3 papers
cs.CV2025
Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision
David C. Jeong, Aditya Puranik, James Vong +5
Egocentric human body estimation allows for the inference of user body pose and shape from a wearable camera's first-person perspective. Although research has used pose estimation…
cs.CV2023
SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentation
David C. Jeong, Hongji Liu, Saunder Salazar +2
While recent two-stage many-to-one deep learning models have demonstrated great success in 3D human pose estimation, such models are inefficient ways to detect 3D key points in a s…
cs.CV2023
MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection
David C. Jeong, Tianma Shen, Hongji Liu +4
Emotion detection presents challenges to intelligent human-robot interaction (HRI). Foundational deep learning techniques used in emotion detection are limited by information-const…