Abstract
Continuing the Perception Test challenge series, we organised the fourth edition as a workshop at the European Conference on Computer Vision (ECCV) 2026 in Malmö, Sweden. This edition focused on spatial intelligence and featured four different tracks: unified multiple-choice videoQA and grounded videoQA from the original Perception Test benchmark, alongside two new tracks based on city-scale walking-tour videos (KilometerAudio and KilometerVision). In this report, we describe the new benchmarks used for the city-scale tracks and summarise the winning solutions across all tracks, including a generalist model that competed across all tracks with satisfactory performance. The winning solutions in the newly added city-scale tracks demonstrated that complex spatial and multimodal reasoning can be solved by expensive agentic pipelines, but remains difficult for multimodal models used standalone.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kitashov, F., Carreira, J., Ginosar, S., Damen, D., Zisserman, A., & Pătrăucean, V. (2026). Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning. https://omanscience.com/en/articles/perception-test-2026-challenge-summary-and-extension-to-city-scale-audio-visual-reasoning
MLA 9
Kitashov, Fedor, et al. "Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning." https://omanscience.com/en/articles/perception-test-2026-challenge-summary-and-extension-to-city-scale-audio-visual-reasoning.
Chicago (author–date)
Kitashov, Fedor, João Carreira, Shiry Ginosar, Dima Damen, Andrew Zisserman, and Viorica Pătrăucean. 2026. "Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning." https://omanscience.com/en/articles/perception-test-2026-challenge-summary-and-extension-to-city-scale-audio-visual-reasoning.
Harvard
Kitashov, F., Carreira, J., Ginosar, S., Damen, D., Zisserman, A. and Pătrăucean, V. (2026) 'Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning', Available at: https://omanscience.com/en/articles/perception-test-2026-challenge-summary-and-extension-to-city-scale-audio-visual-reasoning.
Vancouver
Kitashov F, Carreira J, Ginosar S, Damen D, Zisserman A, Pătrăucean V. Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning. https://omanscience.com/en/articles/perception-test-2026-challenge-summary-and-extension-to-city-scale-audio-visual-reasoning
IEEE
F. Kitashov, J. Carreira, S. Ginosar, D. Damen, A. Zisserman, and V. Pătrăucean, "Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning," https://omanscience.com/en/articles/perception-test-2026-challenge-summary-and-extension-to-city-scale-audio-visual-reasoning.