SIFT Matching with CNN Evidences for Particular Object Retrieval
Zhang Guixuan1,4; Zeng Zhi1; Zhang Shuwu1; Zhang Yuan2; Wu Wanchun3
2017-05-17
发表期刊NEUROCOMPUTING
卷号238期号:238页码:399-409
文章类型Article
摘要Many object instance retrieval systems are typically based on matching of local features, such as SIFT. However, these local descriptors serve as low-level clues, which are not sufficiently distinctive to prevent false matches. Recently, deep convolutional neural networks (CNN) have shown their promise as a semantic-aware representation for many computer vision tasks. In this paper, we propose a novel approach to employ CNN evidences to improve the SIFT matching accuracy, which plays a critical role in improving the object retrieval performance. To weaken the interference of noise, we extract compact CNN representations from a number of generic object regions. Then a query-adaptive method is proposed to choose appropriate CNN evidence to verify each pre-matched SIFT pair. Two different visual matching verification functions are introduced and evaluated. Moreover, we investigate the suitability of fine-tuning the CNN for our proposed approach. Extensive experiments on benchmark dataSets demonstrate the effectiveness of our method for particular object retrieval. Our results compare favorably to the state-of-the-art methods with acceptable memory usage and query time. (C) 2017 Elsevier B.V. All rights reserved.
关键词Particular Object Retrieval Bag-of-words Sift Matching Convolutional Neural Networks
WOS标题词Science & Technology ; Technology
DOI10.1016/j.neucom.2017.01.081
关键词[WOS]NEAREST-NEIGHBOR SEARCH ; IMAGE RETRIEVAL ; SCALE ; SIMILARITY
收录类别SCI
语种英语
项目资助者National Science and Technology Supporting Program of China(2015BAH49F01) ; Key Technology R&D Program of Beijing(D161100005216001)
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000397372100035
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/14307
专题数字内容技术与服务研究中心_新媒体服务与管理技术
作者单位1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
2.Alibaba Grp, Beijing, Peoples R China
3.Chongqing Med Univ, Childrens Hosp, Chongqing, Peoples R China
4.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Zhang Guixuan,Zeng Zhi,Zhang Shuwu,et al. SIFT Matching with CNN Evidences for Particular Object Retrieval[J]. NEUROCOMPUTING,2017,238(238):399-409.
APA Zhang Guixuan,Zeng Zhi,Zhang Shuwu,Zhang Yuan,&Wu Wanchun.(2017).SIFT Matching with CNN Evidences for Particular Object Retrieval.NEUROCOMPUTING,238(238),399-409.
MLA Zhang Guixuan,et al."SIFT Matching with CNN Evidences for Particular Object Retrieval".NEUROCOMPUTING 238.238(2017):399-409.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
SIFT Matching with C(2393KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang Guixuan]的文章
[Zeng Zhi]的文章
[Zhang Shuwu]的文章
百度学术
百度学术中相似的文章
[Zhang Guixuan]的文章
[Zeng Zhi]的文章
[Zhang Shuwu]的文章
必应学术
必应学术中相似的文章
[Zhang Guixuan]的文章
[Zeng Zhi]的文章
[Zhang Shuwu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: SIFT Matching with CNN Evidences for Particular Object Retrieval.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。