Your browser does not support JavaScript!
[Apr-19] Deep Transfer Learning for Visual Data Analysis

Seminar of Institute of Information Systems and Applications

Speaker :

Prof. Y. C. Frank Wang 

Academia Sinica

Topic :

Deep Transfer Learning for Visual Data Analysis

Date :

15:30-17:00 Wednesday 19-Apr-2017

Place :

台達館R107Delta Building R107


Prof. Min Sun



The growing research on machine learning, especially deep learning, has led to many exciting applications and breakthroughs in the areas of computer vision and multimedia. In this talk, I will highlight our research progress in developing deep learning models, which are particular designed for solving cross-domain data analysis problems in different scenarios. Particular applications include domain adaptation, image classification, and multi-label classification will be presented. The above research works and details can be found in our recent publications in CVPR, ICCV, ECCV, and AAAI.


Y.-C. Frank Wang received the B.S. degree in Electrical Engineering from the National Taiwan University, Taipei, Taiwan in 2001. He received the M.S. and Ph.D. degrees in Electrical and Computer Engineering from Carnegie Mellon University, Pittsburgh, PA, USA, in 2004 and 2009, respectively. Dr. Wang joined the Research Center for
Information Technology Innovation (CITI), Academia Sinica, Taiwan, in 2009, where he currently holds the position as an Associate Research Fellow
and also serves as the Deputy Director of CITI. He leads the Multimedia and Machine Learning Laboratory, CITI, and works on research projects of computer vision, pattern recognition, machine learning, and image processing. Dr. Wang serves as Organization, Program Committee Member, and Area Chairs for multiple international conferences or activities, and several of his papers were nominated for the Best Paper Awards at related international conferences such as IEEE ICIP, IEEE ICME and IAPR MVA. In 2013, he was selected among the Outstanding Young Researchers by the National Science Council of Taiwan.

All faculties and students are welcome to join.