MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation.

Ehsan Asali Prashant Doshi Jin Sun

Published in: CoRR (2023)

Keyphrases

multi view
view invariant
action recognition
single view
multiple views
d objects

human actions
depth map
three dimensional
camera calibration
multiple viewpoints
dynamic scenes

computer vision
activity recognition
range images
semi supervised
surface reconstruction
body parts

visual hull
range data
partial occlusion
motion capture
view synthesis