Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition

arXiv:2403.06577v1 Announce Type: new
Abstract: Classification and localization of driving actions over time is important for advanced driver-assistance systems and naturalistic driving studies. Temporal localization is challenging because it requires robustness, reliability, and accuracy. In this study, we aim to improve the temporal localization and classification accuracy performance by adapting video action recognition and 2D human-pose estimation networks to one model. Therefore, we design a transformer-based fusion architecture to effectively combine 2D-pose features and spatio-temporal features. The model uses 2D-pose …

abstract accuracy action recognition advanced aim arxiv classification cs.cv driver driving embeddings fusion localization performance recognition reliability robustness studies study systems temporal transformer type