In this paper we describe our TRECVID 2008 video retrieval experiments. The MediaMill team participated in three tasks: concept detection, automatic search, and interactive search...
Cees G. M. Snoek, Koen E. A. van de Sande, Ork de ...
Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
This paper introduces a web image dataset created by NUS’s Lab for Media Search. The dataset includes: (1) 269,648 images and the associated tags from Flickr, with a total of 5,...
Annotations of multimedia documents typically have been pursued in two different directions. Either previous approaches have focused on low level descriptors, such as dominant colo...