Motion information scalability is an important requirement for a fully scalable video codec, especially in low bit rate or small resolution decoding scenarios, for which the fully...
The model-view-controller pattern is used to keep a data model and its views consistent. Usually there is a one-to-one correspondence between the data in the model and its represen...
In this paper, we present an approach to multi-view image-based 3D reconstruction by statistically inversing the ray-tracing based image generation process. The proposed algorithm...
Many existing approaches to collaborative filtering can neither handle very large datasets nor easily deal with users who have very few ratings. In this paper we present the Prob...
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feed...
Hueihan Jhuang, Thomas Serre, Lior Wolf, Tomaso Po...