Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS paradigm that explicitly models temporal instance consistency alongside the referring segmentation. Specifically, we introduce a novel hybrid memory that facilitates inter-frame collaboration for robust spatio-temporal matching and propagation. Features of frames with automatically generated high-quality reference masks are propagated to segment the remaining frames based on multi-granularity association to achieve temporally consistent R-VOS. Furthermore, we propose a new Mask Consistency Score (MCS) metric to evaluate the temporal consistency of video segmentation. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin, leading to top-ranked performance on popular R-VOS benchmarks, i.e., Ref-YouTube-VOS (67.1%) and Ref-DAVIS17 (65.6%).

翻译：视频目标指代分割（R-VOS）方法由于时间上下文的可变性及视觉相似物体的存在，在保持目标分割一致性方面面临挑战。我们提出了一种端到端的R-VOS范式，该范式在指代分割的同时显式建模时间实例一致性。具体而言，我们引入了一种新颖的混合记忆机制，通过帧间协作实现鲁棒的时空匹配与传播。基于自动生成的高质量参考掩码，通过多粒度关联对剩余帧进行特征传播与分割，从而实现时间一致性的R-VOS。此外，我们提出了一种新的掩码一致性分数（MCS）指标来评估视频分割的时间一致性。大量实验表明，我们的方法显著提升了时间一致性，在主流R-VOS基准测试（即Ref-YouTube-VOS达到67.1%，Ref-DAVIS17达到65.6%）中取得了顶级性能。