he worked in the Microsoft Research Asia as an intern. He was engaged in the research of the technology of 3D full degree freedom gesture which is the foundation of Kinect and holelens. He obtained his BA degree from the institute for interdisciplinary information sciences of Tsinghua University and was awarded the Excellent Undergraduate of Beijing.

Liu Yu

Dr.Liu Yu is currently working as a vice research director in SenseTime Research. He received his PhD from Multimedia Lab (MMLab), the Chinese University of Hong Kong in 2020, supervised by Prof. Xiaogang Wang. Before that he received bachelor degree in 2016 with best bachelor thesis award. He was the only awardee of Google PhD Fellowship 2019 in the Greater China area.
His research interests include: Artificial General Intelligence, Deep RL and neural network understanding under billions of data. Previously he was also proficient in object detection and face/body analysis (detection, keypoints, attribute, recognition, generation, synthesis).
In recent years he is a reviewer for CVPR, ICCV, NeurIPS, ICLR, AAAI, IJCAI, T-PAMI, IJCV, TCSVT, TIP, PRCV.