The effects of data sources: A baseline evaluation of the MoCA dataset

In this work we discuss the action classification performance obtained with a baseline assessment of the MoCA dataset: a multimodal, synchronised dataset including Motion Capture data and multi-view video sequences of upper body actions in a cooking scenario. To this purpose, we setup a classification pipeline to manipulate the two data type. For the MoCap, we employ a representation based on the use of 3D+t histograms modelling the space-time evolution of an action, classified using a classical Support Vector Machine with a linear kernel. As for the videos, we learn the representation using a variant of the Inception 3D model, followed by a Single Layer Perceptron as a classifier. Discussing the experimental analysis will be the opportunity to observe the diversity of MoCap and video data at work in two scenarios of uneven complexity, i.e. on streams of data describing regular repetitions of the same action, or when actions are part of a more complex and structured activity where actions influence each other.