CASIA OpenIR  > 智能感知与计算研究中心
MFC: A Multi-scale Fully Convolutional Approach for Visual Instance Retrieval
Hao, Jiedong1,2; Wang, Wei1; Dong, Jing1; Tan, Tieniu1
2017-09
Conference Name2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
Conference Date10-14 July 2017
Conference PlaceHong Kong
AbstractPrevious work has shown that feature maps of deep convolutional neural networks (CNNs) can be interpreted as feature representation of an image. Image features aggregated from these feature maps have achieved steady progress in terms of performances on visual instance retrieval tasks in recent years. The key to the success of such methods is feature representation. Inthispaper,westudyhowtorepresentanimage using discriminative features. We demonstrate first that image size is an important factor which affects the performance of instance retrieval but has not been thoroughly discussed in previous work. Based on experimental evaluations, we propose a multi-scale fully convolutional (MFC) approach to encode the image efficiently and effectively. The proposed method is simple to implement, which does not employ sophisticated post-processing techniques such as query expansion, yet shows promising results on four public datasets. 
KeywordVisual Instance Retrieval Image Resizing Strategy Multi-scale Representation Fully Convolutional Neural Network
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20992
Collection智能感知与计算研究中心
Corresponding AuthorDong, Jing
Affiliation1.中国科学院自动化研究所智能感知与计算研究中心
2.中国科学院大学
First Author Affilication中国科学院自动化研究所
Corresponding Author Affilication中国科学院自动化研究所
Recommended Citation
GB/T 7714
Hao, Jiedong,Wang, Wei,Dong, Jing,et al. MFC: A Multi-scale Fully Convolutional Approach for Visual Instance Retrieval[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
ICME-w53.pdf(922KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hao, Jiedong]'s Articles
[Wang, Wei]'s Articles
[Dong, Jing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hao, Jiedong]'s Articles
[Wang, Wei]'s Articles
[Dong, Jing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hao, Jiedong]'s Articles
[Wang, Wei]'s Articles
[Dong, Jing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ICME-w53.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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