Intention from Motion

In this paper, we propose Intention from Motion, a new paradigm for action prediction where, without using any contextual information, we can predict human intentions all originating from the same motor act, non specific of the following performed action. To this purpose, we have designed a new multimodal dataset consisting of a set of motion capture marker 3D data and 2D video sequences where, by only analysing very similar movements in both training and test phases, we are able to predict the underlying intention, i.e., the future, never observed, action. We also present an extensive three-fold experimental evaluation as a baseline, customizing state-of-the-art techniques for 3D and 2D data analysis, and proposing fusion methods to combine the two types of available data. This work constitutes a proof of concept for this new paradigm as we empirically prove the affordability of predicting intentions by analysing motion patterns and without considering any additional contextual cues.