Abstract. Motion segmentation involves identifying regions of the image that correspond to independently moving objects. The number of independently moving objects, and type of mot...
While camcorders have become a commodity home appliance, few watch the recorded videos or share them with friends and relatives due to the difficulty of turning the raw footage in...
Two major challenges in collaborative filtering are the efficiency of the algorithms and the quality of the recommendations. A variety of machine learning methods have been applie...
What type of algorithms and statistical techniques support learning from very large datasets over long stretches of time? We address this question through a memory bounded version...
Gaussian Process Temporal Difference (GPTD) learning offers a Bayesian solution to the policy evaluation problem of reinforcement learning. In this paper we extend the GPTD framew...