Add stronger/light detectors and the mobile pose.The main contributors are listed in doc/contributors.md. Currently, it is maintained by Jiefeng Li*, Hao-shu Fang*, Yuliang Xiu and Chao Xu. If it can not solve your problems or if you find any bugs, don't hesitate to comment on GitHub or make a pull request! ContributorsĪlphaPose is based on RMPE(ICCV'17), authored by Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai and Cewu Lu, Cewu Lu is the corresponding author. More detailed inference options and examples, please refer to GETTING_STARTED.md Common issue & FAQĬheck out faq.md for faq. It is the first open-source online pose tracker that achieves both 60+ mAP (66.5 mAP) and 50+ MOTA (58.3 MOTA) on PoseTrack Challenge dataset.ĪlphaPose supports both Linux and Windows!
To match poses that correspond to the same person across frames, we also provide an efficient online pose tracker called Pose Flow. Sep 2018: v0.2.0 version of AlphaPose is released! It runs at 20 fps on COCO validation set (4.6 people per image on average) and achieves 71 mAP!ĪlphaPose is an accurate multi-person pose estimator, which is the first open-source system that achieves 70+ mAP (75 mAP) on COCO dataset and 80+ mAP (82.1 mAP) on MPII dataset.Dec 2018: General version of PoseFlow is released! 3X Faster and support pose tracking results visualization!.Feb 2019: CrowdPose is integrated into AlphaPose Now!.Apr 2019: MXNet version of AlphaPose is released! It runs at 23 fps on COCO validation set.Dec 2019: v0.3.0 version of AlphaPose is released! Smaller model, higher accuracy!.