Efficient Pose looks very interesting - it seems to be fast and can generate decent frame rates in "real time". I'm not confident in the accuracy claims compared to OpenPose though, and given that it can only track a single person and is nowhere near as established as Openpose it may only have a niche usefulness. Worth a look though:

The article: 
link.springer.com/article/10.1007/s10489-020-01918-7

The github:
github.com/daniegr/EfficientPose

I need to check out the more advanced models on pre-recorded data, I've only played with the real-time options and frozen it up trying to run model IV.

I found the installation to be a little tricky, using the method on the git page didn't work for me and I had to do a fresh install of the different packages. It can only run in Python 3.6 it seems, anything earlier or later is not compatible with the required tensorflow etc. 

Essentially I just opened the "requirements.txt" file and did a pip install of each one individually. For the Torch I had to remove the edition number to make it work.  

​The Openpose demo is great:
https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/demo_quick_start.md#faq
 
https://github.com/CMU-Perceptual-Computing-Lab/openpose/releases
 
The following is relevant to my computer. It’s now very simple to test and save data from openpose.

1. Open PowerShell
2. Type this in to set the correct directory:

PS D:\DOWNLOADS BACKUP> CD "d:\DOWNLOADS BACKUP\OPENPOSE"

1. Type this in to run openpose on the webcam

PS D:\DOWNLOADS BACKUP\OPENPOSE> bin\OpenPoseDemo.exe

1. If you want to save the skeleton data to a json file type this:

bin\OpenPoseDemo.exe --write_json output_jsons/
 
A description of the json file format is here:
https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/output.md#pose-output-format-body_25
 
**To close it you need to close the powershell itself.