Querying by Visual Thesaurus (VT) is a novel paradigm for content-based image retrieval approaches for it gives the user the possibility, in case of inappropriate starting example...
Segmentation in the surveillance domain has to deal with shadows to avoid distortions when detecting moving objects. Most segmentation approaches dealing with shadow detection are ...
Ivan Huerta, Michael Holte, Thomas Moeslund, and J...
This paper addresses the problem of foreground extraction using active illumination and graph-cut optimization. Our approach starts by detecting image regions that are likely to b...
We describe a technique for reconstructing probable occluded surfaces from 3-D range images. The technique exploits the fact that many objects possess shape symmetries that can be...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...