ML Anthology

Enhanced Two-Stage Multi-Person Pose Estimation

Hiroto Honda, Tomohiro Kato, Yusuke Uchida
ECCVW 2018 pp. 217-220
doi:10.1007/978-3-030-11012-3_18 /eccvw/2018/honda2018eccvw-enhanced/

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.

PDF ECCVW Semantic Scholar

Cite

Text

Honda et al. "Enhanced Two-Stage Multi-Person Pose Estimation." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11012-3_18

Markdown

[Honda et al. "Enhanced Two-Stage Multi-Person Pose Estimation." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/honda2018eccvw-enhanced/) doi:10.1007/978-3-030-11012-3_18

BibTeX

@inproceedings{honda2018eccvw-enhanced,
  title     = {{Enhanced Two-Stage Multi-Person Pose Estimation}},
  author    = {Honda, Hiroto and Kato, Tomohiro and Uchida, Yusuke},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {217-220},
  doi       = {10.1007/978-3-030-11012-3_18},
  url       = {https://mlanthology.org/eccvw/2018/honda2018eccvw-enhanced/}
}