Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding
Not on the map. Why?
Abstract (arXiv)
This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, which evaluates state-of-the-art models under highly unconstrained conditions. To provide a comprehensive assessment, the 2026 edition features three specialized tracks: the MOSE track for tracking objects within densely cluttered and severely occluded scenarios; the MeViS-Text track for localizing targets via motion-focused linguistic expressions; and the newly inaugurated MeViS-Audio track, which pioneers acoustic-driven object segmentation. By introducing previously unreleased challenging data and analyzing the cutting-edge, multimodal solutions submitted by participants, this report highlights the community's latest technical advancements and charts promising future directions for robust video scene comprehension.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 32 references that are in the map. First posted on arXiv 28 Apr 2026.
Builds on
28 of 32 references.
References · 28
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2025Qwen2.5-VL Technical Reportcited by 5,587
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
- 2025DINOv3cited by 1,414
- 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
- 2025SAM 3: Segment Anything with Conceptscited by 906
- 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 234
- 2023MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressionscited by 228
- 2023Towards Open Vocabulary Learning: A Surveycited by 166
- 2025Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videoscited by 159
- 2024VISA: Reasoning Video Object Segmentation via Large Language Modelscited by 127
- 2023Transformer-Based Visual Segmentation: A Surveycited by 124
16 more
- 2026Qwen3-ASR Technical Reportcited by 118
- 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107
- 2024T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergycited by 94
- 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 62
- 2019Semantic Correlation Promoted Shape-Variant Context for Segmentationcited by 61
- 2024A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Modelscited by 52
- 2022Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensuscited by 50
- 2025MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentationcited by 35
- 2025Exploiting Temporal State Space Sharing for Video Semantic Segmentationcited by 15
- 2024PVUW 2024 Challenge on Complex Video Understanding: Methods and Resultscited by 12
- 2024LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentationcited by 8
- 2025The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VAcited by 7
- 2025PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wildcited by 5
- 2024Just a Few Glances: Open-Set Visual Perception with Image Prompt Paradigmcited by 4
- 2025LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentationcited by 4
- 2026VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.