We present a Dynamic Data Driven Application System (DDDAS) to track 2D shapes across large pose variations by learning non-linear shape manifold as overlapping, piecewise linear s...
We present a video summarization technique based on supervised learning. Within a class of videos of similar nature, user provides the desired summaries for a subset of videos. Ba...
The usefulness of a video database depends on whether the video of interest can be easily located. In this paper, we propose a video retrieval algorithm based on the integration o...
This paper proposes the kernel orthogonal mutual subspace method (KOMSM) for 3D object recognition. KOMSM is a kernel-based method for classifying sets of patterns such as video fr...
Augmented Reality (AR) has been acclaimed as one of the promising technologies for advancing future UbiComp (Ubiquitous Computing) environments. Despite a myriad of AR application...