— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
Changes in motion properties of trajectories provide useful cues for modeling and recognizing human activities. We associate an event with significant changes that are localized in...
Naresh P. Cuntoor, B. Yegnanarayana, Rama Chellapp...
We present a computer vision system for robust object tracking in 3D by combining evidence from multiple calibrated cameras. This kernel-based 3D tracker is automatically bootstra...
Ambrish Tyagi, Mark A. Keck, James W. Davis, Geras...
In this paper, we address the problem of face tracking across illumination changes and occlusions. The method is based on leveraging the strengths of both Adaboost to deal with cl...
Earlier this year, a major effort was initiated to study the theoretical and empirical aspects of the automatic detection of semantic concepts in broadcast video, complementing ong...