Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Proceedings of the 15th international conference on World Wide Web
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Why we tag: motivations for annotation in mobile and online media
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Proceedings of the 15th international conference on Multimedia
Inferring generic activities and events from image content and bags of geo-tags
CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Leveraging probabilistic season and location context models for scene understanding
CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Event recognition: viewing the world with a third eye
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Proceedings of the 18th international conference on World wide web
WSMC '09 Proceedings of the 1st workshop on Web-scale multimedia corpus
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Inferring photographic location using geotagged web images
Multimedia Tools and Applications
Tagging photos using users' vocabularies
Neurocomputing
Hi-index | 0.01 |
Recent research has shown the power of geotagging for many multimedia applications. In this paper, we present an integrated and intuitive system for suggesting location-driven tags for a geotagged photo. Potential tags from multiple sources are extracted, including points of interest (POI) tags from a public Geographic Names Information System (GNIS) database, community tags from Flickr® pictures, and personal tags shared through user's own, family and friends' photo collections. To increase the effectiveness of GNIS POI tags, bags of place name tags are first retrieved and then re-ranked using a combined tf-idf and spatial distance criteria. The community tags from photos taken in the vicinity of the input geotagged photo are ranked according to distance and visual similarity to the input photo. Personal tags from other personally related photos inherently carry a significant weight due to their high relevance than both the generic place name tags and community tags, and are ranked by weights decaying over time and distance differences. Finally, a rich set of the most relevant location-driven tags is presented to the user in the form of individual tags clouds under the three mentioned source categories. The tag clouds act as intuitive suggestions for tagging an input image. Preliminary user evaluation has revealed the respective benefits of the three categories and shown the effectiveness of the integrated tag suggestion system.