DJW cdece0b32a 第一次提交 | 10 months ago | |
---|---|---|
.. | ||
onehand10k | 10 months ago | |
rhd2d | 10 months ago | |
README.md | 10 months ago |
Top-down methods divide the task into two stages: object detection, followed by single-object pose estimation given object bounding boxes. At the 2nd stage, regression based methods directly regress the keypoint coordinates given the features extracted from the bounding box area, following the paradigm introduced in Deeppose: Human pose estimation via deep neural networks.
Results on OneHand10K val set
Model | Input Size | PCK@0.2 | AUC | EPE | Details and Download |
---|---|---|---|---|---|
ResNet-50 | 256x256 | 0.990 | 0.485 | 34.21 | resnet_onehand10k.md |
Results on RHD test set
Model | Input Size | PCK@0.2 | AUC | EPE | Details and Download |
---|---|---|---|---|---|
ResNet-50 | 256x256 | 0.988 | 0.865 | 3.32 | resnet_rhd2d.md |