Image classification by search with explicitly and implicitly semantic representations | |
Zhang, Chunjie1,2; Zhu, Guibo3; Huang, Qingming1,2,4; Tian, Qi5 | |
刊名 | INFORMATION SCIENCES |
2017-01-10 | |
卷号 | 376期号:0页码:125-135 |
关键词 | Explicit Representation Implicit Representation Semantic Modeling Image Classification |
DOI | 10.1016/j.ins.2016.10.019 |
文献子类 | Article |
英文摘要 | Image classification refers to the task of automatically classifying the categories of images based on the contents. This task is typically solved using visual features with the histogram based classification scheme. Although effective, this strategy has two drawbacks. On one hand, histogram based representation often disregards the object layout which is very important for classification. On the other hand, visual features are unable to fully separate different images due to the semantic gap. To solve these two problems, in this paper, we propose a novel image classification method by explicitly and implicitly representing the images with searching strategy. First, to make use of object layouts, we randomly select a number of regions and then use these regions for image representations. Second, we generate the explicitly semantic representations using a number of pre-learned semantic models. Third, we measure the visual similarities with the Internet images and use the text information for implicitly semantic representations. Since Internet images are contaminated with noise, the resulting representations only implicitly reflect the contents of images. Finally, both the explicitly and implicitly semantic representations are jointly modeled for image classifications by training bi-linear classifiers. We evaluate the effectiveness of the proposed image classification by search with explicitly and implicitly semantic representations method (EISR) on the Scene-15 dataset, the MIT-Indoor dataset, the UIUC-Sports dataset and the PASCAL VOC 2007 dataset. The experimental results prove the usefulness of the proposed method. (C) 2016 Elsevier Inc. All rights reserved. |
WOS关键词 | SCENE CLASSIFICATION ; LOCAL FEATURES ; LOW-RANK ; RECOGNITION ; CATEGORIZATION ; ANNOTATION ; SPACE |
WOS研究方向 | Computer Science |
语种 | 英语 |
WOS记录号 | WOS:000388545100009 |
资助机构 | National Natural Science Foundation of China(61303154) |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/13351] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
作者单位 | 1.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100864, Peoples R China 3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intell Info Proc, Beijing 100190, Peoples R China 5.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA |
推荐引用方式 GB/T 7714 | Zhang, Chunjie,Zhu, Guibo,Huang, Qingming,et al. Image classification by search with explicitly and implicitly semantic representations[J]. INFORMATION SCIENCES,2017,376(0):125-135. |
APA | Zhang, Chunjie,Zhu, Guibo,Huang, Qingming,&Tian, Qi.(2017).Image classification by search with explicitly and implicitly semantic representations.INFORMATION SCIENCES,376(0),125-135. |
MLA | Zhang, Chunjie,et al."Image classification by search with explicitly and implicitly semantic representations".INFORMATION SCIENCES 376.0(2017):125-135. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论