We propose a new approach for face recognition under arbitrary illumination conditions, which requires only one training image per subject (if there is no pose variation) and no 3...
Effective provisioning of next generation distributed applications hosted on diverse middleware platforms incurs significant challenges due to the applications’ growing complex...
Dimple Kaul, Arundhati Kogekar, Aniruddha S. Gokha...
If robotic agents are to act autonomously they must have the ability to construct and reason about models of their physical environment. For example, planning to achieve goals req...
One recent approach to build highly scalable and robust networked virtual environments (NVEs) is by using peer-to-peer overlay networks. Voronoi-based Overlay Network (VON) has be...
Videos usually consist of activities involving interactions between multiple actors, sometimes referred to as complex activities. Recognition of such activities requires modeling ...
Utkarsh Gaur, Yingying Zhu, Bi Song, Amit Roy-Chow...