Key points are not available for this paper at this time.
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 search-based 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.
Fang et al. (Wed,) studied this question.