Transferable Interactiveness Knowledge for Human-Object Interaction Detection

TL;DR

This paper introduces a transferable interactiveness knowledge framework for human-object interaction detection, improving generalization across datasets and enhancing detection accuracy by leveraging hierarchical and consistency learning.

Contribution

It proposes a novel interactiveness network that learns generalizable interaction knowledge from multiple datasets and integrates it with HOI detection models.

Findings

Outperforms state-of-the-art HOI detection methods on multiple datasets.

Demonstrates effective transferability of interactiveness knowledge across datasets.

Utilizes hierarchical features and consistency tasks to improve interaction understanding.

Abstract

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 a human and an object interact with each other or not. We found that interactiveness knowledge can be learned across HOI datasets and bridge the gap between diverse 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 (NIS) before HOI classification in inference. On account of the generalization ability of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results. We utilize the human instance and body part features together to learn the interactiveness in hierarchical paradigm, i.e., instance-level and body part-level interactivenesses. Thereafter, a consistency task is proposed to guide the learning and extract deeper interactive visual clues. We extensively evaluate the proposed method on HICO-DET, V-COCO, and a newly constructed PaStaNet-HOI dataset. With the learned interactiveness, our method outperforms state-of-the-art HOI detection methods, verifying its efficacy and flexibility. Code is available at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network.