Pith. sign in

https://github.com/matterport/Mask RCNN (2017)

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

Learning to Train with Synthetic Humans

cs.CV · 2019-08-02 · conditional · novelty 5.0

Synthetic humans improve multi-person pose estimation mainly through extra occlusion; masking their losses beats using their labels, and a teacher-guided sampler adds a small extra gain.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning to Train with Synthetic Humans cs.CV · 2019-08-02 · conditional · none · ref 2

    Synthetic humans improve multi-person pose estimation mainly through extra occlusion; masking their losses beats using their labels, and a teacher-guided sampler adds a small extra gain.