Paper ID: 2407.13750

Pose-guided multi-task video transformer for driver action recognition

Ricardo Pizarro, Roberto Valle, Luis Miguel Bergasa, José M. Buenaposada, Luis Baumela

We investigate the task of identifying situations of distracted driving through analysis of in-car videos. To tackle this challenge we introduce a multi-task video transformer that predicts both distracted actions and driver pose. Leveraging VideoMAEv2, a large pre-trained architecture, our approach incorporates semantic information from human keypoint locations to enhance action recognition and decrease computational overhead by minimizing the number of spatio-temporal tokens. By guiding token selection with pose and class information, we notably reduce the model's computational requirements while preserving the baseline accuracy. Our model surpasses existing state-of-the art results in driver action recognition while exhibiting superior efficiency compared to current video transformer-based approaches.

Submitted: Jul 18, 2024