Multiview Supervision By Registration

2018/11/27 by Yilun Zhang, Zhang, Yilun, Hyun Soo Park +1
Computer Science · #Video Surveillance and Tracking Methods #Advanced Vision and Imaging #Human Pose and Action Recognition

paper · pdf · doi:10.48550/arxiv.1811.11251

Abstract

This paper presents a semi-supervised learning framework to train a keypoint detector using multiview image streams given the limited labeled data (typically

Citations

• On Information and Sufficiency
• Random sample consensus

Related

• Semi-supervised Dense Keypoints Using Unlabeled Multiview Images
• MONET: Multiview Semi-supervised Keypoint Detection via Epipolar Divergence
• GoodPoint: unsupervised learning of keypoint detection and description
• Co-Learning: Towards Semi-Supervised Object Detection with Road-side Cameras
• A Detector-oblivious Multi-arm Network for Keypoint Matching