DRG: Dual Relation Graph for Human-Object Interaction Detection
It addresses a challenging problem in computer vision for applications like scene understanding, but appears incremental as it builds on existing HOI detection approaches.
The paper tackles human-object interaction detection by introducing a dual relation graph that aggregates spatial-semantic context to resolve ambiguity, achieving favorable results compared to state-of-the-art methods on two large-scale benchmarks.
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.