A successful representation of objects in the literature is as a collection of patches, or parts, with a certain appearance and position. The relative locations of the different p...
In this paper, we describe a statistical method to detect highlights in a baseball game video. The input video is first segmented into scene shots, within which the camera motion ...
This paper considers the problems of feature variation and concept uncertainty in typical learning-based video semantic classification schemes. We proposed a new online semantic c...
The traditional processing flow of segmentation followed by classification in computer vision assumes that the segmentation is able to successfully extract the object of interest....
We address the problem of label assignment in computer
vision: given a novel 3-D or 2-D scene, we wish to assign a
unique label to every site (voxel, pixel, superpixel, etc.). To...
Daniel Munoz, James A. Bagnell, Martial Hebert, Ni...