CASIA OpenIR  > 数字内容技术与服务研究中心  > 版权智能与文化计算
Region based Image Retrieval with Query-Adaptive Feature Fusion
Zhang, Guixuan; Zhang, Shuwu; Zeng, Zhi; Guan, Hu; Wang, Fangxin
Conference NameIEEE International Conference on Image Processing (ICIP)
Conference Date17-20 September 2017
Conference PlaceCNCC, Beijing, China
AbstractRecently, image representation based on convolutional neural network (CNN) becomes more popular than SIFT based feature, such as Fisher vector (FV). However, which of the two works better for image retrieval is not entirely clear yet. In this paper, we propose to fuse CNN and FV to incorporate the advantages of both features for image retrieval. We extract CNN feature and FV from multi-scale regions, which makes the representation more robust to image noise. Then a query-adaptive feature fusion method is proposed, which is used jointly with 2-D inverted index under the framework of bag-of-words. Moreover, we make an evaluation of different CNN feature extraction methods for the region based method. Extensive experiments on four benchmark datasets demonstrate the effectiveness of our method with efficiency in both time cost and memory usage.
KeywordImage Retrieval Convolutional Neural Networks Fisher Vector Feature Fusion
Document Type会议论文
AffiliationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhang, Guixuan,Zhang, Shuwu,Zeng, Zhi,et al. Region based Image Retrieval with Query-Adaptive Feature Fusion[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
0003675.pdf(4449KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Guixuan]'s Articles
[Zhang, Shuwu]'s Articles
[Zeng, Zhi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Guixuan]'s Articles
[Zhang, Shuwu]'s Articles
[Zeng, Zhi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Guixuan]'s Articles
[Zhang, Shuwu]'s Articles
[Zeng, Zhi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 0003675.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.