Multi-Instance Pose Networks (MIPNet)

[levan92]

trafficstars

Hi! Firstly, thank you for this wonderful library.

May I know if there are any plans to implement MIPNet in mmpose?

It is particularly useful to tackle data where there are crowded/highly occluded humans. Was previously the SOTA on OCHuman before ViTPose came along. Within the realms of convnets, it should still be the SOTA, and it seems like the idea is general enough to be applied to different types of backbones.

[jin-s13]

Thanks! We are sorry that we do not have enough resources to support all these awesome algorithms. Please vote here to raise its priority. We sincerely appreciate contributions from the community. If you are interested in reproducing this, please let us know.

[levan92]

Thanks for your prompt reply. Will add a comment there and vote!