Transferable Interactiveness Knowledge for Human-Object Interaction Detection

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.

arXiv commentCVPR2019

Cited by in corpus (7)

• SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network
• Learning Human-Object Interaction Detection using Interaction Points
• ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos
• Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
• QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
• Intra- and Inter-Action Understanding via Temporal Action Parsing
• Effective Actor-centric Human-object Interaction Detection