Paper Info
Title
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 and alleviate 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 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 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 HAKE-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 <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network</uri> .
Year
DOI
Venue
2022
10.1109/TPAMI.2021.3054048
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
DocType
Volume
Algorithms,Humans,Learning
Journal
44
Issue
ISSN
Citations 
7
0162-8828
0
PageRank 
References 
Authors
0.34
20
6
Name
Order
Citations
PageRank
Yonglu Li1227.05
Xinpeng Liu251.75
Xiaoqian Wu313.15
Xijie Huang4192.26
Liang Xu5192.26
Cewu Lu699362.08