Transferable Interactiveness Knowledge for Human-Object Interaction Detection

TL;DR

This paper introduces a transferable interactiveness network that learns general human-object interaction knowledge across datasets, significantly improving HOI detection performance by filtering non-interactions before classification.

Contribution

The paper proposes a novel Interactiveness Network that captures general interactiveness knowledge, enhancing HOI detection models' accuracy and transferability across datasets.

Findings

Outperforms state-of-the-art HOI detection methods on HICO-DET and V-COCO datasets.

Demonstrates effective transfer of interactiveness knowledge across different HOI datasets.

Validates the generalization ability of the interactiveness network in diverse scenarios.

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 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.