We have created the first image search engine based entirely on faces. Using simple text queries such as "smiling men with blond hair and mustaches," users can search thr...
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
Access to devices that integrate Global Positioning data with image and sound acquisition becomes more common, enabling people to build large collections of locative multimedia. A...
To take the first step beyond keyword-based search toward entity-based search, suitable token spans ("spots") on documents must be identified as references to real-world...
Sayali Kulkarni, Amit Singh, Ganesh Ramakrishnan, ...
Navigation through large multimedia collections that include videos and images still remains a hard problem. In this paper, we introduce a novel method to visualize and navigate t...