報告題目：多視角學(xué)習(xí)進(jìn)展綜述
報告人：陶大程( Dacheng Tao)教授，IEEE/IAPR/SPIE Fellow
單位：悉尼科技大學(xué)
報告時間：2016年9月17日(周六)上午10:30-11:30
報告地點：逸夫樓408會議室
報告摘要：
In recent years, many algorithms for learning from multi-view data by considering the diversity of different views have been proposed. These views may be obtained from multiple sources or different feature subsets. For example, a person can be identified by face, fingerprint, signature or iris with information obtained from multiple sources, while an image can be represented by its color or texture features, which can be seen as different feature subsets of the image. In this talk, we will organize the similarities and differences between a wide variety of multi-view learning approaches, highlight their limitations, and then demonstrate the basic fundamentals for the success of multi-view learning. The thorough investigation on the view insufficiency problem and the in-depth analysis on the influence of view properties (consistence and complementarity) will be beneficial for the continuous development of multi-view learning.
報告人簡介：
陶大程教授是信息科學(xué)領(lǐng)域著名學(xué)者，IEEE/IAPR/SPIE等國際著名學(xué)會會士，現(xiàn)就職于悉尼科技大學(xué)量子計算與智能系統(tǒng)中心。陶大程教授致力于計算機(jī)視覺、數(shù)據(jù)挖掘、機(jī)器學(xué)習(xí)等領(lǐng)域的研究，在IEEE TPAMI、TNNLS、TKDE、TIP、JMLR、IJCV、ICML、NIPS、CVPR、ECCV、ICCV、ICDM、SIGKDD等國際頂尖學(xué)術(shù)期刊和會議上發(fā)表論文超過兩百篇，并獲得IEEE ICDM07、ICDM13、ICDM14 10-year highest impact paper等多篇最佳論文/最佳學(xué)生論文/最有影響力論文獎項。陶大程教授亦是Australian Scopus-Eureka Prize(2015)、ACS Gold Disruptor Award(2015)、UTS Vice-Chancellor’s Medal for Exceptional Research(2015)等澳大利亞國家、學(xué)會和高校學(xué)術(shù)獎項的獲得者。
太陽集團(tuán)tyc5997
TOP
