BDD-X

The 'BDD-X' dataset is used to evaluate driving behavior recognition and reasoning in autonomous driving video understanding, containing multimodal data that supports the analysis of causal relationships between visual and language modalities.

Papers using BDD-X (3)

MCAM: Multimodal Causal Analysis Model For Ego-vehicle-level Driving Video Understanding2025Multimodal Framework For Explainable Autonomous Driving: Integrating Video, Sensor, And Textual Data For Enhanced Decision-making And Transparency2025Dolphins: Multimodal Language Model for Driving2023 · 1 cites