Yuan wins best poster award at ICCV conference

by Nicole Capozziello

Published January 28, 2020

Junsong Yuan, associate professor in the Department of Computer Science and Engineering and director of the Visual Computing Lab, received an award for Best Poster at the 5th International HANDS workshop at the International Conference on Computer Vision (ICCV).

Junsong Yuan.

Junsong Yuan

The workshop, entitled Observing and Understanding Hands in Action, brought together researchers whose work focuses on 2D/3D hand detection, segmentation, pose estimation and tracking problems and its applications. The workshop was sponsored by Facebook Reality Labs and attracted participants from top universities around the world.

Yuan’s award-winning poster was entitled “A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image.” In it, Yuan and the research team proposed a simple yet effective approach, known as Anchor-to-Joint regression network (A2J), which showed promise in experiments using five different datasets. Real-time hand pose estimation plays a key role for applications such as hand gesture control, sign language understanding and virtual/augmented reality.

ICCV 2019 took place in Seoul, Korea from October 27 to November 2. Yuan presented six papers at the conference, including one oral presentation.