Skip to Content

MPHOI rgb. Part 3 of 4 [dataset] Open Access

Human-Object Interaction (HOI) recognition in videos is important for analyzing human activity. Most existing work focusing on visual features usually suffer from occlusion in the real-world scenarios. Such a problem will be further complicated when multiple people and objects are involved in HOIs. Consider that geometric features such as human pose and object position provide meaningful information to understand HOIs, we argue to combine the benefits of both visual and geometric features in HOI recognition, and propose a novel Two-level Geometric feature-informed Graph Convolutional Network (2G-GCN). The geometric-level graph models the interdependency between geometric features of humans and objects, while the fusion-level graph further fuses them with visual features of humans and objects. To demonstrate the novelty and effectiveness of our method in challenging scenarios, we propose a new multi-person HOI dataset (MPHOI-72). Extensive experiments on MPHOI-72 (multi-person HOI), CAD-120 (single-human HOI) and Bimanual Actions (two-hand HOI) datasets demonstrate our superior performance compared to state-of-the-arts.


Resource type
Creator: Shum, Hubert P. H. 1
Editor: Shum, Hubert P. H. 1
Editor: Li, Frederick W. B. 1
Editor: Qiao, Tanqiu 1
Creator: Qiao, Tanqiu 1
1 Durham University, UK
Research methods
Other description
Code published on GitHub:

Human-object interaction
Graph convolution neural networks
Feature fusion, multi-person interaction
Multi-person interaction
Cited in
Creative Commons Attribution 4.0 International (CC BY)

Durham University
Date Created

File Details

T. Qiao
Date Uploaded
Date Modified
3 August 2022, 09:08:47
Audit Status
Audits have not yet been run on this file.
not yet characterized
Activity of users you follow
User Activity Date
User N. Syrotiuk has updated MPHOI rgb. Part 3 of 4 [dataset] over 1 year ago
User N. Syrotiuk has updated MPHOI rgb part3 [dataset] over 1 year ago
User N. Syrotiuk has updated MPHOI rgb part3 [dataset] over 1 year ago