arXiv：cs.LG· Fedor Kitashov, Jo\~ao Carreira, Shiry Ginosar, Dima Damen, Andrew Zisserman, Viorica P\u{a}tr\u{a}ucean·· 4 小时前
Perception Test 2026 挑战赛总结：新增城市尺度音视频推理赛道
Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning
AI 导读
Perception Test 2026 作为第四届挑战赛在 ECCV 2026 举办，聚焦空间智能，设 unified multiple-choice videoQA、grounded videoQA 及新增城市尺度赛道 KilometerAudio 和 KilometerVision 共四个赛道。
正文
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.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.12081 [cs.CV] |
| (or arXiv:2610.12081v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12081 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Viorica Patraucean Dr [view email]
[v1]
Thu, 8 Oct 2026 14:54:26 UTC (4,946 KB)
来源：arXiv：cs.LG · arxiv.org