Transferable Interactiveness Knowledge for Human-Object Interaction Detection
This addresses the challenge of accurately detecting interactions in computer vision, offering a transferable solution that enhances HOI detection models, though it is incremental as it builds on prior methods.
The paper tackles the problem of Human-Object Interaction (HOI) Detection by introducing Interactiveness Knowledge to determine if humans and objects interact, which can be learned across datasets and integrated with existing models. It achieves state-of-the-art results on HICO-DET and V-COCO datasets, with significant performance improvements.
Human-Object Interaction (HOI) Detection is an important problem to understand how humans interact with objects. In this paper, we explore Interactiveness Knowledge which indicates whether human and object interact with each other or not. We found that interactiveness knowledge can be learned across HOI datasets, regardless of HOI category settings. Our core idea is to exploit an Interactiveness Network to learn the general interactiveness knowledge from multiple HOI datasets and perform Non-Interaction Suppression before HOI classification in inference. On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results. We extensively evaluate the proposed method on HICO-DET and V-COCO datasets. Our framework outperforms state-of-the-art HOI detection results by a great margin, verifying its efficacy and flexibility. Code is available at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network.