ABSTRACT
Points of interest (POIs) are a core component of geographical databases and of location based services. POI acquisition was performed by domain experts but associated costs and access difficulties in many regions of the world reduce the coverage of manually built geographical databases. With the availability of large geotagged multimedia datasets on the Web, a sustained research effort was dedicated to automatic POI discovery and characterization. However, in spite of its practical importance, POI localization was only marginally addressed. To compute POI coordinates an assumption was made that the more data were available, the more precise the localization will be. Here we shift the focus of the process from data quantity to data quality. Given a set of geotagged Flickr photos associated to a POI, close-up classification is used to trigger a spatial clustering process. To evaluate the newly introduced method against different other localization schemes, we create an accurate ground truth. We show that significant localization error reductions are obtained compared to a coordinate averaging approach and to a X-Means clustering scheme.
- M. Ankerst and al. Optics: ordering points to identify the clustering structure. In SIGMOD 1999. Google ScholarDigital Library
- D. J. Crandall and al. Mapping the world's photos. In WWW2009, pages 761--770, 2009. Google ScholarDigital Library
- M. Hall and al. The weka data mining software: an update. SIGKDD Explor. Newsl., 11(1):10--18, 2009. Google ScholarDigital Library
- J. Hays and A. A. Efros. im2gps: estimating geographic information from a single image. In CVPR 2008.Google ScholarCross Ref
- L. S. Kennedy and M. Naaman. Generating diverse and representative image search results for landmarks. In WWW 2008. Google ScholarDigital Library
- D. Pelleg and A. Moore. X-means: Extending k-means with efficient estimation of the number of clusters. In ICML 2000. Google ScholarDigital Library
- A. Rae and al. Mining the web for points of interest. In SIGIR 2012. Google ScholarDigital Library
- T. Rattenbury and al. Towards automatic extraction of event and place semantics from flickr tags. In SIGIR 2007, pages 103--110, 2007. Google ScholarDigital Library
- P. Serdyukov and al. Placing flickr photos on a map. In SIGIR 2009, pages 484--491, 2009. Google ScholarDigital Library
- M. Szummer and R. W. Picard. Indoor-outdoor image classification. In CAIVD 1998. Google ScholarDigital Library
- A. Torralba and A. Oliva. Depth estimation from image structure. IEEE PAMI, 24(9):1226--1238, 2002. Google ScholarDigital Library
Index Terms
- Towards precise POI localization with social media
Recommendations
Mining the web for points of interest
SIGIR '12: Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrievalA point of interest (POI) is a focused geographic entity such as a landmark, a school, an historical building, or a business. Points of interest are the basis for most of the data supporting location-based applications. In this paper we propose to ...
A HITS-based POI recommendation algorithm for location-based social networks
ASONAM '13: Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and MiningLocation-Based Social Networks (LBSNs), (also called as Geo-Social Networks), has been attracting more and more users by providing services that integrate social activities with location information. LBSN systems usually provide support for indicating ...
Modeling locations with social media
AbstractIn this paper we focus on the locations explicit and implicit in users descriptions of their surroundings. We propose a statistical language modeling approach to identifying locations in arbitrary text, and investigate several ways to estimate the ...
Comments