Weakly-supervised Human-object Interaction Detection
Weakly-supervised Human-object Interaction Detection
复制标题
DOI：
10.5220/0010196802930300
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Masaki Sugimoto;Ryosuke Furuta;Y. Taniguchi
中科院分区：
文献类型：
--
作者：
Masaki Sugimoto;Ryosuke Furuta;Y. Taniguchi
人与物体交互检测是一种图像识别任务，检测图像中的成对（人和物体）并估计它们之间的关系，例如“握着”或“骑着”。基于监督学习的现有方法需要花费大量精力来创建训练数据，因为它们需要以人与物体的边界框（BB）以及表示关系的动词标签的形式提供监督。在本文中，我们扩展了提案聚类学习（PCL），这是一种弱监督的对象检测方法，用于一项称为弱监督人与对象交互检测的新任务，其中在训练期间仅将动词标签分配给整个图像（即不给出 BB）。实验表明，所提出的方法可以成功地学习检测人和物体的 BB 以及它们之间的动词标签，而无需实例级监督。
Human-Object Interaction detection is the image recognition task of detecting pairs (a person and an object) in an image and estimating the relationships between them, such as “holding” or “riding”. Existing methods based on supervised learning require a lot of effort to create training data because they need the supervision provided as Bounding Boxes (BBs) of people and objects and verb labels that represent the relationships. In this paper, we extend Proposal Cluster Learning (PCL), a weakly-supervised object detection method, for a new task called weakly-supervised human-object interaction detection, where only the verb labels are assigned to the entire images (i.e., no BBs are given) during the training. Experiments show that the proposed method can successfully learn to detect the BBs of people and objects and the verb labels between them without instance-level supervision.