Region based Image Retrieval with Query-Adaptive Feature Fusion
Zhang, Guixuan; Zhang, Shuwu; Zeng, Zhi; Guan, Hu; Wang, Fangxin
2017
会议名称IEEE International Conference on Image Processing (ICIP)
会议日期17-20 September 2017
会议地点CNCC, Beijing, China
摘要Recently, 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.
关键词Image Retrieval Convolutional Neural Networks Fisher Vector Feature Fusion
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/15411
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Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Zhang, Guixuan,Zhang, Shuwu,Zeng, Zhi,et al. Region based Image Retrieval with Query-Adaptive Feature Fusion[C],2017.
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
0003675.pdf(4449KB)会议论文 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
[Zhang, Shuwu]的文章
[Zeng, Zhi]的文章
百度学术
百度学术中相似的文章
[Zhang, Guixuan]的文章
[Zhang, Shuwu]的文章
[Zeng, Zhi]的文章
必应学术
必应学术中相似的文章
[Zhang, Guixuan]的文章
[Zhang, Shuwu]的文章
[Zeng, Zhi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 0003675.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。