—Inferring latent structures from observations helps to model and possibly also understand underlying data generating processes. A rich class of latent structures are the latent ...
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...
This paper presents a novel feature-matching based approach for rigid object tracking. The proposed method models the tracking problem as discovering the affine transforms of obje...
Weiyu Zhu, Song Wang, Ruei-Sung Lin, Stephen E. Le...
We introduce a novel energy minimization method to decompose a video into a set of super-resolved moving layers. The proposed energy corresponds to the cost of coding the sequence...
This paper investigates whether Web comments can be exploited for cross-media retrieval. Comparing Web items such as texts, images, videos, music, products, or personal profiles ...