VIMS Lab is situated in Department of Computer & Information Sc, University of Delaware, Newark, DE. USA.
At VIMS we work on various problems related to image/video processing...
Placing shadows is difficult task since shadows depend on the relative positions of lights and objects in an unintuitive manner. To simplify the task of the modeler, we present a ...
This paper examines the problem of moving object detection. More precisely, it addresses the difficult scenarios where background scene textures in the video might change over tim...
Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stef...
Abstract. In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from longterm observations of mo...