Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding

TL;DR

This report summarizes the objectives, datasets, and top methodologies of the 2026 PVUW Challenge, which evaluates multimodal pixel-level video understanding in highly unconstrained environments across three specialized tracks.

Contribution

It introduces new challenging datasets, three novel tracks including audio-driven segmentation, and provides a comprehensive analysis of state-of-the-art multimodal solutions.

Findings

Introduction of challenging new datasets for pixel-level understanding.

Development of three specialized tracks including audio-driven segmentation.

Analysis of cutting-edge multimodal solutions and future directions.

Abstract

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.