Cover Image

Understanding Real-World Traffic Safety through RoadSafe365 Benchmark

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Xinyu, Jacob, Darryl C., Liu, Yuxin, Du, Xinsong, Ye, Muchao, Zhou, Bolei, He, Pan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control
by: Jacob, Darryl, et al.
Published: (2026)

VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models
by: Ye, Muchao, et al.
Published: (2024)

COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection
by: Jacob, Darryl Cherian, et al.
Published: (2026)

A Simple Framework Towards Vision-based Traffic Signal Control with Microscopic Simulation
by: He, Pan, et al.
Published: (2024)

OISD: On-Policy Internal Self-Distillation of Language Models
by: Liu, Xinyu, et al.
Published: (2026)

SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning
by: Zhao, Zihao, et al.
Published: (2026)

SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction
by: Peng, Zhenghao, et al.
Published: (2025)

Embodied Scene Understanding for Vision Language Models via MetaVQA
by: Wang, Weizhen, et al.
Published: (2025)

Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
by: Liu, Yuxin, et al.
Published: (2025)

LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection
by: Piehl, Mitchell, et al.
Published: (2026)

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding
by: Huang, Muye, et al.
Published: (2024)

Dreamland: Controllable World Creation with Simulator and Generative Models
by: Mo, Sicheng, et al.
Published: (2025)

SafeMVDrive: Multi-view Safety-Critical Driving Video Synthesis in the Real World Domain
by: Zhou, Jiawei, et al.
Published: (2025)

InspecSafe-V1: A Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios
by: Liu, Zeyi, et al.
Published: (2026)

Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding
by: Zeng, Tong, et al.
Published: (2025)

Robustifying Safety-Aligned Large Language Models through Clean Data Curation
by: Liu, Xiaoqun, et al.
Published: (2024)

RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding
by: Liu, Xiyan, et al.
Published: (2025)

SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation
by: Ma, Yingzi, et al.
Published: (2026)

MMTABREAL: Real-World Benchmark for Multimodal Table Understanding
by: Titiya, Prasham, et al.
Published: (2025)

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
by: Zhang, Jun, et al.
Published: (2025)

AGSENet: A Robust Road Ponding Detection Method for Proactive Traffic Safety
by: Zhang, Ronghui, et al.
Published: (2024)

Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping
by: Du, Tianxiang, et al.
Published: (2026)

Enhancing Road Safety: Real-Time Detection of Driver Distraction through Convolutional Neural Networks
by: Sheikh, Amaan Aijaz, et al.
Published: (2024)

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
by: Rong, Xuankun, et al.
Published: (2025)

How Far Has AI Come in Liver Fibrosis Staging? A Large-Scale Real-World Dataset and Benchmark
by: Liu, Yuanye, et al.
Published: (2026)

CauCLIP: Bridging the Sim-to-Real Gap in Surgical Video Understanding via Causality-Inspired Vision-Language Modeling
by: He, Yuxin, et al.
Published: (2026)

TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
by: Zhou, Xingcheng, et al.
Published: (2025)

Urban Scene Diffusion through Semantic Occupancy Map
by: Zhang, Junge, et al.
Published: (2024)

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
by: Chen, Junkai, et al.
Published: (2025)

Driving in Corner Case: A Real-World Adversarial Closed-Loop Evaluation Platform for End-to-End Autonomous Driving
by: Geng, Jiaheng, et al.
Published: (2025)

Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
by: Liu, Zhizheng, et al.
Published: (2024)

Joint Optimization for 4D Human-Scene Reconstruction in the Wild
by: Liu, Zhizheng, et al.
Published: (2025)

UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective
by: He, Jun, et al.
Published: (2025)

RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
by: Xun, Shuhang, et al.
Published: (2025)

UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
by: Liu, Mingxuan, et al.
Published: (2025)

VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning
by: Ji, Yuheng, et al.
Published: (2025)

From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding
by: Wang, Yandi, et al.
Published: (2026)

POINTS1.5: Building a Vision-Language Model towards Real World Applications
by: Liu, Yuan, et al.
Published: (2024)

CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World
by: Yu, Yating, et al.
Published: (2025)

PolyReal: A Benchmark for Real-World Polymer Science Workflows
by: Liu, Wanhao, et al.
Published: (2026)