Because of their lack of rules, general broadcast videos are more difficult to analyze than news or sport videos. To retrieve human interventions in this context, a robust face tr...
Abstract— Many computer vision problems such as recognition, image retrieval, and tracking require matching two images. Currently, ones try to find as reliable as possible match...
This paper proposes a method for the rapid and precise estimation of human hand postures by combining 2-D appearance matching and 3-D model-based fitting. First a rough posture e...
In this paper we describe our submission for iCLEF2006: an interface that allows users to search FLICKR in Arabic for images with captions in a range of languages. We report and di...
Patch descriptors are used for a variety of tasks ranging from finding corresponding points across images, to describing object category parts. In this paper, we propose an image ...