PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos.

Yufei Zhang Jeffrey O. Kephart Zijun Cui Qiang Ji

Published in: CoRR (2024)

Keyphrases

human activities
video sequences
fuzzy logic
image sequences
computer science
static images
dynamical systems
computer vision
view invariant
human subjects
optical flow
artificial intelligence
fault diagnosis
dynamic model
video clips
pose estimation
stereo camera
physical processes
model based tracking