Details for entry MaskR-CNN

Short Name:
MaskR-CNN
Long Name:
Mask R-CNN
Use MPII Pose for training:
no
Use COCO for training:
yes
Use external training:
no
Use multiple frames for pose estimation:
no
Predict pose tracks:
no
URL:
https://arxiv.org/pdf/1703.06870.pdf
Description:
without fine-tuning. using the official code-base: https://github.com/facebookresearch/Detectron model: e2e_keypoint_rcnn_R-101-FPN_s1x.yaml head box, head top, and neck are set using other detections, i.e. ears, eyes, shoulders.
Bibtex:
Specs:
GeForce GTX 1080 Ti
Runtime:
1.5
Open Source:
yes
Number of submissions:
yes
Last Submission:
2018-04-13 12:27:54
Published:
2018-04-13 12:33:50

Imprint | Data Protection


© PoseTrack