Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/www2008/paper/373> ?p ?o. }
Showing items 1 to 15 of
15
with 100 items per page.
- 373 creator lyndon-kennedy.
- 373 creator mor-naaman.
- 373 type InProceedings.
- 373 label "Diverse and Representative Image Search Results for Landmarks".
- 373 sameAs 373.
- 373 abstract "Can we automatically generate representative and diverse views of the world's landmarks from community-contributed collections on the web? Community-contributed collections of media on the web are a becoming a vast, rich resource for image and video on a long-tailed array of topics. We use a combination of context- and content-based tools to generate representative sets of images for location-driven features and landmarks, a common search task. To do that, we using location and other metadata, as well as tags associated with images, and the images' visual features. We present an approach to extracting tags that represent landmarks. We show how to use unsupervised methods to extract representative views and images for each landmark. This approach can potentially scale to provide better search and representation for every landmark, worldwide. We evaluate the system in the context of web image search using a real-life dataset of 110,000 images from the San Francisco area.".
- 373 hasAuthorList authorList.
- 373 hasTopic World_Wide_Web.
- 373 isPartOf proceedings.
- 373 keyword "image analysis".
- 373 keyword "image search".
- 373 keyword "photo collections".
- 373 keyword "social media".
- 373 keyword "tagging".
- 373 title "Diverse and Representative Image Search Results for Landmarks".