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.
@article{arxiv.2604.00395,
title = {Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge},
author = {Jinrong Zhang and Canyang Wu and Xusheng He and Weili Guan and Jianlong Wu and Liqiang Nie},
journal= {arXiv preprint arXiv:2604.00395},
year = {2026}
}
Comments
1st Place Solution for the 5th PVUW MOSE Challenge (CVPR 2026 Workshop)