中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Instance-level object retrieval via deep region CNN

文献类型：期刊论文

作者Min, Weiqing2; Mei, Shuhuan2,3; Duan, Hua3; Jiang, Shuqiang1,2
刊名MULTIMEDIA TOOLS AND APPLICATIONS
出版日期2019-05-01
卷号78期号:10页码:13247-13261
关键词Faster R-CNN Deep learning Instance-level object retrieval Instre
ISSN号1380-7501
DOI10.1007/s11042-018-6427-1
英文摘要Instance retrieval is a fundamental problem in the multimedia field for its various applications. Since the relevancy is defined at the instance level, it is more challenging comparing to traditional image retrieval methods. Recent advances show that Convolutional Neural Networks (CNNs) offer an attractive method for image feature representations. However, the CNN method extracts features from the whole image, thus the extracted features contain a large amount of background noisy information, leading to poor retrieval performance. To solve the problem, this paper proposed a deep region CNN method with object detection for instance-level object retrieval, which has two phases, i.e., offline Faster R-CNN training and online instance retrieval. First, we train a Faster R-CNN model to better locate the region of the objects. Second, we extract the CNN features from the detected object image region and then retrieve relevant images based on the visual similarity of these features. Furthermore, we utilized three different strategies for feature fusing based on the detected object region candidates from Faster R-CNN. We conduct the experiment on a large dataset: INSTRE with 23,070 object images and additional one million distractor images. Qualitative and quantitative evaluation results have demonstrated the advantage of our proposed method. In addition, we conducted extensive experiments on the Oxford dataset and the experimental results further validated the effectiveness of our proposed method.
资助项目National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61322212] ; National Natural Science Foundation of China[61602437] ; National Natural Science Foundation of China[61672497] ; National Natural Science Foundation of China[61472229] ; National Natural Science Foundation of China[61202152] ; Beijing Municipal Commission of Science and Technology[D161100001816001] ; Beijing Natural Science Foundation[4174106] ; Lenovo Outstanding Young Scientists Program ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-notch Young Professionals ; China Postdoctoral Science Foundation[2016M590135] ; China Postdoctoral Science Foundation[2017T100110] ; Science and Technology Development Fund of Shandong Province of China[2016ZDJS02A11] ; Science and Technology Development Fund of Shandong Province of China[ZR2017MF027] ; Taishan Scholar Climbing Program of Shandong Province ; SDUST Research Fund[2015TDJH102]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000471654900028
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/4183]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Duan, Hua
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
3.Shandong Univ Sci & Technol, Coll Math & Syst Sci, Qingdao 266590, Shandong, Peoples R China
推荐引用方式
GB/T 7714		 Min, Weiqing,Mei, Shuhuan,Duan, Hua,et al. Instance-level object retrieval via deep region CNN[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2019,78(10):13247-13261.
APA Min, Weiqing,Mei, Shuhuan,Duan, Hua,&Jiang, Shuqiang.(2019).Instance-level object retrieval via deep region CNN.MULTIMEDIA TOOLS AND APPLICATIONS,78(10),13247-13261.
MLA Min, Weiqing,et al."Instance-level object retrieval via deep region CNN".MULTIMEDIA TOOLS AND APPLICATIONS 78.10(2019):13247-13261.

入库方式： OAI收割

来源：计算技术研究所

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。