Worker Posture Analysis
Benchmarking state-of-the-art pose estimation algorithms across camera configurations for real-world 3D human pose analysis.
Computer VisionPose EstimationModel BenchmarkingDeep Learning
Hi, I'm Jason Wang
Ph.D. Candidate in Data Science at the University of Virginia, building deep learning systems for computer vision and 3D human understanding.
Featured Research
Deep learning and computer vision research applied to real-world 3D understanding
3D Pose-to-Kinematics Mapping
We benchmark three state-of-the-art 3D pose estimation models on biomechanical joint angle accuracy and discover that models with lower MPJPE produce higher joint angle error — challenging a core assumption in the field.
Deep LearningBiomechanics3D Pose EstimationEvaluation MetricsComputer Vision
Tennis Serve Dataset & Analysis
A large-scale 3D pose estimation dataset of 5,966 professional tennis serves from broadcast video, enabling motion classification, player identification, and performance prediction using deep learning at unprecedented scale.
Computer VisionDatasetML PipelinePose Estimation3D ReconstructionClassification
Deep Learning for Pediatric Crohn's Disease
A deep learning approach for predicting pediatric Crohn's disease from histopathological whole slide images, with investigation of inter-site generalizability and site-specific artifact mitigation.
Deep LearningMedical ImagingHistopathologyCNNGrad-CAM
Research Focus
Computer Vision
Building and benchmarking state-of-the-art pose estimation and 3D reconstruction models
Deep Learning
Designing transformer and CNN architectures for 3D pose lifting, generative modeling, and domain adaptation
Applied AI
Deploying ML pipelines for large-scale video analysis, medical imaging, and human motion understanding