—We propose a unified graphical model that can represent both the causal and noncausal relationships among random variables and apply it to the image segmentation problem. Specif...
Abstract--Learning multiple related tasks from data simultaneously can improve predictive performance relative to learning these tasks independently. In this paper we propose a nov...
Jean Baptiste Faddoul, Boris Chidlovskii, Fabien T...
Abstract. In this paper we propose a new benchmark problem for dynamic combinatorial optimisation. Unlike most previous benchmarks, we focus primarily on the underlying dynamics of...
A neural net with multiple output nodes is capable of distinguishing among a set of related input classes even in the absence of training. It can do so with an accuracy that is ma...
This paper proposes an advanced spatially scalable video coding approach that exploits the inter layer correlation between different resolution layers by classified patch learning...