论文标题
DRG：人类对象相互作用检测的双关系图
DRG: Dual Relation Graph for Human-Object Interaction Detection
论文作者
论文摘要
我们解决了人类对象相互作用（HOI）检测的具有挑战性的问题。现有方法要么孤立地识别每个人类对象对的相互作用，要么基于复杂的外观特征执行关节推断。在本文中，我们利用抽象的空间语义表示来描述每个人类对象对，并通过双重关系图（一个以人为中心的对象和一个对象）来汇总场景的上下文信息。我们提出的双重关系图有效地捕获了场景中的歧视性线索，以解决本地预测中的歧义。我们的模型在概念上很简单，与两个大规模基准数据集上的最新HOI检测算法相比，您的模型可取得优惠的结果。
We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features. In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph (one human-centric and one object-centric). Our proposed dual relation graph effectively captures discriminative cues from the scene to resolve ambiguity from local predictions. Our model is conceptually simple and leads to favorable results compared to the state-of-the-art HOI detection algorithms on two large-scale benchmark datasets.
