The 10th AI City Challenge

第十届 AI 城市挑战赛

The 10th AI City Challenge, held with ECCV 2026, marks a decade of community benchmarking for intelligent transportation, smart cities, and physical AI. Since its 2017 start with vehicle detection, classification, and tracking, the challenge has grown into a broad benchmark suite for multi-camera perception, multimodal reasoning, synthetic-to-real learning, generative forecasting, and privacy-preserving evaluation.

第十届 AI 城市挑战赛与 ECCV 2026 同期举行，标志着智能交通、智慧城市和物理人工智能领域社区基准测试走过了十个年头。自 2017 年以车辆检测、分类和跟踪起步以来，该挑战赛已发展成为涵盖多摄像头感知、多模态推理、合成到真实学习、生成式预测以及隐私保护评估的广泛基准测试套件。

The 2026 edition continued this growth with 325 registered teams, up from 245 in 2025, and participation from 26 countries and regions, up from 15. Its six primary tracks cover multi-camera 3D perception, transportation safety captioning and VQA, traffic anomaly reasoning, text-based person anomaly search, generative traffic video forecasting, and cross-city object detection. Track 3 further includes two out-of-domain leaderboards, submitted as Tracks 7 and 8, for fisheye traffic-violation understanding and pedestrian situated-intent VQA.

2026 年的赛事延续了这一增长势头，注册参赛队伍从 2025 年的 245 支增加到 325 支，参与国家和地区从 15 个增加到 26 个。其六大主要赛道涵盖了多摄像头 3D 感知、交通安全描述与视觉问答（VQA）、交通异常推理、基于文本的行人异常搜索、生成式交通视频预测以及跨城市目标检测。第三赛道还额外包含了两个域外（out-of-domain）排行榜（即赛道 7 和赛道 8），分别针对鱼眼镜头交通违规理解和行人情境意图视觉问答。

This paper summarizes the challenge setup, datasets, evaluation protocols, leaderboard results, and workshop papers. Across tracks, successful systems combine foundation models with geometric grounding, retrieval or reranking, synthetic-data design, domain adaptation, and controlled inference.

本文总结了挑战赛的设置、数据集、评估协议、排行榜结果以及研讨会论文。在各个赛道中，表现优异的系统均结合了基础模型与几何定位、检索或重排序、合成数据设计、域适应以及受控推理等技术。