Transfer-LMR: Heavy-Tail Driving Behavior Recognition in Diverse Traffic Scenarios

arXiv:2405.05354v1 Announce Type: new
Abstract: Recognizing driving behaviors is important for downstream tasks such as reasoning, planning, and navigation. Existing video recognition approaches work well for common behaviors (e.g. "drive straight", "brake", "turn left/right"). However, the performance is sub-par for underrepresented/rare behaviors typically found in tail of the behavior class distribution. To address this shortcoming, we propose Transfer-LMR, a modular training routine for improving the recognition performance across all driving behavior classes. We extensively evaluate our approach on METEOR and …

abstract arxiv behavior class cs.cv distribution diverse drive driving found however navigation performance planning reasoning recognition tasks traffic transfer type video work