We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach...
We describe the goals of the ATTEST project, which started in March 2002 as part of the Information Society Technologies (IST) programme, sponsored by the European Commission. In ...
Much of the research on video-based human motion capture assumes the body shape is known a priori and is represented coarsely (e.g. using cylinders or superquadrics to model limbs...
Alexandru O. Balan, Leonid Sigal, Michael J. Black...
In this paper, we propose a new method, video repairing, to robustly infer missing static background and moving foreground due to severe damage or occlusion from a video. To recov...
Jiaya Jia, Tai-Pang Wu, Yu-Wing Tai, Chi-Keung Tan...
This paper presents a polygon soup representation for multiview data. Starting from a sequence of multi-view video plus depth (MVD) data, the proposed quad-based representation ta...