报告题目：Beyond Deep Recognition: Discovering Visual Patterns in Big Visual Data
Thanks to deep learning, many computer vision tasks nowadays are formulated as the regression problem, from high-level vision tasks such as object detection and semantic segmentation, to middle-level tasks such as structure from motion, and low-level tasks such as image matching and optical flow. Often times one has to rely on huge amounts of annotated training data to succeed in this “curve-fitting” battlefield. However, computer vision can be more than a regression problem. In this talk, I will discuss a complementary yet overlooked problem beyond visual recognition and regression: discovering visual patterns in images and videos. I will discuss our recent work of visual pattern discovery, and explore how to utilize them to better summarize, search, and interpret visual data. Applications in object instance search, object detection, action recognition, and video summarization will also be discussed.
Junsong Yuan is currently an Associate Professor and Director of Visual Computing Lab of CSE Department, State University of New York at Buffalo. Before that he was an Associate Professor at Nanyang Technological University (NTU), Singapore. He received his Ph.D. from Northwestern University, M.Eng. from National University of Singapore, and B.Eng. from Huazhong University of Science and Technology. He is currently Senior Area Editor of Journal of Visual Communications and Image Representation (JVCI), Associate Editor of IEEE Trans. on Image Processing (T-IP) and IEEE Trans. on Circuits and Systems for Video Technology (T-CSVT), and served as a Guest Editor for International Journal of Computer Vision (IJCV). He was Program Co-Chair of ICME'18 and Area Chair of CVPR, ACM MM, ICIP, ICPR, ACCV, WACV etc. He received Best Paper Award from IEEE Trans. on Multimedia, Nanyang Assistant Professorship from NTU, and Outstanding EECS Ph.D. Thesis award from Northwestern University. He is a Fellow of International Association of Pattern Recognition (IAPR).