Series of work (ECCV2020, CVPR2021, CVPR2021, ECCV2022) about Compositional Learning for Human-Object Interaction Exploration

[ICLR 2022] RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

CVPR2021: Detecting Human-Object Interaction via Fabricated Compositional Learning

One-Stage HOI detection code: Visual Compositional Learning for Human-Object Interaction Detection (ECCV2020), Affordance Transfer Learning for Human-Object Interaction Detection (CVPR2021)