... mayalready lead to a good performance.1 IntroductionThere are many ways in which we can refer to ob-jects and people in the real world. A chair, for ex-ample, can be referred to as red, large, ... instance?In this paper, we address this question by sys-tematically training the graph-based REG algorithmon a number of “semantically transparent” data setsof various sizes and evaluating ... the evaluation methodology ofthe REG challenges, training and testing on two do-mains (a furniture and a people domain), and usingtwo automatic metrics (Dice and accuracy) to mea-sure human-likeness....