For scene classification, patch-level linear features do not always work as well as handcrafted features. In this paper, we present a new model to greatly improve the usefulness ...
Liwei Wang, Yin Li, Jiaya Jia, Jian Sun, David Wip...
Given an image sequence of a scene consisting of multiple rigidly moving objects, multi-body structure-and-motion (MSaM) is the task to segment the image feature tracks into the d...
The ever-growing use of modeling languages today is largely due to a maturation of model-based development technologies. However, there is enough room for improving language specif...
Abstract. We propose a methodology for recognizing actions at a distance by watching the human poses and deriving descriptors that capture the motion patterns of the poses. Human p...
The paper presents two new approaches to multiobjective design space exploration for parametric VLSI systems. Both considerably reduce the number of simulations needed to determin...