QQ客服 官方微博 反馈留言

	ROBUST FISHER CODES FOR LARGE SCALE IMAGE RETRIEVAL
	Lin, Jie ; Duan, Ling-Yu ; Huang, Tiejun ; Gao, Wen
	2013
关键词	Fisher kernel local descriptors aggregation large scale visual search
英文摘要	Fisher vectors (FV) have shown great advantages in large scale visual search. However, traditional FV suffers from noisy local descriptors, which may deteriorate the FV discriminative power. In this paper, we propose a robust Fisher vectors (RFV). To fulfill fast search and light storage over a large scale image dataset, we employ a simple binarization method to compress RFV to generate compact robust Fisher codes (RFC). Extensive comparison experiments on benchmark datasets have shown that both RFV and RFC outperforms the state-of-the-art performance. The scalability of RFC has been validated on a dataset of over 1 million images as well.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000329611501139&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Acoustics; Engineering, Electrical & Electronic; EI; CPCI-S(ISTP); 7
语种	英语
DOI标识	10.1109/ICASSP.2013.6637904
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/292551]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Lin, Jie,Duan, Ling-Yu,Huang, Tiejun,et al. ROBUST FISHER CODES FOR LARGE SCALE IMAGE RETRIEVAL. 2013-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。