Filters








659 Hits in 5.4 sec

Exploiting Flickr Tags and Groups for Finding Landmark Photos [chapter]

Rabeeh Abbasi, Sergey Chernov, Wolfgang Nejdl, Raluca Paiu, Steffen Staab
2009 Lecture Notes in Computer Science  
In this paper we propose a new method to identify landmark photos using tags and social Flickr groups.  ...  Many people take pictures of different city landmarks and post them to photo-sharing systems like Flickr. They also add tags and place photos in Flickr groups, created around particular themes.  ...  Acknowledgments: We would like to thank Bhaskar Mehta who contributed on the early stages of this work, as well as Klaas Dellschaft for providing the datasets.  ... 
doi:10.1007/978-3-642-00958-7_62 fatcat:23mw5fwfhnh3dpvyyxqindsnqy

A Survey of Geo-tagged Multimedia Content Analysis within Flickr [chapter]

Evaggelos Spyrou, Phivos Mylonas
2014 IFIP Advances in Information and Communication Technology  
and recommendations based on pre-processed collaborative geo-tagged photos, resulting into more efficient, optimized search results.  ...  It further specializes its focus by providing an overview of current state-of-the-art techniques with respect to geo-tagged content access, processing and manipulation within the popular Flickr social  ...  [10] identified landmarks using tags and Flickr groups, without exploiting geospatial information.  ... 
doi:10.1007/978-3-662-44722-2_14 fatcat:ikhug3ptc5honpl3djdeb4srs4

An Overview of Flickr Challenges and Research Opportunities

Evaggelos Spyrou, Phivos Mylonas
2014 2014 9th International Workshop on Semantic and Social Media Adaptation and Personalization  
It is rather true that nowadays diversity and a potential for growth characterize the field of popular social networks like Flickr.  ...  Some historical facts of its origin are presented, followed by a review of its digital photo sharing and tagging capabilities, focusing on the most popular related research fields, like travel applications  ...  But why do people upload in common view and moreover tag their photos? Angus and Thelwall [11] investigated the main motivations for using Flickr and for tagging photos.  ... 
doi:10.1109/smap.2014.19 dblp:conf/smap/SpyrouM14 fatcat:muq47hk4arcoligdagxkwfvaka

GuideMe! The World of sights in your pocket

Sergej Zerr, Kerstin Bischoff, Sergey Chernov
2011 2011 IEEE 27th International Conference on Data Engineering  
Web 2.0 applications are a rich source of multimedia resources, that describe sights, events, whether conditions, traffic situations and other relevant objects along the user's route.  ...  Our method for extracting landmark information from Web 2.0 exploits tags and social groups from Flickr. The details of the landmark tags extraction can be found in [5] .  ...  For the current demonstration we used about 50.000 photos from Flickr groups about landmarks and 100.000 photos from groups about other topics.  ... 
doi:10.1109/icde.2011.5767953 dblp:conf/icde/ZerrBC11 fatcat:lr7m6pt5fjabnhdrv5prnhk7vu

From Tags to Trends: A First Glance at Social Media Content Dynamics [chapter]

Evaggelos Spyrou, Phivos Mylonas
2012 IFIP Advances in Information and Communication Technology  
By postprocessing them, we select the most appropriate tags that are able to describe landmarks and events occurring within these places of interest and examine their temporal dynamics over a long period  ...  In this paper we analyze user-generated photos uploaded to Flickr 1 in order to extract meaningful semantic trends covering specific geographical areas of interest.  ...  [5] identify landmarks using tags and Flickr groups, without exploiting geospatial information, aiming to find relevant landmark-related tags, whereas the work presented in [6] analyzes tags associated  ... 
doi:10.1007/978-3-642-33412-2_44 fatcat:isi7yxfhlvguxiss3qojwcscby

Learning Landmarks by Exploiting Social Media [chapter]

Chia-Kai Liang, Yu-Ting Hsieh, Tien-Jung Chuang, Yin Wang, Ming-Fang Weng, Yung-Yu Chuang
2010 Lecture Notes in Computer Science  
Photographs relevant to each landmark tag were retrieved from Flickr and distinctive visual features were extracted from them.  ...  Association analysis is used to find the containment relationship between landmark tags and other geographic names, thus forming a geographic hierarchy.  ...  For each landmark, we manually examined and selected at least 500 Flickr photos that indeed capture the landmark structure.  ... 
doi:10.1007/978-3-642-11301-7_23 fatcat:bp35iyyq35b63ee2cokxas36xi

Analyzing Flickr metadata to extract location-based information and semantically organize its photo content

Evaggelos Spyrou, Phivos Mylonas
2016 Neurocomputing  
We then cluster photos taken within the box based on their geo-tagging metadata information (i.e., their latitude and longitude information) and divide large areas into smaller groups of fixed size, which  ...  By post-processing the latter, we are then able to rank them and thus select the most appropriate tags that describe landmarks and other places of interest, as well as events occurring within these places  ...  [1] identify landmarks using tags and Flickr groups, without exploiting geospatial information, aiming to find relevant landmark-related tags, whereas the work presented in [4] analyzes tags associated  ... 
doi:10.1016/j.neucom.2014.12.104 fatcat:w6kq7ckywfhpbgxeek7f5sqlmy

Placing User-Generated Photo Metadata on a Map

Evangelos Spyrou, Phivos Mylonas
2011 2011 Sixth International Workshop on Semantic Media Adaptation and Personalization  
In this paper we analyze large user photo collections from Flickr in order to select the most appropriate tags to describe a geographical area.  ...  We are then able to rank them and select the most appropriate that are able to describe landmarks and other places of interest that are contained within.  ...  [1] identify landmarks using tags, Flickr groups without exploiting geospatial information.  ... 
doi:10.1109/smap.2011.16 dblp:conf/smap/SpyrouM11 fatcat:klxpu77nnzbkdeyuxg77dhanby

Research and applications on georeferenced multimedia: a survey

Yan-Tao Zheng, Zheng-Jun Zha, Tat-Seng Chua
2010 Multimedia tools and applications  
In recent years, the emergence of georeferenced media, like geotagged photos, on the Internet has opened up a new world of possibilities for geographic related research and applications.  ...  world, and (4) estimating geographic location of a photo.  ...  The canonical photo selection is then cast to finding the most salient photo out of a group of visually similar ones.  ... 
doi:10.1007/s11042-010-0630-z fatcat:5andae7vyraahn3xaqc25x7dui

Extracting Touristic Information from Online Image Collections

E. Ardizzone, F. Di Miceli, M. La Cascia, G. Mazzola
2012 2012 Eighth International Conference on Signal Image Technology and Internet Based Systems  
Flickr).  ...  with a reasonable number of touristic landmarks.  ...  User tags can be exploited as an additional source for spatio-temporal discrimination between images, and they can enrich the landmark detection techniques.  ... 
doi:10.1109/sitis.2012.77 dblp:conf/sitis/ArdizzoneMCM12 fatcat:gvlyytghwbefdn2adz72nw7hti

Social multimedia: highlighting opportunities for search and mining of multimedia data in social media applications

Mor Naaman
2010 Multimedia tools and applications  
In recent years, various Web-based sharing and community services such as Flickr and YouTube have made a vast and rapidly growing amount of multimedia content available online.  ...  These collections present, at once, new challenges and exciting opportunities for multimedia research. This article presents an approach for "social multimedia" applications.  ...  Acknowledgements The author would like to acknowledge the contributions of his colleagues and interns at Yahoo!  ... 
doi:10.1007/s11042-010-0538-7 fatcat:4rolpe4c35gbdhgrsvowywao4i

Mapping the world's photos

David J. Crandall, Lars Backstrom, Daniel Huttenlocher, Jon Kleinberg
2009 Proceedings of the 18th international conference on World wide web - WWW '09  
We find that visual and temporal features improve the ability to estimate the location of a photo, compared to using just textual features.  ...  We then study the interplay between this structure and the content, using classification methods for predicting such locations from visual, textual and temporal features of the photos.  ...  For the classifiers that use only textual tags, the improvement is small (though statistically significant, at p < 0.00001): many Flickr users appear to label groups of consecutive photos with the same  ... 
doi:10.1145/1526709.1526812 dblp:conf/www/CrandallBHK09 fatcat:tkxiyqqth5evdave2plygueabu

Discovering Geo-Informative Attributes for Location Recognition and Exploration

Quan Fang, Jitao Sang, Changsheng Xu
2014 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
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  ...  This results in 6,111 photos for GoogleStreetView and 3,501 photos for Flickr.  ... 
doi:10.1145/2648581 fatcat:wjjt6h6yljbk5mr2wpqj6i5i2a

EyeSpy

Marek Bell, Stuart Reeves, Barry Brown, Scott Sherwood, Donny MacMillan, John Ferguson, Matthew Chalmers
2009 Proceedings of the 27th international conference on Human factors in computing systems - CHI 09  
, with geo-referenced photos collected from the Flickr website.  ...  By locating the places in which other players' tags were created and 'confirming' them, players earn points for themselves and verify the tags' locations.  ...  Thanks also to the other members of the Social/Ubiquitous/Mobile Group who helped directly or indirectly with this work.  ... 
doi:10.1145/1518701.1518723 dblp:conf/chi/BellRBSMFC09 fatcat:ohhsnwy4uzcbjjjghtq26sac6y

Community-Contributed Media Collections: Knowledge at Our Fingertips [chapter]

Tania Cerquitelli, Alessandro Fiori, Alberto Grand
2011 Community-Built Databases  
For example, social video-sharing communities like YouTube are incorporating ever-increasing amounts of user-contributed media, or photo-sharing communities like Flickr are managing a huge photographic  ...  This chapter reviews different collections of user-contributed media, such as YouTube, Flickr, and Wikipedia, by presenting the main features of their online social networking sites.  ...  Then, for each of these groups, a ranked list of suggested tags is generated according to tag frequency and past inserted tags.  ... 
doi:10.1007/978-3-642-19047-6_2 fatcat:pijcr2c3j5e5tjs73zbtuue6qa
« Previous Showing results 1 — 15 out of 659 results