[109.11.30]Efficient Detection of Human Object Interactions


講 題:
Efficient Detection of Human Object Interactions

This talk will focus on how human object interactions can be detected using deep neural networks. We will discuss how to detect if a luggage is either taken by a human or put down by a human. These kinds of detections are especially useful for protecting the safety of passengers on public transportations such as at airports and stations where unattended luggage poses threats to human safety. Further, luggage are also lost in large numbers causing huge financial losses, our methods can be used to find lost luggage more efficiently. We achieve high accuracy and efficiency in such detections.

Pao-Ann Hsiung, Ph.D., received B.S. in Mathematics and Ph.D. in Electrical Engineering from the National Taiwan University, Taiwan, in 1991 and 1996, respectively. He is currently a full professor in the Department of Computer Science and Information Engineering, the Director of Smart Living Technology Research Center, Vice Director of the Taiwan-India Joint Research Center on AI at Indian Institute of Technology (IIT) Ropar, India and the National Chung Cheng University (CCU), Taiwan. He was the Department Chair from August 2011 to January 2016 and the Dean of International Affairs from February 2016 to July 2017. He was also the Director General of the Intelligence Technology Department, Chiayi City Government (嘉義市政府智慧科技處處長) in 2018. He helped the Chiayi City to obtain the TOP7 in the ICF Global Smart City Competition. He has also helped Chiayi City to obtain a funding of more than 300 million Taiwan dollars in the year 2018. He has published more than 287 papers in international journals and conferences. He was the recipient of the 2010 CCU Outstanding Research Award, the 2001 ACM Taipei Chapter Kuo-Ting Li Young Researcher, and the 2004 CCU Young Scholar Research Award. Dr. Hsiung is an IET fellow, a senior member of the IEEE and the ACM, and a life member of the IICM. His main research interests include deep learning, smart cyber-physical systems, reconfigurable computing, smart traffic optimization, and smart grid design. He can be contacted at pahsiung@csie.io.