RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914221158039552 |
|---|---|
| author | Guan, Runwei Hu, Rongsheng Chen, Shangshu Xiao, Ningyuan Xia, Xue Liu, Jiayang Chen, Beibei Tang, Ziren Ouyang, Ningwei Liang, Shaofeng Fan, Yuxuan Sun, Wanjie Yue, Yutao |
| author_facet | Guan, Runwei Hu, Rongsheng Chen, Shangshu Xiao, Ningyuan Xia, Xue Liu, Jiayang Chen, Beibei Tang, Ziren Ouyang, Ningwei Liang, Shaofeng Fan, Yuxuan Sun, Wanjie Yue, Yutao |
| contents | 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 (VQA) dataset specifically tailored for roadside scenarios. The dataset comprises 34,736 diverse QA pairs collected under varying weather, illumination, and traffic conditions, targeting not only object attributes but also the intent, legality, and interaction patterns of traffic participants. RoadSceneVQA challenges models to perform both explicit recognition and implicit commonsense reasoning, grounded in real-world traffic rules and contextual dependencies. To fully exploit the reasoning potential of Multi-modal Large Language Models (MLLMs), we further propose CogniAnchor Fusion (CAF), a vision-language fusion module inspired by human-like scene anchoring mechanisms. Moreover, we propose the Assisted Decoupled Chain-of-Thought (AD-CoT) to enhance the reasoned thinking via CoT prompting and multi-task learning. Based on the above, we propose the baseline model RoadMind. Experiments on RoadSceneVQA and CODA-LM benchmark show that the pipeline consistently improves both reasoning accuracy and computational efficiency, allowing the MLLM to achieve state-of-the-art performance in structural traffic perception and reasoning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System Guan, Runwei Hu, Rongsheng Chen, Shangshu Xiao, Ningyuan Xia, Xue Liu, Jiayang Chen, Beibei Tang, Ziren Ouyang, Ningwei Liang, Shaofeng Fan, Yuxuan Sun, Wanjie Yue, Yutao Computer Vision and Pattern Recognition 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 (VQA) dataset specifically tailored for roadside scenarios. The dataset comprises 34,736 diverse QA pairs collected under varying weather, illumination, and traffic conditions, targeting not only object attributes but also the intent, legality, and interaction patterns of traffic participants. RoadSceneVQA challenges models to perform both explicit recognition and implicit commonsense reasoning, grounded in real-world traffic rules and contextual dependencies. To fully exploit the reasoning potential of Multi-modal Large Language Models (MLLMs), we further propose CogniAnchor Fusion (CAF), a vision-language fusion module inspired by human-like scene anchoring mechanisms. Moreover, we propose the Assisted Decoupled Chain-of-Thought (AD-CoT) to enhance the reasoned thinking via CoT prompting and multi-task learning. Based on the above, we propose the baseline model RoadMind. Experiments on RoadSceneVQA and CODA-LM benchmark show that the pipeline consistently improves both reasoning accuracy and computational efficiency, allowing the MLLM to achieve state-of-the-art performance in structural traffic perception and reasoning tasks. |
| title | RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.18286 |