Re-Mine, Learn and Reason: Exploring the Cross-Modal Semantic Correlations for Language-Guided HOI Detection

Abstract

Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict <human, action, object> triplets. Despite the challenges posed by the numerous interaction combinations, they also offer opportunities for multi-modal learning of visual texts. In this paper, we present a systematic and unified framework (RmLR) that enhances HOI detection by incorporating structured text knowledge. Firstly, we qualitatively and quantitatively analyze the loss of interaction information in the two-stage HOI detector and propose a re-mining strategy to generate more comprehensive visual representation. Secondly, we design more fine-grained sentence- and word-level alignment and knowledge transfer strategies to effectively address the many-to-many matching problem between multiple interactions and multiple texts. These strategies alleviate the matching confusion problem that arises when multiple interactions occur simultaneously, thereby improving the effectiveness of the alignment process. Finally, HOI reasoning by visual features augmented with textual knowledge substantially improves the understanding of interactions. Experimental results illustrate the effectiveness of our approach, where state-of-the-art performance is achieved on public benchmarks.