← Back to all news
arXiv Computer Vision By Han Zhang, Yilin Zhao, Zaid Pervaiz Bhat, Zheng Tang, Varun Praveen, Vidya N. Murali, David C. Anastasiu, Tomasz Kornuta

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

Read the original on arXiv Computer Vision →

The paper introduces TAR (Traffic Anomaly Reasoning) and its evaluation suite TAR-Bench, designed to train and assess video‑language models on tasks beyond simple anomaly detection. TAR offers 44,040 chain‑of‑thought annotations covering 10 tasks across 3,670 CCTV videos, while TAR‑Bench supplies 960 human‑curated test annotations from 80 clips of 17 YouTube videos. Experiments show that strong question‑answering performance does not guarantee temporal or scene reasoning, and multi‑task fine‑tuning on TAR consistently improves model scores, with a 10‑task model outperforming its zero‑shot baseline by 21.4 points. The datasets serve as the official training and evaluation data for AI City Challenge 2026 Track 3.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Aug 14

UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations

arXiv:2608. 13031v1 Announce Type: cross Abstract: Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, violations, and interactions between vehicles and vulnerable road users.

By Peng Li, Qianqian Xu, Shilong Bao, Yangbangyan Jiang, Qingming Huang
llmsagentsmultimodal
More like this →
arXiv Computer Vision
Aug 27

TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding

TAU-Agent is a retrieval‑augmented framework designed for traffic anomaly understanding in transportation videos. It uses a central retrieval agent to coordinate a Video Captioning Tool and an Open‑Vocabulary Tracking Tool, gathering captions, temporal intervals, and object trajectories relevant to a query. The collected evidence, along with sampled frames and the query, is fed into a fine‑tuned vision‑language model that reasons and generates an answer. TAU-Agent was evaluated on the AI City Challenge 2026 benchmarks, achieving notable scores across multiple tracks and ranking second, twelfth, and fifth respectively.

By Yuqiang Lin, Yan Shi, Sam Lockyer, Harish Tayyar Madabushi, Adrian Evans, Wenbin Li, Yinhai Wang, Nic Zhang
llmsragagentsfine-tuningmultimodalbenchmarks
More like this →
arXiv AI
Sep 21

AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents

AgentVidBench is a new multi‑hop video question‑answering benchmark designed to evaluate spatial, temporal, and causal reasoning in multimodal large language models (MLLMs). Unlike existing tests that focus on simple scene queries or global summaries, AgentVidBench includes step‑by‑step solution traces to assess whether agents gather the necessary evidence to justify their answers. Experiments with 12 MLLMs show limited single‑turn performance, but integrating these models into agentic workflows improves both accuracy and trajectory scores, establishing AgentVidBench as a comprehensive testbed for future research on agentic video understanding.

By Seoyeon An, Hyeonseo Jang, Minsu Kim, Chanho Lee, Younghan Park, Kangwook Lee
llmsagentsnlpmultimodalbenchmarks
More like this →