Refereed conference paper presented and published in conference proceedings
香港中文大学研究人员 ( 现职)
汤晓鸥教授 (信息工程学系) |
王晓刚教授 (电子工程学系) |
全文
数位物件识别号 (DOI) http://dx.doi.org/10.1109/ICCV.2013.356 |
引用次数
Web of Sciencehttp://aims.cuhk.edu.hk/converis/portal/Publication/14WOS source URL
Scopushttp://aims.cuhk.edu.hk/converis/portal/Publication/38Scopus source URL
其它资讯
摘要Recent works have shown that facial attributes are useful in a number of applications such as face recognition and retrieval. However, estimating attributes in images with large variations remains a big challenge. This challenge is addressed in this paper. Unlike existing methods that assume the independence of attributes during their estimation, our approach captures the interdependencies of local regions for each attribute, as well as the high-order correlations between different attributes, which makes it more robust to occlusions and misdetection of face regions. First, we have modeled region interdependencies with a discriminative decision tree, where each node consists of a detector and a classifier trained on a local region. The detector allows us to locate the region, while the classifier determines the presence or absence of an attribute. Second, correlations of attributes and attribute predictors are modeled by organizing all of the decision trees into a large sum-product network (SPN), which is learned by the EM algorithm and yields the most probable explanation (MPE) of the facial attributes in terms of the region's localization and classification. Experimental results on a large data set with 22,400 images show the effectiveness of the proposed approach. ? 2013 IEEE.
着者Luo P., Wang X., Tang X.
会议名称2013 http://aims.cuhk.edu.hk/converis/portal/Publication/14th IEEE International Conference on Computer Vision, ICCV 2013
会议开始日01.12.2013
会议完结日08.12.2013
会议地点Sydney, NSW
会议国家澳大利亚
出版年份2013
月份1
日期1
页次2864 - 2871
国际标準书号978http://aims.cuhk.edu.hk/converis/portal/Publication/1479928392
国际标準期刊号1550-5499
语言英式英语
关键词attributes, deep learning, face recognition