Object Grounding via Iterative Context Reasoning
Object Grounding via Iterative Context Reasoning
复制标题
通过迭代上下文推理进行对象基础
DOI：
10.1109/iccvw.2019.00177
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Greg Mori
中科院分区：
文献类型：
--
作者：
Lei Chen;Mengyao Zhai;Jiawei He;Greg Mori
在本文中，我们解决了弱监督目标定位问题。对于从其描述中提取的图像和一组查询，目标是定位图像中的每个查询。在弱监督设置中，在训练时间不能访问地面实况查询停飞。提出了一种通过迭代上下文推理迭代更新查询表示和区域表示的弱监督对象基础的新方法。这种迭代的上下文细化逐渐解决了查询和区域中的歧义和含糊，从而有助于解决扎根方面的挑战。我们在两个具有挑战性的视频对象定位数据集上展示了我们提出的模型的有效性。
In this paper, we tackle the problem of weakly-supervised object grounding. For an image and a set of queries extracted from its description, the goal is to localize each query in the image. In a weakly-supervised setting, ground-truth query groundings are not accessible at training time. We propose a novel approach for weakly-supervised object grounding through iterative context reasoning in which we update query representations and region representations iteratively conditioning on each other. Such iterative contextual refinement gradually resolves ambiguity and vagueness in the queries and regions, thus helping to resolve challenges in grounding. We show the effectiveness of our proposed model on two challenging video object grounding datasets.