# The 10th AI City Challenge

arXiv: https://arxiv.org/abs/2608.17044 · HTML: https://mlsanity.com/paper/2608.17044/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 16 of 16)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [The 7th AI City Challenge](https://mlsanity.com/paper/2304.07500/) (2023)
- [The 8th AI City Challenge](https://mlsanity.com/paper/2404.09432/) (2024)
- [The 9th AI City Challenge](https://mlsanity.com/paper/2508.13564/) (2025)
- [CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting](https://mlsanity.com/paper/2608.07693/) (2026)
- [FaLCon: Facet-Anchored Retrieval with Late Consensus for Sim2Real Text-Based Person Anomaly Search](https://mlsanity.com/paper/2608.09474/) (2026)
- [GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction](https://mlsanity.com/paper/2608.09493/) (2026)
- [From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning](https://mlsanity.com/paper/2608.10317/) (2026)
- [Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval](https://mlsanity.com/paper/2608.12843/) (2026)
- [UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations](https://mlsanity.com/paper/2608.13031/) (2026)

## Built on by (most cited first, 8 of 8)

- [Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking](https://mlsanity.com/paper/2608.24130/) (2026)
- [Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection](https://mlsanity.com/paper/2608.24154/) (2026)
- [TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding](https://mlsanity.com/paper/2608.25935/) (2026)
- [VANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models](https://mlsanity.com/paper/2609.09396/) (2026)
- [Online Multi-Camera 3D Tracking via ID Prediction over Recurrent Sparse Queries](https://mlsanity.com/paper/2609.18363/) (2026)
- [Sim-to-Real Traffic Scene Understanding by Decoupling Semantics from Caption Generation with V-JEPA](https://mlsanity.com/paper/2609.18562/) (2026)
- [SCOUT: Sim-to-Real Text-Based Person Retrieval by Embedding-Space Prediction over Frozen Video Features](https://mlsanity.com/paper/2609.19483/) (2026)
- [The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale](https://mlsanity.com/paper/2610.18511/) (2026)

## Abstract (arXiv)

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. 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. 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.