GPS: Group People Segmentation with Detailed Part Inference
Lists
Only you see this
Abstract
Noticeable progress has been witnessed in general object detection, semantic segmentation and instance segmentation, while parsing a group of people is still a challenging task for human-centric visual understanding due to severe occlusion and various poses. In this paper, we present a new large-scale dataset named “GPS (Group People Segmentation)” to boost academical study and technology development. GPS contains 14000 elaborately annotated images with 20 fine-grained semantic category labels related to human, divided into two sub-datasets corresponding to indoor and outdoor scenes involving various poses, occlusion and background. We further propose a novel GPSNet for group people segmentation. GPSNet consists of a new “Adjusted RoI Align” module to adjust position of detected person and align RoI features, such that the network does not need to fit various positions of each person. A fusion of global and local features is also employed to refine parsing results. Compared with baseline methods, GPSNet achieves the best performance on GPS Dataset.
BibTeX
@inproceedings{liao2019gps,
author = {Yue Liao and Si Liu and Tianrui Hui and Chen Gao and Yao Sun and Hefei Ling and Bo Li},
title = {{GPS: Group People Segmentation with Detailed Part Inference}},
booktitle = {ICME},
year = {2019},
doi = {10.1109/icme.2019.00112},
}Loading related content...