← Search

Ningwei Ouyang

2 accepted papers

2026

RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System

AAAI 2026technical

Current roadside perception systems mainly focus on instance-level perception, which fall short in enabling interaction via natural language and reasoning about traffic behaviors in context. To bridge this gap, we introduce RoadSceneVQA, a large-scale and richly annotated visual question answering (

Cited by 0SourcePDFScholar
2025

Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension

ICRA 2025

Embodied perception is essential for intelligent vehicles and robots in interactive environmental understanding. However, these advancements primarily focus on vision, with limited attention given to using 3D modeling sensors, restricting a comprehensive understanding of objects in response to promp

Cited by 19SourcecodeScholar