SNNs for Human Pose Estimation (or something like that)

Human Pose Estimation task is extremely challenging with event-driven cameras. We have been able to do it with an ANN approach but we are curious how would we go about approaching with an SNN. It's a 13 point skeleton regression problem with 2D pose from a single camara, in the camera reference frame. We have the popular Human 3.6m video dataset's event converted version in good quality (spatial and temporal resolution) and DHP19, in the same format. 

This can be either an implementation or a discussion about possibilities.

Go to group wiki Go to wiki users Info


Day Time Location
Mon, 08.05.2023 15:00 - 16:00 Lobby
Tue, 02.05.2023 15:00 - 16:00 Open air area near lobby
Fri, 05.05.2023 14:00 - 15:00 Lobby
Tue, 09.05.2023 15:00 - 16:00 Lobby


Gaurvi Goyal