Stacked hourglass network

Published

Sep 17, 2016

Stacked hourglass network is an AI model developed by University of Michigan (United States), first published in September 2016. It works in the vision domain, on tasks such as pose estimation.

Epoch AI has no training-compute estimate for this model. It was trained on roughly 802.8M datapoints.

The reference paper has 5,316 citations.

Full record

Organization: University of Michigan
Country of organization: United States
Domain: Vision
Task: Pose estimation
Dataset size: 802.8M
Numerical format: FP32
Citations: 5,316