SPATIAL WEIGHTED FISHER VECTOR FOR IMAGE RETRIEVAL
Qi,Chengzuo; Shi,Cunzhao; Xu,Jian; Wang,Chunheng; Xiao,Baihua
2017-07
会议名称IEEE International Conference on Multimedia and Expo
页码463 - 468
会议日期10-14 July 2017
会议地点hongkong
摘要
Several recent works interpret convolutional features produced
by deep convolutional neural networks as local descriptors.
Existing high-dimensional aggregation based methods,
e.g., Fisher Vector (FV) obtain inferior performance to pooling
based methods in most situations, and we observe that
it is mainly caused by the ignorance of spatial weights. In
this paper, we propose a novel method named spatial weighted
Fisher Vector (SWFV) to enhance the representation of
FV by injecting the spatial weight map to FV. In addition,
we further analyze the distribution of spatial weights and propose
truncated spatial weighted FV (TSWFV). Experimental
results on two benchmark datasets demonstrate that the two
proposed methods achieve competitive results compared with
other global representation based methods.
关键词Fisher Vector Spatial Weight Convolu-tional Feature
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19582
专题复杂系统管理与控制国家重点实验室_影像分析与机器视觉
作者单位Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China
推荐引用方式
GB/T 7714
Qi,Chengzuo,Shi,Cunzhao,Xu,Jian,et al. SPATIAL WEIGHTED FISHER VECTOR FOR IMAGE RETRIEVAL[C],2017:463 - 468.
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
SPATIAL WEIGHTED FIS(1429KB)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
[Qi,Chengzuo]的文章
[Shi,Cunzhao]的文章
[Xu,Jian]的文章
百度学术
百度学术中相似的文章
[Qi,Chengzuo]的文章
[Shi,Cunzhao]的文章
[Xu,Jian]的文章
必应学术
必应学术中相似的文章
[Qi,Chengzuo]的文章
[Shi,Cunzhao]的文章
[Xu,Jian]的文章
相关权益政策
暂无数据
收藏/分享
文件名: SPATIAL WEIGHTED FISHER VECTOR FOR IMAGE 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。