The goal of video segmentation is to accurately segment and track every pixel in diverse scenarios. In this paper, we present Tube-Link, a versatile framework that addresses multiple core tasks of video segmentation with a unified architecture. Our framework is a near-online approach that takes a short subclip as input and outputs the corresponding spatial-temporal tube masks. To enhance the modeling of cross-tube relationships, we propose an effective way to perform tube-level linking via attention along the queries. In addition, we introduce temporal contrastive learning to instance-wise discriminative features for tube-level association. Our approach offers flexibility and efficiency for both short and long video inputs, as the length of each subclip can be varied according to the needs of datasets or scenarios. Tube-Link outperforms existing specialized architectures by a significant margin on five video segmentation datasets. Specifically, it achieves almost 13% relative improvements on VIPSeg and 4% improvements on KITTI-STEP over the strong baseline Video K-Net. When using a ResNet50 backbone on Youtube-VIS-2019 and 2021, Tube-Link boosts IDOL by 3% and 4%, respectively. Code will be available.

翻译：视频分割的目标是在多样化的场景中精确分割并追踪每一个像素。本文提出Tube-Link，一个以统一架构解决视频分割多项核心任务的通用框架。我们的框架采用准在线方式，以短子片段作为输入，输出对应的时空管状掩码。为增强跨管关系建模能力，我们提出一种有效方法，通过沿查询维度的注意力机制实现管级链接。此外，我们引入时序对比学习，为实例级判别特征进行管级关联。该方法对短视频和长视频输入均具备灵活性与高效性，子片段的长度可根据数据集或场景需求动态调整。在五个视频分割数据集上，Tube-Link显著超越现有专用架构，具体而言，相较于强基线Video K-Net，它在VIPSeg上实现了近13%的相对提升，在KITTI-STEP上提升4%；在Youtube-VIS-2019与2021数据集上采用ResNet50主干网络时，Tube-Link分别将IDOL的性能提升了3%与4%。代码将开源。