SPATIAL WEIGHTED FISHER VECTOR FOR IMAGE RETRIEVAL

CASIA OpenIR > 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

	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
第一作者单位	中国科学院自动化研究所
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