The recent transformer-based models have dominated the Referring Video Object
Segmentation (RVOS) task due to the superior performance. Most prior works
adopt unified DETR framework to generate segmentation masks in
query-to-instance manner. In this work, we integrate strengths of that leading
RVOS models to build up an effective paradigm. We first obtain binary mask
sequences from the RVOS models. To improve the consistency and quality of
masks, we propose Two-Stage Multi-Model Fusion strategy. Each stage rationally
ensembles RVOS models based on framework design as well as training strategy,
and leverages different video object segmentation (VOS) models to enhance mask
coherence by object propagation mechanism. Our method achieves 75.7% J&F on
Ref-Youtube-VOS validation set and 70% J&F on test set, which ranks 1st place
on 5th Large-scale Video Object Segmentation Challenge (ICCV 2023) track 3.
Code is available at this https URL

通过将 RVOS 模型与 Two-Stage Multi-Model Fusion 策略结合，提出了一种有效的模式，该模式在 Ref-Youtube-VOS 验证集上实现了 75.7% 的 J&F， 在测试集上实现了 70% 的 J&F，在第 5 届大规模视频对象分割挑战（ICCV 2023）的第 3 组中排名第一。