Details for entry Miracle

Short Name:
Miracle
Long Name:
ByteDance AILab
Use MPII Pose for training:
no
Use COCO for training:
yes
Use external training:
yes
Use multiple frames for pose estimation:
no
Predict pose tracks:
yes
URL:
Description:
ByteDance AI Lab, Beijing, China; Author: Dongdong Yu(#), Kai Su(#), Jia Sun, Changhu Wang(*).# means contribute equally. * means corresponding author;Training data: COCO + Posetrack + AI challenge; For pose estimation, our approach uses only single frame. please cite: @inproceedings{yu2018multi, title={Multi-person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network}, author={Yu, Dongdong and Su, Kai and Sun, Jia and Wang, Changhu}, booktitle={European Conference on Computer Vision}, pages={221--226}, year={2018}, organization={Springer} }
Bibtex:
Specs:
Titan
Runtime:
1
Open Source:
no
Number of submissions:
4
Last Submission:
2018-08-31 17:52:07
Published:
0000-00-00 00:00:00

Imprint | Data Protection


© PoseTrack