Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge

TL;DR

This paper introduces TEP, a training-free method that enhances complex video object segmentation by integrating tracking models and multimodal language models, achieving top results in the PVUW Challenge.

Contribution

The novel tracking-enhanced prompt approach improves segmentation of tiny and semantic objects without additional training, outperforming existing methods.

Findings

Achieved 56.91% on PVUW Challenge 2026 test set.

Outperforms SAM3 on tiny and semantic-dominated objects.

First place in the PVUW Challenge for complex video segmentation.

Abstract

In the Complex Video Object Segmentation task, researchers are required to track and segment specific targets within cluttered environments, which rigorously tests a method's capability for target comprehension and environmental adaptability. Although SAM3, the current state-of-the-art solution, exhibits unparalleled segmentation performance and robustness on conventional targets, it underperforms on tiny and semantic-dominated objects. The root cause of this limitation lies in SAM3's insufficient comprehension of these specific target types. To address this issue, we propose TEP: Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompts. As a training-free approach, TEP leverages external tracking models and Multimodal Large Language Models to introduce tracking-enhanced prompts, thereby alleviating the difficulty SAM3 faces in understanding these challenging targets. Our method achieved first place (56.91%) on the test set of the PVUW Challenge 2026: Complex Video Object Segmentation Track.