Gradient Boundary Histograms for Action Recognition

TL;DR

This paper presents gradient boundary histograms (GBH), a fast, efficient local spatiotemporal descriptor for action recognition that outperforms existing gradient-based methods on large datasets.

Contribution

The paper introduces GBH, a novel, computationally efficient descriptor that improves local structure and motion representation for action recognition tasks.

Findings

GBH outperforms other gradient-based descriptors on large datasets.

Recognition accuracy is maintained with reduced spatial resolution.

GBH offers high efficiency and low memory usage.

Abstract

This paper introduces a high efficient local spatiotemporal descriptor, called gradient boundary histograms (GBH). The proposed GBH descriptor is built on simple spatio-temporal gradients, which are fast to compute. We demonstrate that it can better represent local structure and motion than other gradient-based descriptors, and significantly outperforms them on large realistic datasets. A comprehensive evaluation shows that the recognition accuracy is preserved while the spatial resolution is greatly reduced, which yields both high efficiency and low memory usage.