模式识别系列讲座
lecture series in pattern recognition
题目：improving image annotation and retrieval with graphical models
报告人：prof. luis enrique sucar
主持人：prof. kaiqi huang
时间：august 12, 2013(monday), 10:00am-12:00am
地点：no.2 conference room (3rd floor), intelligence building
报告摘要（abstract）：
abstract. automatic image annotation and retrieval are two important and difficult problems in computer vision. in this talk i will present our work in using graphical models for improving the results of the basic algorithms in both problems, in particular:
(i) by incorporating spatial relations, (ii) by integrating semantic information, and (iii) by adding user and automatic feedback. experimental results will be presented on the iapr dataset, a segmented and annotated image collection developed by our group.
报告人简介（biography）：
dr. l. enrique sucar is director of research and senior researcher at the department of computer science, instituto nacional de astrofísica, óptica y electrónica (inaoe), puebla, mexico. he has a ph.d. in computing (artificial intelligence), imperial college, university of london, london, u.k. (1988-1992); m.sc. in electrical engineering (computer systems), stanford university, palo alto, ca, u.s.a. (1980-1982); and b. sc. in electronics and communications engineering, instituto tecnológico y de estudios superiores de monterrey (itesm), monterrey, n.l., mexico. (1976-1980). he has been a researcher at the electrical research institute (1982-1993) and professor at itesm cuernavaca (1994-2005). he has been visiting professor at imperial college, london; university of british columbia, canada; and inria, france. he is member of the national research system, level iii; of the mexican academy of science and a senior member of ieee. he has been member of the advisory board for ijcai, and president of the mexican ai society. he is associate editor of several journals, and has been member of the program committee of multiple international conferences. he has supervised 16 ph thesis, directed more than 20 research projects, and published more than 150 papers in journal, books and conference proceedings. his main research interests are in probabilistic graphical models and their application in vision, robotics and biomedicine. for further information see:
|
