This paper presents a hybrid 1D motion estimation algorithm which combines pixel-based and region-based approaches that can give depth images from translational video sequences wi...
This paper presents a framework to simultaneously segment and track multiple body parts of interacting humans in the presence of mutual occlusion and shadow. The framework uses mu...
Automatic indexing of music instruments for multi-timbre sounds is challenging, especially when partials from different sources are overlapping with each other. Temporal features, ...
Xin Zhang, Wenxin Jiang, Zbigniew W. Ras, Rory A. ...
Bottom-up, fully unsupervised segmentation remains a daunting challenge for computer vision. In the cosegmentation context, on the other hand, the availability of multiple images ...
We propose a method to automatically transform mesh animations into animation collages, i.e. moving assemblies of shape primitives from a database given by an artist. An animation...