Boosted random contextual semantic space based representation for visual recognition
详细信息 查看全文
- 作者：Chunjie Zhanga ; zhangcj@ucas.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Zhe Xuea ; xuezhe10@mails.ucas.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Xiaobin Zhu ; b ; brucezhucas@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Huanian Wangc ; huanianwang06@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Qingming Huanga ; d ; qmhuang@jdl.ac.cn" class="auth_mail" title="E-mail the corresponding author ; Qi Tiane ; qitian@cs.utsa.edu" class="auth_mail" title="E-mail the corresponding author
- 关键词：Pattern recognition ; Image processing ; Visual representation
- 刊名：Information Sciences
- 出版年：2016
- 出版时间：10 November 2016
- 年：2016
- 卷：369
- 期：Complete
- 页码：160-170
- 全文大小：833 K
文摘
- •
We propose an image representation method using boosted random contextual semantic spaces.
- •
The proposed BRCSS can alleviate the semantic gap by using semantic space based image representation.
- •
BRCSS uses the visual representation of images in an iterative way with random sampling and re-weighting.
- •
Experimental results demonstrate the effectiveness and efficiency of the proposed method.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |