DeRVOS：解耦一致轨迹生成与多模态理解用于指代视频目标分割
DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentation
将 RVOS 解耦为预训练实例轨迹生成与多模态理解两个分支，并用 TAIS 模块做跨帧对齐与隐式轨迹选择，为视频分割中轨迹一致性与语言对齐的分离建模提供了可复用范式。
原文依据 we propose DeRVOS, a framework that decouples RVOS into two key branches: consistent trajectory generation and multimodal understanding.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论指代视频目标分割（RVOS）旨在根据自然语言表达分割视频中的目标。与早期关注静态单目标场景的工作不同，近期研究处理更复杂的运动场景。先前方法通常采用基于查询的、逻辑多阶段流水线来处理这些场景。然而，这种范式从头学习轨迹一致性建模与多模态融合，常导致轨迹不一致和多模态理解不足。为解决这些局限，我们提出 DeRVOS，一个将 RVOS 解耦为两个关键分支的框架：一致轨迹生成和多模态理解。我们使用强大的预训练实例轨迹生成模型提取时间一致的目标表示，并通过统一多模态编码器进行跨模态对齐，从而实现轨迹一致性和视觉语言理解的上游建模。该设计将 RVOS 简化为建模指代表达与实例轨迹之间关系的任务。为连接两个分支并实现高效的运动感知语义理解，我们引入轨迹对齐与隐式选择（TAIS）模块，该模块逐步执行跨帧多模态对齐和运动引导的隐式轨迹选择。大量实验表明，DeRVOS 在传统 RVOS 基准和具有挑战性的 MeViS 数据集上均达到最优结果，超越基于 LVLM 的方法 4.7%。
英文原文摘要 1565 字符
Referring video object segmentation (RVOS) aims to segment objects within a video according to natural language expressions. Unlike earlier works focusing on static single-object scenarios, recent studies address more complex motion scenes. Previous methods typically adopt a query-based, logically multi-stage pipeline to handle these scenarios. However, this paradigm learns trajectory consistency modeling and multimodal fusion from scratch, which often leads to trajectory inconsistencies and insufficient multimodal understanding. To address these limitations, we propose DeRVOS, a framework that decouples RVOS into two key branches: consistent trajectory generation and multimodal understanding. We extract temporally consistent object representations using a powerful pretrained instance trajectory generation model and perform cross-modal alignment via a unified multimodal encoder, enabling upstream modeling of trajectory consistency and vision-language understanding. This design reduces RVOS to the task of modeling the relationship between referring expressions and instance trajectories. To connect the two branches and enable efficient motion-aware semantic understanding, we introduce the Trajectory Alignment and Implicit Selection (TAIS) module, which progressively performs cross-frame multimodal alignment and motion-guided implicit trajectory selection. Extensive experiments demonstrate that DeRVOS achieves state-of-the-art results on both traditional RVOS benchmarks and the challenging MeViS dataset, surpassing LVLM-based methods by 4.7%.