Multiple-Human Parsing in the Wild

19 May 2017  ·  Jianshu Li, Jian Zhao, Yunchao Wei, Congyan Lang, Yidong Li, Terence Sim, Shuicheng Yan, Jiashi Feng ·

Human parsing is attracting increasing research attention. In this work, we aim to push the frontier of human parsing by introducing the problem of multi-human parsing in the wild... Existing works on human parsing mainly tackle single-person scenarios, which deviates from real-world applications where multiple persons are present simultaneously with interaction and occlusion. To address the multi-human parsing problem, we introduce a new multi-human parsing (MHP) dataset and a novel multi-human parsing model named MH-Parser. The MHP dataset contains multiple persons captured in real-world scenes with pixel-level fine-grained semantic annotations in an instance-aware setting. The MH-Parser generates global parsing maps and person instance masks simultaneously in a bottom-up fashion with the help of a new Graph-GAN model. We envision that the MHP dataset will serve as a valuable data resource to develop new multi-human parsing models, and the MH-Parser offers a strong baseline to drive future research for multi-human parsing in the wild. read more

PDF Abstract

Datasets


Introduced in the Paper:

MHP

Used in the Paper:

COCO LIP

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multi-Human Parsing MHP v1.0 MH-Parser AP 0.5 50.10% # 3
Multi-Human Parsing MHP v2.0 MH-Parser AP 0.5 17.99% # 2

Methods


No methods listed for this paper. Add relevant methods here