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 HICODET 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 avail- able at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPR.2019.00370 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | ISSN |
Computer vision,Computer science,Artificial intelligence | Conference | 1063-6919 |
Citations | PageRank | References |
13 | 0.51 | 0 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yonglu Li | 1 | 22 | 7.05 |
Siyuan Zhou | 2 | 49 | 7.27 |
Xijie Huang | 3 | 19 | 2.26 |
Liang Xu | 4 | 19 | 2.26 |
Ze Ma | 5 | 13 | 0.84 |
Haoshu Fang | 6 | 57 | 6.86 |
Yanfeng Wang | 7 | 59 | 16.46 |
Cewu Lu | 8 | 993 | 62.08 |