Monday, January 11, 2016, 2:30pm to 3:30pm, room F107, INRIA Montbonnot
Seminar by Yan Yan, University of Trento, Italy
Multiple Tasks are Better than One: Multi-task Learning for Head Pose Estimation, Activity Recognition and Event Detection
Machine Learning (ML) and Computer Vision (CV) have been put together during the development of computer vision in the past decade. Nowadays, machine learning is considered as a powerful tool to solve many computer vision problems. Multi- task learning, as one important branch of machine learning, has developed very fast during the past decade. Multi-task learning methods aim to simultaneously learn classification or regression models for a set of related tasks. This typically leads to better models as compared to a learner that does not account for task relationships. The goal of multi-task learning is to improve the performance of learning algorithms by learning classifiers for multiple tasks jointly. This works particularly well if these tasks have some commonality and are generally slightly under-sampled. we will talk about some challenging problems existing in the computer vision area under the multi-task learning framework. At the first glance of a picture, probably some questions naturally presented themselves in your mind. i.e., How do we know where a person is looking at from far-field low-resolution cameras? How do we know what each person is doing? And how do we know what this event is? Is it a ‘Wedding ceremony’ or ‘Flash mob gathering’? In this talk we will answer these questions in detail from the computer vision point of view considering both single and multiple camera setups and from the machine learning point of view, especially under the multi-task learning framework.
Short biography: Yan Yan received the PhD degree in computer science from the University of Trento, Italy, in 2014 and M.S. degree in Pattern Recognition and Intelligent Systems from Shanghai Jiao Tong University, China, in 2010 and M.S. degree in Electrical and Computer Engineering from Georgia Institute of Technology, USA, in 2010. He is currently a research fellow with the MHUG group at the University of Trento, Italy. He was a visiting scholar with Carnegie Mellon University in 2013 and a visiting research fellow with the Advanced Digital Sciences Center (ADSC), UIUC, Singapore in 2015. His research interests include computer vision, machine learning, and multimedia. He has been PC members for several major conferences and reviewers for referred journals in computer vision and multimedia area. He has served as a guest editor in IEEE Transactions on Pattern Analysis and Machine Intelligence. He received the Best Student Paper Award in ICPR 2014 and Best paper Award in ACM Multimedia 2015.
