2 papers
cs.CV2026
IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
Sunghyun Baek, Jaemyung Yu, Seunghee Koh +3
Test-time adaptation (TTA) has been widely explored to prevent performance degradation when test data differ from the training distribution. However, fully leveraging the rich repr…
cs.CV2021
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning
Hanbyel Cho, Yooshin Cho, Jaemyung Yu +1
Existing 3D human pose estimation algorithms trained on distortion-free datasets suffer performance drop when applied to new scenarios with a specific camera distortion. In this pa…