First-Person Activity Recognition from Micro-Action Representations using Convolutional Neural Networks and Object Flow Histograms

A novel frst-person human activity recognition framework is pro-posed in this work. Our proposed methodology is inspired by the central role moving objects have in egocentric activity videos. Using a Deep Convolutional
Neural Network we detect objects and develop discriminant object flow his-tograms in order to represent fine-grained micro-actions during short temporal windows. Our framework is based on the assumption that large scale activities
are synthesized by fine-grained micro-actions. We gather all the micro-actions and perform Gaussian Mixture Model clusterization, so as to build a micro-action vocabulary that is later used in a Fisher encoding schema. Results
show that our method can reach 60% recognition rate on the benchmark ADL dataset. The capabilities of the proposed framework are also showcased by profoundly evaluating for a great deal of hyper-parameters and comparing to
other State-of-the-Art works.