Transferable Interactiveness Knowledge for Human-Object Interaction Detection

25 Jan 2021  ·  Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Xijie Huang, Liang Xu, Cewu Lu ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Human-Object Interaction Detection HICO-DET TIN (TIPAMI) mAP 20.93 # 47
Human-Object Interaction Detection V-COCO TIN (TIPAMI) AP(S1) 49.1 # 28

Methods


No methods listed for this paper. Add relevant methods here