Difference between revisions of "Occlusions"
(Created page with "[https://www.youtube.com/results?search_query=Occlusion+Deep+Learning+ YouTube search...] * Conditional Adversarial Architecture (CAA) AI Sees Through Walls <youtube>WTn...") |
|||
| Line 3: | Line 3: | ||
* [[Conditional Adversarial Architecture (CAA)]] AI Sees Through Walls | * [[Conditional Adversarial Architecture (CAA)]] AI Sees Through Walls | ||
| − | <youtube> | + | 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] |
| + | |||
| + | <youtube>kBFMsY5ZP0o</youtube> | ||
| + | <youtube>_l5Pi7XcNOo</youtube> | ||
Revision as of 21:46, 17 October 2018
- Conditional Adversarial Architecture (CAA) AI Sees Through Walls
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
