Conditional Adversarial Architecture (CAA)

From
Revision as of 22:28, 17 October 2018 by BPeat (talk | contribs)
Jump to: navigation, search

YouTube search...

Massachusetts Institute of Technology (MIT) & Massachusetts General Hospital

Occlusion is a fundamental problem in human pose estimation and many other vision tasks. Instead of hallucinating missing body parts based on visible ones, we demonstrate a solution that leverages radio signals to accurately track the 2D human pose through walls and obstructions. Through-Wall Human Pose Estimation Using Radio Signals | Mingmin Zhao, Tianhong Li, Mohammad Abu, Alsheikh Yonglong, Tian Hang Zhao, Antonio Torralba, Dina Katabi - MIT CSAIL

Our-teacher-student-network-model-used-in-RF-Pose-The-upper-pipeline-provides-training.png