DJW cdece0b32a 第一次提交 10 months ago
..
onehand10k cdece0b32a 第一次提交 10 months ago
rhd2d cdece0b32a 第一次提交 10 months ago
README.md cdece0b32a 第一次提交 10 months ago

README.md

Top-down regression-based pose estimation

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 and Models

OneHand10K Dataset

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

RHD Dataset

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