论文标题
通过负担能图零射的人类对象互动识别
Zero-Shot Human-Object Interaction Recognition via Affordance Graphs
论文作者
论文摘要
我们为在挑战性的环境中提出了一种新方法，用于零击的人类对象互动识别，涉及与看不见的动作相互作用（而不是仅仅看不见的作用和对象的组合）。我们的方法利用图形内容外部的知识以图形的形式使用，该图形对动作和对象之间的负担关系进行建模，即是否可以在给定对象上执行动作。我们提出了一个损失函数，目的是将图中包含的知识提炼到模型中，同时还使用图表来通过在潜在空间上施加局部结构来正规化学习的表示形式。我们在几个数据集（包括流行的HICO和HICO-DET）上评估了我们的方法，并表明它表现优于当前的艺术状态。
We propose a new approach for Zero-Shot Human-Object Interaction Recognition in the challenging setting that involves interactions with unseen actions (as opposed to just unseen combinations of seen actions and objects). Our approach makes use of knowledge external to the image content in the form of a graph that models affordance relations between actions and objects, i.e., whether an action can be performed on the given object or not. We propose a loss function with the aim of distilling the knowledge contained in the graph into the model, while also using the graph to regularise learnt representations by imposing a local structure on the latent space. We evaluate our approach on several datasets (including the popular HICO and HICO-DET) and show that it outperforms the current state of the art.
