This paper describes how the handling of visual media objects is implemented in the visual information retrieval project VizIR. Essentially, four areas are concerned: media access...
Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...
This paper addresses the training of classification trees for weakly labelled data. We call ”weakly labelled data”, a training set such as the prior labelling information pro...
Model management is a framework for supporting meta-data related applications where models and mappings are manipulated as first class objects using operations such as Match, Merge...
Recently, the wide deployment of practical face recognition systems gives rise to the emergence of the inter-modality face recognition problem. In this problem, the face images in ...