Skeleon-Based Typing Style Learning For Person Identification
This work provides a new method for person identification, which could be useful for security or personalized interaction systems, by leveraging typing style dynamics from skeleton data.
This paper addresses person identification through typing style analysis, utilizing a novel architecture based on adaptive non-local spatio-temporal graph convolutional networks. By extracting and learning the dynamics of joint positions, the model achieves superior discriminative and generalization abilities compared to state-of-the-art skeleton-based models.
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.