we propose a series of compositional approach to address the long-tailed, few-shot and zero-shot issues on HOI detection. The page gives a brief introduction to those works

We devise a deep Visual Compositional Learning (VCL) framework, which is a simple yet efficient framework to effectively address this problem. VCL first decom- poses an HOI representation into object and verb specific features, and then composes new interaction samples in the feature space via stitching the decomposed features. The integration of decomposition and compo- sition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection.

HOI detection usually suffers from the open long-tailed nature of interactions with objects, while human has extremely powerful compositional perception ability to cognize rare or unseen HOI samples. Inspired by this, we devise a novel HOI compositional learning framework, termed as Fabricated Compositional Learning (FCL), to address the problem of open long-tailed HOI detection. Specifically, we introduce an object fabricator to generate effective object representations, and then combine verbs and fabricated objects to compose new HOI samples. With the proposed object fabricator, we are able to generate large-scale HOI samples for rare and unseen categories to alleviate the open long-tailed issues in HOI detection.