A system is described that tracks moving objects in a video dataset so as to extract a representation of the objects' 3D trajectories. The system then finds hierarchical clus...
This paper presents a new approach for representing multidimensional data by a compact number of bases. We consider the multidimensional data as tensors instead of matrices or vec...
In this paper, we propose a shape reconstruction and image restoration method for paper documents with curved surfaces or fold lines by using a stereo vision system. Characters in...
Atsushi Kawarago, Atsushi Yamashita, Kenjiro T. Mi...
We propose a general framework to index very large datasets of spatial data in a distributed system. Our proposal is built on the recently proposed Scalable Distributed Rtree (SD-...
We propose a flexible summarization framework for teamsport videos, which is able to integrate both the knowledge about displayed content (e.g. level of interest, type of view, et...