A bottom-up pose estimator built by adding a deconvolution-based high-resolution feature pyramid to HRNet, trained with multi-resolution supervision and tested with heatmap aggregation, reports state-of-the-art COCO and CrowdPose results.
A unified multi-scale deep convolutional neural network for fast object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
A bottom-up pose estimator built by adding a deconvolution-based high-resolution feature pyramid to HRNet, trained with multi-resolution supervision and tested with heatmap aggregation, reports state-of-the-art COCO and CrowdPose results.