Dynamic Matrix Decomposition for Action Recognition

TL;DR

This paper introduces a dynamic matrix decomposition approach that effectively captures local motion features for action recognition in videos, demonstrating promising detection accuracy on benchmark datasets.

Contribution

The paper proposes a novel dynamic appearance technique combined with low-rank and structured sparse matrix decomposition for improved action activity analysis.

Findings

Effective encoding of localized spatio-temporal features.

Captures changes in adjacent frame differences.

Shows promising detection accuracy on benchmark datasets.

Abstract

Designing a technique for the automatic analysis of different actions in videos in order to detect the presence of interested activities is of high significance nowadays. In this paper, we explore a robust and dynamic appearance technique for the purpose of identifying different action activities. We also exploit a low-rank and structured sparse matrix decomposition (LSMD) method to better model these activities.. Our method is effective in encoding localized spatio-temporal features which enables the analysis of local motion taking place in the video. Our proposed model use adjacent frame differences as the input to the method thereby forcing it to capture the changes occurring in the video. The performance of our model is tested on a benchmark dataset in terms of detection accuracy. Results achieved with our model showed the promising capability of our model in detecting action activities.