← All news Press Release · August 2026

Stellarview Vision Language Model Ranked World #1 in Traffic Video AI

Track 3 win at the NVIDIA AI City Challenge 2026, with research accepted at ECCV 2026 in Malmö, Sweden.

NVIDIA

NVIDIA AI City Challenge 2026 · ECCV 2026, Malmö, Sweden

Overview

India, August 2026. Stellarview is proud to share that its Vision Language Model has been ranked World #1 in Traffic Video AI after winning Track 3 of the NVIDIA AI City Challenge 2026.

Our Vision-Language Model system was recognized globally for its ability to understand, reason about, and explain complex events in transportation surveillance footage, after competing with some of the best AI labs in the world.

View the official AI City Challenge 2026 leaderboard

Research accepted at ECCV 2026

The research behind our winning solution has also been accepted at ECCV 2026 in Malmö, Sweden: one of the world's leading conferences in computer vision and artificial intelligence.

Built in India. Recognized globally.

Want to see Recon in action?

See how Stellarview's Vision Language Models power natural-language search and enforcement on India's roads.

Request a Demo