Institute of Information Science Academia Sinica
Topic: Recent Advances in Deep Transfer Learning for Visual Analysis
Speaker: Prof. 王鈺強 (Graduate Institute of Communication Engineering, National Taiwan University)
Date: 2019-08-09 (Fri) 10:30 – 12:30
Location: Auditorium106 at IIS new Building
Host: Chu-Song Chen

Abstract:

In this talk, I will talk about what recent developments and progresses in deep learning and transfer learning, and their applications to visual recognition and synthesis. We will introduce our recent CVPR/ECCV/NeurIPS/ICLR/AAAI works on scene understanding, person re-identification, few-shot learning, video summarization, and image translation, which are all based on deep transfer learning. I will also share my experiences in industrial collaboration on the above topics.

 

 


BIO:

Yu-Chiang Frank Wangreceived his PhD and MS degrees in ECE from Carnegie Mellon University in 2009 and 2004, respectively. He obtained his BS degree in EE from National Taiwan University in 2001. Before joining Dept. Electrical Engineering at National Taiwan University as an associate professor in 2017, Dr. Wang joined the Research Center for IT Innovation at Academia Sinica as an Assistant Research Fellow in 2009. With research focuses on computer vision, pattern recognition, and machine learning, he has been working in computer vision, in particular on the topics of robust face recognition and domain adaptation. Dr. Wang was promoted to an Associate Research Fellow in 2013, and also served as a Deputy Director of our center since 2015.

In Aug. 2017, Dr. Wang joined the Department of Electrical Engineering at National Taiwan University as an associate professor. Leading the Vision and Learning Lab at NTU, Dr. Wang focuses on a range of computer vision and deep learning topics, including image segmentation, object recognition, video analysis and summarization. Dr. Wang and his team received the First Place Award at Taiwan Tech Trek by the National Science Council (NSC) of Taiwan in 2011. In 2013 and 2017, he was twice selected as the Outstanding Young Researcher by NSC/MOST (Ministry of Science and Technology). In 2018, his team won the Second Place Award for the research poster presentation at NVIDIA GTC Taiwan.