In this paper we consider the task of recognizing human actions in realistic video where human actions are dominated by irrelevant factors. We first study the benefits of removing non-action video segments, which are the ones that do not portray any human action. We then learn a non-action classifier and use it to down-weight irrelevant video segments. The non-action classifier is trained using ActionThread, a dataset with shot-level annotation for the occurrence or absence of a human action. The non-action classifier can be used to identify non-action shots with high precision and subsequently used to improve the performance of action recognition systems.
@article{arxiv.1604.06397,
title = {Improving Human Action Recognition by Non-action Classification},
author = {Yang Wang and Minh Hoai},
journal= {arXiv preprint arXiv:1604.06397},
year = {2016}
}