Skeleon-Based Typing Style Learning For Person Identification

TL;DR

This paper introduces a novel skeleton-based model using adaptive non-local spatio-temporal graph convolutional networks for person identification through typing style, demonstrating robustness to noise and environmental variations.

Contribution

The paper proposes a new architecture for typing style-based person identification utilizing adaptive non-local graph convolutions and introduces two datasets for this task.

Findings

Model outperforms state-of-the-art skeleton-based methods.

Robustness to noisy and changing environmental conditions.

Effective analysis of joint movements for identification.

Abstract

We present a novel architecture for person identification based on typing-style, constructed of adaptive non-local spatio-temporal graph convolutional network. Since type style dynamics convey meaningful information that can be useful for person identification, we extract the joints positions and then learn their movements' dynamics. Our non-local approach increases our model's robustness to noisy input data while analyzing joints locations instead of RGB data provides remarkable robustness to alternating environmental conditions, e.g., lighting, noise, etc. We further present two new datasets for typing style based person identification task and extensive evaluation that displays our model's superior discriminative and generalization abilities, when compared with state-of-the-art skeleton-based models.