Show simple item record

dc.contributor.authorFang, Su-Wenzh_CN
dc.contributor.authorQu, Yan-Yunzh_CN
dc.contributor.authorChen, Chengzh_CN
dc.contributor.authorSong, Shu-Yangzh_CN
dc.contributor.author曲延云zh_CN
dc.date.accessioned2015-07-22T02:39:49Z
dc.date.available2015-07-22T02:39:49Z
dc.date.issued2012zh_CN
dc.identifier.citationProceedings - International Conference on Machine Learning and Cybernetics, 2012,3:1111-1117zh_CN
dc.identifier.other20130115851396zh_CN
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/86791
dc.descriptionConference Name:2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012. Conference Address: Xian, Shaanxi, China. Time:July 15, 2012 - July 17, 2012.zh_CN
dc.descriptionHebei University; IEEE Systems, Man and Cybernetics Society; Chongqing University; South China University of Technology; Hong Kong Baptist Universityzh_CN
dc.description.abstractThis paper aims at learning discriminative visual words for object localization. These visual words are different from those learned from the generic object recognition which usually contain the negative visual words located on the background. For the purpose of object localization, the approach requires that the positive discriminative visual words mostly lie in the foreground object and the negative ones lie in the background. We firstly rank the visual words by the following three methods: the SVM classifier, the foreground likelihood ratio and the mutual information. Then, we integrate the three ranking results in an optimal combinational way and select the discriminative visual words by maximizing the object hit rate. Moreover, a coarse-to-fine detection framework to locate the object is designed. In the first stage, a branch-and-bound scheme combined with the discriminative visual words is implemented to find candidate object regions. In the second stage, a sliding window classifier is used to find the object location. The experimental results demonstrate that the approach is effective and efficient, and superior to Efficient Subwindow Search scheme. 漏 2012 IEEE.zh_CN
dc.language.isoen_USzh_CN
dc.publisherIEEE Computer Societyzh_CN
dc.source.urihttp://dx.doi.org/10.1109/ICMLC.2012.6359510zh_CN
dc.subjectCascades (fluid mechanics)zh_CN
dc.subjectClassifierszh_CN
dc.subjectCyberneticszh_CN
dc.subjectFeature extractionzh_CN
dc.subjectLearning systemszh_CN
dc.titleObject localization based on discriminative visual wordszh_CN
dc.typeConferencezh_CN


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record