cv

PhD

School of Interactive Computing, Georgia Institute of Technology

Computer Science

BS

UM-SJTU Joint Institute, Shanghai Jiao Tong University

Electrical and Computer Engineering

Embedded Software Engineer Intern

Bosch China

Deep Learning-based Gesture Recognition Algorithm Development

• Developed gesture recognition algorithms for Human-Vehicle Interaction using DNN.
• Applied the attention network to the neural network for dynamic gesture classification.
• Achieved 90% accuracy for 16 static gestures and 9 dynamic gestures on webcam with 720p@30fps.

Motion-based visual encoding can improve performance on perceptual tasks with dynamic time series

IEEE Visualization Conference (VIS 2024)

In this paper, We examine the effectiveness of staging and tracing in dynamic displays. Results showed that tracing and staging are preferred by participants, and improve their performance in mean and variance tasks respectively. They also preferred display time 3 times shorter when staging is used. Also, encoding animation speed with mean and variance in congruent tasks is associated with higher accuracy.

Hierarchical conversational preference elicitation with bandit feedback

Conference on Information and Knowledge Management 2022 (CIKM 2022)

This research proposed a hierarchical structure for the traditional UCB (Upper Confidence Bound) method. Meanwhile, sufficient mathematical proofs and extensive experiments have verified the hierarchical UCB as an improved algorithm.