Difference between revisions of "Conditional Adversarial Architecture (CAA)"

Revision as of 22:47, 17 October 2018

@@ Line 4: / Line 4: @@
 * [http://sleep.csail.mit.edu/ Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture | Mingmin Zhao, Shichao Yue, Dina Katabi, Tommi Jaakkola, Matt Bianchi - Massachusetts Institute of Technology (MIT) & Massachusetts General Hospital]
 * [http://www.ncbi.nlm.nih.gov/pubmed/30180591 Entangled Conditional Adversarial Autoencoder for de Novo Drug Discovery | Polykovskiy D, Zhebrak A, Vetrov D, Ivanenkov Y, Aladinskiy V, Mamoshina P, Bozdaganyan M, Aliper A, Zhavoronkov A, Kadurin A]
-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. [http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhao_Through-Wall_Human_Pose_CVPR_2018_paper.pdf 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]
 https://www.researchgate.net/profile/Mingmin_Zhao3/publication/328049475/figure/fig2/AS:677681750351875@1538583328633/Our-teacher-student-network-model-used-in-RF-Pose-The-upper-pipeline-provides-training.png