Multiple spatial pooling for visual object recognition
文献类型：期刊论文
| 作者 | Huang, Yongzhen ; Wu, Zifeng; Wang, Liang; Song, Chunfeng
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2014-04-10 |
| 卷号 | 129页码:225-231 |
| 关键词 | Object classification Spatial modeling Multiple pooling |
| 英文摘要 | Global spatial structure is an important factor for visual object recognition but has not attracted sufficient attention in recent studies. Especially, the problems of features' ambiguity and sensitivity to location change in the image space are not yet well solved. In this paper, we propose multiple spatial pooling (MSP) to address these problems. MSP models global spatial structure with multiple Gaussian distributions and then pools features according to the relations between features and Gaussian distributions. Such a process is further generalized into a unified framework, which formulates multiple pooling using matrix operation with structured sparsity. Experiments in terms of scene classification and object categorization demonstrate that MSP can enhance traditional algorithms with small extra computational cost. (C) 2013 Elsevier B.V. All rights reserved. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence |
| 研究领域[WOS] | Computer Science |
| 关键词[WOS] | INSPIRED FEATURE MANIFOLD ; SPARSE REPRESENTATION ; SCENE CLASSIFICATION ; FEATURES |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000332132400027 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/3812]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 作者单位 | Chinese Acad Sci CASIA, Inst Automat, NLPR, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Huang, Yongzhen,Wu, Zifeng,Wang, Liang,et al. Multiple spatial pooling for visual object recognition[J]. NEUROCOMPUTING,2014,129:225-231. |
| APA | Huang, Yongzhen,Wu, Zifeng,Wang, Liang,&Song, Chunfeng.(2014).Multiple spatial pooling for visual object recognition.NEUROCOMPUTING,129,225-231. |
| MLA | Huang, Yongzhen,et al."Multiple spatial pooling for visual object recognition".NEUROCOMPUTING 129(2014):225-231. |
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。