Multi-human Parsing with a Graph-based Generative Adversarial Model

doi:10.1145/3418217

Multi-human Parsing with a Graph-based Generative Adversarial Model

2021-04-16

19

OA

AI

DOI：10.1145/3418217

Save

View PDF

Abstract

En 中文

Human parsing is an important task in human-centric image understanding in computer vision and multimedia systems. However, most existing works on human parsing mainly tackle the single-person scenario, which deviates from real-world applications where multiple persons are present simultaneously with interaction and occlusion. To address such a challenging multi-human parsing problem, we introduce a novel multi-human parsing model named MI-I-Parser, which uses a graph-based generative adversarial model to address the challenges of close-person interaction and occlusion in multi-human parsing. To validate the effectiveness of the new model, we collect a new dataset named Multi-Human Parsing (MHP), which contains multiple persons with intensive person interaction and entanglement. Experiments on the new MHP dataset and existing datasets demonstrate that the proposed method is effective in addressing the multi-human parsing problem compared with existing solutions in the literature.

Keywords:

Human parsing

multi-human parsing

human-centric image analysis

generative adversarial networks

graph convolution network

Multi-human Parsing with a Graph-based Generative Adversarial Model

Abstract

AI Summary

Journal

Organization