Spatial modeling via feature co-pooling and SG grafting
文献类型:期刊论文
作者 | Liu, Feng1![]() ![]() ![]() |
刊名 | NEUROCOMPUTING
![]() |
出版日期 | 2014-09-02 |
卷号 | 139页码:415-422 |
关键词 | Object classification Spatial modeling Feature selection |
英文摘要 | Spatial information is an important cue for visual object analysis. Various studies in this field have been conducted. However, they are either too rigid or too fragile to efficiently utilize such information. In this paper, we propose to model the distribution of objects' local appearance patterns by using their co-occurrence at different spatial locations. In order to represent such a distribution, we propose a flexible framework called spatial feature co-pooling, with which the relations between patterns are discovered. As the final representation resulted from our framework is of high dimensionality, we propose a semi-greedy (SG) grafting algorithm to select the most discriminative features. Experimental results on the CIFAR 10, UIUC Sports and VOC 2007 datasets show that our method is effective and comparable with the state-of-art algorithms. (C) 2014 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] | IMAGE FEATURES ; CLASSIFICATION ; OBJECT |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000337661800038 |
源URL | [http://ir.ia.ac.cn/handle/173211/3810] ![]() |
专题 | 自动化研究所_智能感知与计算研究中心 |
作者单位 | 1.Southeast Univ, Sch Automat, Nanjing 210096, Jiangsu, Peoples R China 2.Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Feng,Huang, Yongzhen,Wang, Liang,et al. Spatial modeling via feature co-pooling and SG grafting[J]. NEUROCOMPUTING,2014,139:415-422. |
APA | Liu, Feng,Huang, Yongzhen,Wang, Liang,Yang, Wankou,&Sun, Changyin.(2014).Spatial modeling via feature co-pooling and SG grafting.NEUROCOMPUTING,139,415-422. |
MLA | Liu, Feng,et al."Spatial modeling via feature co-pooling and SG grafting".NEUROCOMPUTING 139(2014):415-422. |
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。