Abstract. We propose a generative approach to the problem of labeling images containing configurations of objects from multiple classes. The main building blocks are dense statisti...
This paper introduces a video object segmentation algorithm developed in the context of the European project Art.live1 where constraints on the quality of segmentation and the pro...
Alice Caplier, Laurent Bonnaud, Jean-Marc Chassery
In this paper, we propose a general framework for fusing bottom-up segmentation with top-down object behavior classification over an image sequence. This approach is beneficial fo...
While traditional graphics techniques provide for the realistic display of three-dimensional objects, these methods often lack the flexibility to emulate expressive effects found ...
Peter-Pike J. Sloan, William Martin, Amy Gooch, Br...
We present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new...