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

Source: [Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge](<https://www.sota2.com/research/paper/69cdf7ff0636e5bf4afcca5e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-03T05:00:04.568Z

Authors: Jinrong Zhang, Canyang Wu, Xusheng He, Weili Guan, Jianlong Wu, Liqiang Nie

Published: 2026-04-01T02:23:23.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Video Object Segmentation on MOSE v2 (test)](<https://www.sota2.com/research/sota/video-object-segmentation-on-mose-v2-test.md>): Video Object Segmentation; MOSE v2 (test); J&F Score: 56.91.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.00395>)

[PDF](<https://arxiv.org/pdf/2604.00395.pdf>)
