Abstract. An artificial system that achieves human-level performance on opendomain tasks must have a huge amount of knowledge about the world. We argue that the most feasible way t...
We build word models for American Sign Language (ASL) that transfer between different signers and different aspects. This is advantageous because one could use large amounts of la...
Tracking over a long period of time is challenging as the appearance, shape and scale of the object in question may vary. We propose a paradigm of tracking by repeatedly segmentin...
A key problem in video content analysis using dynamic graphical models is to learn a suitable model structure given some observed visual data. We propose a Completed Likelihood AI...
Abstract. In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from longterm observations of mo...