State-of-the-art pattern recognition methods have difficulty dealing with problems where the dimension of the output space is large. In this article, we propose a new framework ba...
Speed and availability of information, delivered in past years by Internet technologies, made it easier for any company to outsource primary activities, which resulted in unbundli...
Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...
In this paper, we propose a novel predictive model for
object boundary, which can integrate information from any
sources. The model is a dynamic “object” model whose
manifes...
Tian Shen (Lehigh University), Hongsheng Li (Lehig...
A novel method for extracting parametric junction and corner features in images is presented. By treating each complex feature as a combination of elementary line and edge feature...