Genetic Programming-Evolved Spatio-Temporal Descriptor for Human-Action Recognition

Liu, Li, Shao, Ling and Rockett, Peter (2012) Genetic Programming-Evolved Spatio-Temporal Descriptor for Human-Action Recognition. In: Proceedings of the British Machine Vision Conference 2012. UNSPECIFIED, 18.1-18.12.

Full text not available from this repository.


The potential value of human action recognition has led to it becoming one of the most active research subjects in computer vision. In this paper, we propose a novel method to automatically generate low-level spatio-temporal descriptors showing good performance, for high-level human-action recognition tasks. We address this as an optimization problem using genetic programming (GP), an evolutionary method, which produces the descriptor by combining a set of primitive 3D operators. As far as we are aware, this is the first report of using GP for evolving spatio-temporal descriptors for action recognition. In our evolutionary architecture, the average cross-validation classification error calculated using the support-vector machine (SVM) classifier is used as the GP fitness function. We run GP on a mixed dataset combining the KTH and the Weizmann datasets to obtain a promising feature-descriptor solution for action recognition. To demonstrate generalizability, the best descriptor generated so far by GP has also been tested on the IXMAS dataset leading to better accuracies compared with some previous hand-crafted descriptors.

Item Type: Book Section
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: Pure Connector
Date Deposited: 16 Feb 2017 02:26
Last Modified: 22 Oct 2022 00:00
DOI: 10.5244/C.26.18

Actions (login required)

View Item View Item