Transductive Decoupled Variational Inference for Few-Shot Classification

Towards Single Camera Kinematics Human 3D-Kinematics

Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple de-coupled steps …

Federated Learning With Taskonomy for Non-IID Data

Lookahead Adversarial Learning for Near Real-Time Semantic Segmentation

Gaze Estimation by Exploring Two-Eye Asymmetry

MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation