State-of-the-art methods for human detection and pose estimation require many training samples for best performance. While large, manually collected datasets exist, the captured v...
Leonid Pishchulin, Arjun Jain, Mykhaylo Andriluka,...
We develop a novel and general approach to estimating the accuracy of protein multiple sequence alignments without knowledge of a reference alignment, and use our approach to addre...
Dan F. DeBlasio, Travis J. Wheeler, John D. Kececi...
We present a novel representation for modeling textured
regions subject to smooth variations in orientation and
scale. Utilizing the steerable pyramid of Simoncelli and
Freeman ...
In this work, we present an approach to jointly segment a rigid object in a 2D image and estimate its 3D pose, using the knowledge of a 3D model. We naturally couple the two proces...
Samuel Dambreville, Romeil Sandhu, Anthony J. Yezz...
This paper describesa hierarchicalestimation framework for the computation of diverserepresentationsof motion information. The key features of the resulting framework (or family of...
James R. Bergen, P. Anandan, Keith J. Hanna, Rajes...