Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
CVPR 2018
Yiru Shen, Chen Feng, Yaoqing Yang, and Dong Tian

Proposed two operations on 3D point cloud semantic understanding: kernel correlation and graph pooling, and achieved competitive results in applications of object classification and part segmentation.

Foldingnet: Point cloud auto-encoder via deep grid deformation
CVPR 2018, Spotlight
Yaoqing Yang, Chen Feng, Yiru Shen, and Dong Tian

Proposed a novel framework for 3D point cloud reconstruction using deep auto-encoder. Our method is simple and efficient, and achieves state-of-the-art for linear transfer classification in ModelNet40 dataset (6/19/2018).

Assessing the Accuracy of a Wrist Motion Tracking Method for Counting Bites across Demographic and Food Variables
IEEE Journal of Biomedical and Health Informatics (JBHI), 2017
Yiru Shen, James Salley, Eric Muth, and Adam Hoover

Described a study to test the accuracy of a method that tracks wrist motion during eating to detect and count bites. The purpose was to assess its accuracy across demographic (age, gender, ethnicity) and bite (utensil, container, hand used, food type) variables.

A Study of the Lexicography of Hand Gestures During Eating
Yiru Shen, Eric Muth, and Adam Hoover

Established objective and repeatable gesture definitions based on discernible intent. Such a standard would support the sharing of data and results between researchers working on the problem of automatic monitoring of dietary intake. We defined five gestures: taking a bite of food (bite), sipping a drink of liquid (drink), manipulating food for preparation of intake (utensiling), not moving (rest) and a non-eating category (other).