Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos

TL;DR

This paper introduces a novel graph convolutional network that combines geometric and visual features for improved multi-person human-object interaction recognition in videos, especially under occlusion.

Contribution

It proposes a two-level graph model that integrates geometric and visual features, and introduces a new dataset for multi-person HOI recognition.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effective in scenarios with occlusion and multiple interacting persons

Demonstrates the benefit of combining geometric and visual features

Abstract

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.