Density-Guided Label Smoothing for Temporal Localization of Driving Actions
This work addresses the need for robust and reliable action localization in advanced driver-assistance systems and naturalistic driving studies, representing an incremental improvement.
The paper tackles the problem of temporal localization of driving actions by developing a density-guided label smoothing technique and a post-processing step for fusing multi-view information, achieving an F1 score of 0.271 on the A2 test set of the 2022 NVIDIA AI City Challenge.
Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliability and accurate localization. In this work, we focus on improving the overall performance by efficiently utilizing video action recognition networks and adapting these to the problem of action localization. To this end, we first develop a density-guided label smoothing technique based on label probability distributions to facilitate better learning from boundary video-segments that typically include multiple labels. Second, we design a post-processing step to efficiently fuse information from video-segments and multiple camera views into scene-level predictions, which facilitates elimination of false positives. Our methodology yields a competitive performance on the A2 test set of the naturalistic driving action recognition track of the 2022 NVIDIA AI City Challenge with an F1 score of 0.271.