Discovering Geo-Informative Attributes for Location Recognition and Exploration

	Discovering Geo-Informative Attributes for Location Recognition and Exploration
	Fang, Q; Sang, JT; Xu, CS
发表期刊	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
	2014
卷号	11 期号:1 页码:23
摘要	This article considers the problem of automatically discovering geo-informative attributes for location recognition and exploration. The attributes are expected to be both discriminative and representative, which correspond to certain distinctive visual patterns and associate with semantic interpretations. For our solution, we analyze the attribute at the region level. Each segmented region in the training set is assigned a binary latent variable indicating its discriminative capability. A latent learning framework is proposed for discriminative region detection and geo-informative attribute discovery. Moreover, we use user-generated content to obtain the semantic interpretation for the discovered visual attributes. Discriminative and searchbased attribute annotation methods are developed for geo-informative attribute interpretation. The proposed approach is evaluated on one challenging dataset including GoogleStreetView and Flickr photos. Experimental results show that (1) geo-informative attributes are discriminative and useful for location recognition; (2) the discovered semantic interpretation is meaningful and can be exploited for further location exploration; This article considers the problem of automatically discovering geo-informative attributes for location recognition and exploration. The attributes are expected to be both discriminative and representative, which correspond to certain distinctive visual patterns and associate with semantic interpretations. For our solution, we analyze the attribute at the region level. Each segmented region in the training set is assigned a binary latent variable indicating its discriminative capability. A latent learning framework is proposed for discriminative region detection and geo-informative attribute discovery. Moreover, we use user-generated content to obtain the semantic interpretation for the discovered visual attributes. Discriminative and searchbased attribute annotation methods are developed for geo-informative attribute interpretation. The proposed approach is evaluated on one challenging dataset including GoogleStreetView and Flickr photos. Experimental results show that (1) geo-informative attributes are discriminative and useful for location recognition; (2) the discovered semantic interpretation is meaningful and can be exploited for further location exploration.
关键词	Geo-informative Attributes Location Recognition Latent Model
收录类别	SCI
WOS记录号	WOS:000343984800011
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/2823
专题	多模态人工智能系统全国重点实验室_多媒体计算
推荐引用方式 GB/T 7714	Fang, Q,Sang, JT,Xu, CS. Discovering Geo-Informative Attributes for Location Recognition and Exploration[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2014,11(1):23.
APA	Fang, Q,Sang, JT,&Xu, CS.(2014).Discovering Geo-Informative Attributes for Location Recognition and Exploration.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,11(1),23.
MLA	Fang, Q,et al."Discovering Geo-Informative Attributes for Location Recognition and Exploration".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 11.1(2014):23.

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
a19-fang.pdf（1883KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载