Get Started
Home
Topics
Search
Library
Research questionHow can clinical pose estimation remain reliable when preterm infants’ keypoint annotations are noisy?Self-occlusion and caregiver interference can make infant keypoints difficult to label accurately. These errors may distort models used to estimate spontaneous motility from clinical imagery.
AI
Computer Vision
Health
Image & Video Processing
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy AnnotationsThe evidence concerns pose estimation for preterm infants in real clinical videos, using the proprietary NeoPose dataset of 46 videos from 46 infants. It evaluates noisy-annotation scenarios across three pose-estimation architectures; the findings are limited to the studied dataset and settings.research paper · Sep 3, 2026
Related questions
How can neural map matchers learn accurate 3-DoF poses from noisy GPS positions and heading labels?How can post-hoc vision saliency remain faithful when image orientation changes?How can we interpret multimodal video model performance when benchmark label reliability is unknown?How can semi-supervised medical image segmentation prevent appearance variation from corrupting structural cues and pseudo-labels?