This work proposes a novel attentive graph neural network (AGNN) for zero-shot video object segmentation (ZVOS). The suggested AGNN recasts this task as a process of iterative information fusion over video graphs. Specifically, AGNN builds a fully connected graph to efficiently represent frames as nodes, and relations between arbitrary frame pairs as edges. The underlying pair-wise relations are described by a differentiable attention mechanism. Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation. Experimental results on three video segmentation datasets show that AGNN sets a new state-of-the-art in each case. To further demonstrate the generalizability of our framework, we extend AGNN to an additional task: image object co-segmentation (IOCS). We perform experiments on two famous IOCS datasets and observe again the superiority of our AGNN model. The extensive experiments verify that AGNN is able to learn the underlying semantic/appearance relationships among video frames or related images, and discover the common objects.

中文翻译：

---

通过注意力图神经网络进行零镜头视频对象分割

这项工作提出了一种用于零镜头视频对象分割 (ZVOS) 的新型注意力图神经网络 (AGNN)。建议的 AGNN 将此任务重新定义为视频图上的迭代信息融合过程。具体来说，AGNN 构建了一个全连接图来有效地将帧表示为节点，将任意帧对之间的关​​系表示为边。潜在的成对关系由可微分注意机制描述。通过参数化消息传递，AGNN 能够有效地捕捉和挖掘视频帧之间更丰富和更高阶的关系，从而能够更完整地理解视频内容和更准确的前景估计。三个视频分割数据集的实验结果表明，AGNN 在每种情况下都设置了新的最新技术。为了进一步证明我们框架的通用性，我们将 AGNN 扩展到一个附加任务：图像对象共同分割（IOCS）。我们在两个著名的 IOCS 数据集上进行了实验，并再次观察了我们的 AGNN 模型的优越性。大量的实验验证了 AGNN 能够学习视频帧或相关图像之间的底层语义/外观关系，并发现共同的对象。