From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning

arXiv:2608.10317 · cs.CV · Submitted 2026-08-10 · Read on arXiv

cs.CV

Submitted: 2026-08-10

Updated: 2026-09-23

Code: https://github.com/MoyoG/FETV

Terminology

• Traffic Anomaly Reasoning — 21× in this paper
• Trace — 20× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Fine-Tuning — 11× in this paper · explained in 5 episodes
• Temporal Reasoning — 8× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Reasoning Traces — 7× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Causal Reasoning — 4× in this paper · explained in 2 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Vision-language models — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Core — 3× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• IEEE International Conference on Computer Vision — 2× in this paper
• Semantic Similarity — 2× in this paper · explained in 2 episodes
• Structured Reasoning — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Calibration Failure — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• World Model — 1× in this paper · explained in 7 episodes
• Zero-Shot Generalization — 1× in this paper · explained in 5 episodes

Sources

• Cosmos 3: Omnimodal World Models for Physical AI
• AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
• Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
• SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models
• Qwen3-VL Technical Report
• CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
• The 9th AI City Challenge
• TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance
• MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks
• Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM
• Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models