Geotagged photos of users on social media site, i.e., Flickr provide plentiful location-based data, which has been exploited for location-based services, such as mapping geotags to places (Kennedy et al. 2007), and recommendation of personalized landmarks (Shi et al. 2011). As users' preferences to visit a location or multiple locations in a certain sequence could be affected by their current temporal, and weather context. Existing methods addressed queries either with free of context constraints or with a few dimensions of context. This paper considers the problem of mining context-aware significant semantic travel sequences from geotagged photos.
展开▼