• 2017 5th ITCDM
    2017 5th ITCDM

    2017/07/18~2017/07/21 5th ITCDM

  • 我們的
    我們的"淡江"年代

    展開大學新生活~!!!

  • 讓我們一起展翅飛翔
    讓我們一起展翅飛翔

    Take your dream. Fly high.... 

人:葉倚任教授(高師大數學系)
                    (Department of Mathematics, National Kaohsiung Normal University)

    題:Domain Adaptation for Visual Classification

    期:1051122日(週二)
    間:1610開始
    點:S433

摘要Abstract

For cross-view action recognition and many real-world visual classification problems, one needs to recognize test data at a particular target domain of interest, while training data are collected at a different source domain. Without eliminating such domain differences, recognition of test data using classifiers trained in the source domain will not be expected to produce satisfactory performance. In this talk, I will introduce several domain adaptation approaches, which are able to learn a common feature space relating cross-domain data. In particular, our proposed method (among one of these approaches) not only aims at matching cross-domain data marginal distributions during adaptation, but also exploits the structure of target domain data and update class-conditional distributions accordingly. Experiments on various cross-domain visual classification tasks would verify the effectiveness and robustness of our proposed method.


Short Bio

Dr. Yi-Ren Yeh received his M.S. and Ph.D. degrees from the Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology in 2006 and 2010, respectively. From August 2008 to May 2009, he was a visiting scholar of CyLab, Carnegie Mellon University, Pittsburgh, USA. He was a postdoctoral research fellow of the Research Center for Information Technology Innovation (CITI) at Academia Sinica and Intel-NTU Connected Context Computing Center at National Taiwan University from 2010 to 2013. He was an assistant professor of Department of Applied Mathematics at Chinese Culture University from 2013 to 2015. He joined Department of Mathematics at National Kaohsiung Normal University as an assistant professor from 2015. His research interests include machine learning, data mining, multimedia content analysis, and data analysis in IoT(Internet of Things).

徵107學年度微積分助教(兼任TA)~即日起至6/8止,歡迎報名。 發佈時間: 2018-05-02, 週三
徵107學年度微積分助教(兼任TA)~ 報名時間:自即日起至107年6月8日止...
[徵助教] 淡江大學數學系誠徵專任約聘助教 發佈時間: 2018-04-25, 週三
一、...
數學學系舉辦1場預研生說明會(預定於107報考入學) 發佈時間: 2018-03-16, 週五
數學學系舉辦1場預研生說明會(預定於107報考入學) 說明: 一、時間:107年3月21日(週三)12:10-13:00...
107.03.12_本學期「微積分」人工加簽作業公告(107.03.12) 發佈時間: 2018-03-12, 週一
本學期「微積分」人工加簽作業公告  (107.3.12)...
107/5/29 李志光 教授 (College of William and Mary)-An invitation to preserver problems 發佈時間: 2018-05-14, 週一
主講人:李志光 教授 (College of William and Mary) 題  目: An invitation to preserver problems  日 ...
107/5/22 洪盟凱 教授 (中央大學數學系)-Global existence of weak solutions to the initial-boundary value problem of Euler-Poisson equations with self-gravitation force in spherically symmetric space-times 發佈時間: 2018-05-14, 週一
主講人:洪盟凱 教授 (中央大學數學系) 題  目:Global existence of weak solutions to the initial-boundary value problem of...
107/5/22 連科雅 (淡江大學數學系博士候選人)-Inverse problems for the boundary value problem with the interior nodal subsets 發佈時間: 2018-05-14, 週一
講  題:Inverse problems for the boundary value problem with the interior nodal subsets 演講者:連科雅...
107/5/15 朱家杰 教授 (清華大學數學系)-Volumetric Variational Problems for Partial Differential Equations on Manifold 發佈時間: 2018-04-30, 週一
主講人:朱家杰 教授 (清華大學數學系) 題  目:Volumetric Variational Problems for Partial Differential  Equations on...
107/5/8 洪斌哲 教授 (東吳大學數學系)-On anticyclotomic exceptional zero conjecture for elliptic curves 發佈時間: 2018-04-30, 週一
主講人:洪斌哲 教授 (東吳大學數學系) 題  目:On anticyclotomic exceptional zero conjecture for elliptic curves 日 ...

活動花絮

  • -archive-262_b68a5b5b.jpg
  • -archive-263_4cdbbd58.jpg
  • -archive-272_28130317.jpg
  • cache.15_83ce35a2.jpg.w560_h374.jpg
  • cache.441_70134d79.jpg.w560_h374.jpg
  • cache.442_e8e94f57.jpg.w560_h374.jpg
  • cache.516_6aa3dda0.jpg.w560_h420.jpg
  • cache.534_556f8006.jpg.w560_h420.jpg
  • cache.535_f1c4d921.jpg.w560_h420.jpg
  • cache.538_681b0470.jpg.w560_h420.jpg
數學是一切知識中的最高形式。—— 柏拉圖