Abstract. Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to le...
Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to learn the st...
We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at semantic concept detection. We propose to extract a novel representation, the Sh...
Wei Jiang, Courtenay V. Cotton, Shih-Fu Chang, Dan...
The objective of this paper is to explore the feasibility of using multiple low-altitude, short endurance (LASE) unmanned air vehicles (UAVs) to cooperatively monitor and track th...
David W. Casbeer, Derek B. Kingston, Randal W. Bea...
The design of robust classifiers, which can contend with the noisy and outlier ridden datasets typical of computer vision, is studied. It is argued that such robustness requires l...