DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
Stride-qa: Visual question answering dataset for spatiotemporal reasoning in urban driving scenes
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
DTPQA is a new VQA benchmark consisting of synthetic and real-world traffic images with distance annotations to isolate and measure VLM perception capabilities for driving decisions.
citing papers explorer
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
-
Descriptor: Distance-Annotated Traffic Perception Question Answering (DTPQA)
DTPQA is a new VQA benchmark consisting of synthetic and real-world traffic images with distance annotations to isolate and measure VLM perception capabilities for driving decisions.