论文标题
人体对象互动检测的上下文异质图网络
Contextual Heterogeneous Graph Network for Human-Object Interaction Detection
论文作者
论文摘要
人类对象相互作用（HOI）检测是理解人类活动的重要任务。图形结构适合表示场景中的HOI。由于人与物体之间存在从属 - - 人类扮演主观角色和对象在HOI中起着客观的作用，因此现场中均质实体与异质实体之间的关系也不应同样相同。但是，以前的图形模型将人类和对象视为相同的节点，并且不认为不同实体之间的消息并不相同。在这项工作中，我们通过提出一个异质图网络来解决HOI任务的问题，该图形网络将人类和对象建模为各种节点，并在异质节点之间的均质节点和类间消息之间结合类内的消息。此外，利用了基于类内部环境和阶级上下文的图形注意机制来改善学习。在基准数据集V-Coco和Hico-Det上进行的大量实验表明，阶级和类间消息在HOI检测中非常重要，并验证了我们方法的有效性。
Human-object interaction(HOI) detection is an important task for understanding human activity. Graph structure is appropriate to denote the HOIs in the scene. Since there is an subordination between human and object---human play subjective role and object play objective role in HOI, the relations between homogeneous entities and heterogeneous entities in the scene should also not be equally the same. However, previous graph models regard human and object as the same kind of nodes and do not consider that the messages are not equally the same between different entities. In this work, we address such a problem for HOI task by proposing a heterogeneous graph network that models humans and objects as different kinds of nodes and incorporates intra-class messages between homogeneous nodes and inter-class messages between heterogeneous nodes. In addition, a graph attention mechanism based on the intra-class context and inter-class context is exploited to improve the learning. Extensive experiments on the benchmark datasets V-COCO and HICO-DET demonstrate that the intra-class and inter-class messages are very important in HOI detection and verify the effectiveness of our method.
