Boosted random contextual semantic space based representation for visual recognition
文献类型：期刊论文
| 作者 | Chunjie Zhang ; Zhe Xue; Xiaobin Zhu; Huanian Wang; Qingming Huang; Qi Tian
|
| 刊名 | Information Sciences
 |
| 出版日期 | 2016 |
| 期号 | 369页码:160-170 |
| 关键词 | Pattern Recognition Image Processing Visual Representation |
| 英文摘要 | Visual information has been widely used for image representation. Although proven very effective, the visual representation lacks explicit semantics. However, how to generate a proper semantic space for image representation is still an open problem that needs to be solved. To jointly model the visual and semantic representations of images, we pro- pose a boosted random contextual semantic space based image representation method. Images are initially represented using local feature’s distribution histograms. The semantic space is generated by randomly selecting training images. Images are then mapped into the semantic space accordingly. Semantic context is explored to model the correlations of different semantics which is then used for classification. The classification results are used to re-weight training images in a boosted way. The re-weighted images are used to construct new semantic space for classification. In this way, we are able to jointly consider the visual and semantic information of images. Image classification experiments on several public datasets show the effectiveness of the proposed method. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/15430]  |
| 专题 | 自动化研究所_类脑智能研究中心 |
| 推荐引用方式 GB/T 7714 | Chunjie Zhang,Zhe Xue,Xiaobin Zhu,et al. Boosted random contextual semantic space based representation for visual recognition[J]. Information Sciences,2016(369):160-170. |
| APA | Chunjie Zhang,Zhe Xue,Xiaobin Zhu,Huanian Wang,Qingming Huang,&Qi Tian.(2016).Boosted random contextual semantic space based representation for visual recognition.Information Sciences(369),160-170. |
| MLA | Chunjie Zhang,et al."Boosted random contextual semantic space based representation for visual recognition".Information Sciences .369(2016):160-170. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。