Search Results for author:
Found 4 papers, 1 papers with code
Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency
We propose a novel loss function, multiview consistency, to enable adding additional training data with only 2D supervision.
SportsPose -- A Dynamic 3D sports pose dataset
Accurate 3D human pose estimation is essential for sports analytics, coaching, and injury prevention.
Was that so hard? Estimating human classification difficulty
In this paper, we introduce methods for estimating how hard it is for a doctor to diagnose a case represented by a medical image, both when ground truth difficulties are available for training, and when they are not.
Multi-modal data generation with a deep metric variational autoencoder
We present a deep metric variational autoencoder for multi-modal data generation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
