A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection

Manli Zhu, Edmond S. L. Ho, Hubert P. H. Shum

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Detecting human-object interactions is essential for comprehensive understanding of visual scenes. In particular, spatial connections between humans and objects are important cues for reasoning interactions. To this end, we propose a skeleton-aware graph convolutional network for human-object interaction detection, named SGCN4HOI. Our network exploits the spatial connections between human keypoints and object keypoints to capture their fine-grained structural interactions via graph convolutions. It fuses such geometric features with visual features and spatial configuration features obtained from human-object pairs. Furthermore, to better preserve the object structural information and facilitate human-object interaction detection, we propose a novel skeleton-based object keypoints representation. The performance of SGCN4HOI is evaluated in the public benchmark V-COCO dataset. Experimental results show that the proposed approach outperforms the state-of-the-art pose-based models and achieves competitive performance against other models.
Original languageEnglish
Title of host publication2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Place of PublicationPiscataway, US
PublisherIEEE
ISBN (Electronic)9781665452588
ISBN (Print)9781665452595
DOIs
Publication statusPublished - 9 Oct 2022

Publication series

Name2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
PublisherIEEE
ISSN (Print)1062-922X
ISSN (Electronic)2577-1655

Cite this