Abstract
Geo-tagged photos of Point of Interest (POI) have played a vital role in many location-based applications. It is of importance to extract relevant geo-tagged photos to build an adequate collection of geo-tagged photos for the POI. This paper proposes a novel approach to extract relevant photos for POI from social media without using visual analysis. In our approach, we apply survival analysis to estimate the probability of existing relevant geo-tagged photos which has the POI name in title or tags or description, based on a radius distance from the POI location. Then, we use distinctive tags between the POI and its neighbor POIs to extract other relevant geo-tagged photos within a specific distance inside of which the existent probability of relevant geo-tagged photos is considerable. We present the effectiveness of our method on a case study with two POIs using publicly available data from Flickr.KeywordsSurvival analysisPOIGeo-tagged photosSocial mediaFlickr
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
