Topic:Learning to 'Put yourself in someone's shoes'
Reporter：Prof. Jianbo Shi
Time:2:30-4:00 p.m., April 18th, 2019
Site:The New Conference Hall, School of Computer Science, NPU
Host:Prof. Ying Li
Inviter:Prof. Yanning Zhang
We construct a computational model that integrates object-human, and scene-social affordance into various prediction tasks using active first-person real-world observations. As a large part of our approach is unsupervised, the continuous streams of real-life data allow us to construct and valid our ecological visual perceptual models. A fundamental driving force behind our theme is the recognition that humans are still the best in carrying out many of the complex and un-experienced tasks. By understanding how humans’ actions from different (including his/her own) perspective, we learn a diverse commons sense model of affordance.
Introduction of the Reporter:
Jianbo Shi is a professor of Computer and Information Science at the University of Pennsylvania, where he served as Graduate Group Chair. He studied Computer Science and Mathematics as an undergraduate at Cornell University where he received his B.A. degrees. He received his Ph.D. degree in Computer Science from University of California at Berkeley. He was a research faculty at The Robotics Institute at Carnegie Mellon University before joining the faculty of the University of Pennsylvania.
He has made fundamental contributions to computer vision and machine learning on image segmentation, motion tracking, and data clustering. He was awarded for IEEE Longuet-Higgins Prize for ‘Fundamental contributions in Computer Vision'. According to Google Scholar, his work has been cited over 35,000 times. His current research focuses on first-person vision, human behavior analysis and image recognition-segmentation. His other research interests include image/video retrieval, 3D vision, and vision based desktop computing. His long-term interests center around a broader area of machine intelligence, he wishes to develop a "visual thinking" module that allows computers not only to understand the environment around, but also to achieve cognitive abilities such as machine memory and learning.
He served as an associate editor for IEEE PAMI, and area chairs of CVPR, ICCV, ECCV, NIPS, ICML. He has been engaged in education efforts in China, and co-founded the 1st Sino-US summer school on Vision, Learning, and Pattern Recognition (VLPR).