Enhanced Two-stage Multi-Person Pose Estimation

Hiroto Honda, Tomohiro Kato, Yusuke Uchida; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

Abstract


In this paper we introduce an enhanced multi-person pose estimation method for the competition of the PoseTrack [6] workshop in ECCV 2018. We employ a two-stage human pose detector, where human region detection and keypoint detection are separately performed. A strong encoder-decoder network for keypoint detection has achieved 70.4% mAP for PoseTrack 2018 validation dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Honda_2018_ECCV_Workshops,
author = {Honda, Hiroto and Kato, Tomohiro and Uchida, Yusuke},
title = {Enhanced Two-stage Multi-Person Pose Estimation},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}