This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data. Albeit state-of-the-art approaches designed for this application are all supervised, in this paper we pursue a more challenging direction: Solving the problem with unsupervised learning. To this end, we propose a novel subspace clustering method, which exploits covariance matrix to enhance the action's discriminability and a timestamp pruning approach that allow us to better handle the temporal dimension of the data. Through a broad experimental validation, we show that our computational pipeline surpasses existing unsupervised approaches but also can result in favorable performances as compared to supervised methods.
@article{arxiv.2006.11812,
title = {Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning},
author = {Giancarlo Paoletti and Jacopo Cavazza and Cigdem Beyan and Alessio Del Bue},
journal= {arXiv preprint arXiv:2006.11812},
year = {2022}
}