分离目标识别与追踪，提升视频目标分割的准确性和一致性。
Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
- 先选关键帧确定目标，再专用模块追踪全程
- 在多个数据集上超越现有方法，提升显著
- 适合需要精准定位和稳定追踪的应用场景
指代式视频对象分割旨在通过自然语言提示分割并追踪视频中的目标对象。现有方法通常高度耦合地融合视觉与文本特征，共同生成每帧掩码，但在存在多个相似物体时易出现目标识别模糊，且难以保证跨帧掩码的一致性。为此，本文提出FindTrack，一种高效的解耦框架，将目标识别与掩码传播分离。FindTrack首先通过平衡分割置信度与视觉-文本对齐度，自适应选择关键帧，建立可靠的参考；随后由专用传播模块在全视频范围内追踪并分割目标。解耦设计有效减少目标关联歧义，提升分割一致性。FindTrack在多个公开基准上显著优于现有方法，证明其优越性。
原文摘要 · Abstract (English)
Referring video object segmentation aims to segment and track a target object in a video using a natural language prompt. Existing methods typically fuse visual and textual features in a highly entangled manner, processing multi-modal information together to generate per-frame masks. However, this approach often struggles with ambiguous target identification, particularly in scenes with multiple similar objects, and fails to ensure consistent mask propagation across frames. To address these limitations, we introduce FindTrack, an efficient decoupled framework that separates target identification from mask propagation. FindTrack first adaptively selects a key frame by balancing segmentation confidence and vision-text alignment, establishing a robust reference for the target object. This reference is then utilized by a dedicated propagation module to track and segment the object across the entire video. By decoupling these processes, FindTrack effectively reduces ambiguities in target association and enhances segmentation consistency. FindTrack significantly outperforms all existing methods on public benchmarks, demonstrating its superiority.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。