Portrait of Qing Yang

Qing Yang

Associate Professor
Department of Computer Science and Engineering
University of North Texas

Email qing dot yang at unt dot edu
Office 3940 N. Elm, Room F201, Denton, TX 76207

About

Qing Yang is an Associate Professor in the Department of Computer Science and Engineering at the University of North Texas (UNT). He received the Ph.D. degree in Computer Science from Auburn University in 2011, the M.E. degree in Computer Science from Harbin Institute of Technology in 2005, and the B.E. degree in Computer Science from Nankai University in 2003.

From 2011 to 2017, he was an Assistant Professor in the Department of Computer Science at Montana State University. He joined UNT as an Assistant Professor in 2017 and was promoted to Associate Professor in 2021. His research has been supported by the National Science Foundation, the U.S. Department of Energy, Toyota Motor North America, and the Army Research Laboratory.

News

Research

Connected and Autonomous Vehicles Internet of Things Network Security and Privacy

My current research centers on cooperative perception for connected and automated vehicles, vehicular edge computing, and privacy-preserving machine learning for intelligent transportation systems — spanning efficient multi-agent 3D perception, bandwidth-aware feature sharing, and trustworthy data sharing on the vehicular edge.

Featured Project

M³CAD: Multi-Vehicle, Multi-Task, Multi-Modality Cooperative Autonomous Driving Benchmark ICRA 2026

An open dataset for cooperative autonomous driving research: 204 sequences with 30K frames and 267K annotated instances, collected from 10–60 collaborating vehicles per sequence. Each vehicle carries six cameras, a 64-beam LiDAR, and GPS/IMU, with nuScenes-format annotations covering six tasks — object detection and tracking, mapping, motion forecasting, occupancy prediction, and path planning.

Get the Dataset Paper · Code

Demo: cooperative perception results on the M³CAD dataset.

dCAP: Dynamic Calibration and Articulated Perception for Autonomous Trucks CVPR 2026

Autonomous trucks are articulated at the fifth-wheel hitch, so camera extrinsics across the tractor-trailer rig change over time instead of staying fixed. dCAP is a vision-based framework that continuously estimates the 6-DoF relative pose between tractor and trailer cameras — with no static initialization required — enabling articulated-aware perception for end-to-end driving stacks. The project also releases STT4AT, a CARLA-based benchmark simulating semi-trailer trucks with synchronized multi-sensor suites.

Code & Dataset Paper

Overview of dCAP: dynamic calibration (top) and articulated perception pipeline (bottom) for autonomous trucks

dCAP vs. DUSt3R and VGGT on articulated tractor–trailer calibration (top); the articulated perception pipeline (bottom).

F-Cooper: Feature-Based Cooperative Perception for Autonomous Vehicle Edge Computing Using 3D Point Clouds Best Paper Award · SEC 2019

Sharing raw LiDAR data between vehicles costs about 4 MB per frame — far too much for real-time driving. F-Cooper instead shares compact CNN feature maps (as little as ~200 KB), fusing them across vehicles for 3D object detection. Feature fusion improves detection precision by ~10% within 20 meters and ~30% at longer ranges, with communication delays as low as 71 ms — making real-time cooperative perception on the vehicular edge practical.

Read the Paper

F-Cooper architecture: voxel feature fusion and spatial feature fusion paradigms for cooperative 3D object detection

The F-Cooper framework: two feature-fusion paradigms (VFF and SFF) for cooperative 3D object detection.

Selected Awards and Honors

Selected Publications

M3CAD: Towards Generic Cooperative Autonomous Driving Benchmark
M. Zhu, Y. Zhu, Y. Zhu, Q. Chen, D. Qu, S. Fu, and Q. Yang
Proc. IEEE International Conference on Robotics & Automation (ICRA), 2026. Accepted.
Mind the Hitch: Dynamic Calibration and Articulated Perception for Autonomous Trucks
M. Zhu, Y. Zhu, S. Fu, and Q. Yang
Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. Accepted.
GSOT3D: Towards Generic 3D Single Object Tracking in the Wild
Y. Jiao, Y. Li, J. Ding, Q. Yang, S. Fu, H. Fan, and L. Zhang
Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
Privacy-Preserving Driver Monitoring on the Edges: Transformer-Based Processing of Secret Shares from Video Streams
T. Bai, D. Shao, Y. He, Q. Yang, Y. Feng, and S. Fu
ACM Transactions on Internet of Things, vol. 7, no. 3, 2026.
Bringing Different Views Together: A Hybrid Cooperative Perception Framework for Connected Autonomous Vehicles
D. Carrillo, M. Nutt, M. Meijer, J. Khan, S. Fu, and Q. Yang
IEEE Network, 2025.
SiCP: Simultaneous Individual and Cooperative Perception for 3D Object Detection in Connected and Automated Vehicles
D. Qu, Q. Chen, T. Bai, H. Lu, H. Fan, H. Zhang, S. Fu, and Q. Yang
Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
HEAD: A Bandwidth-Efficient Cooperative Perception Approach for Heterogeneous Connected and Autonomous Vehicles
D. Qu, Q. Chen, Y. Zhu, Y. Zhu, S. S. Avedisov, S. Fu, and Q. Yang
Proc. European Conference on Computer Vision (ECCV), Springer, 2024.
F-Cooper: Feature Based Cooperative Perception for Autonomous Vehicle Edge Computing System using 3D Point Clouds Best Paper Award
Q. Chen, X. Ma, S. Tang, J. Guo, Q. Yang, and S. Fu
Proc. ACM/IEEE Symposium on Edge Computing (SEC), 2019.
Slim-FCP: Lightweight Feature-Based Cooperative Perception for Connected Automated Vehicles
J. Guo, D. Carrillo, Q. Chen, Q. Yang, S. Fu, H. Lu, and R. Guo
IEEE Internet of Things Journal, 2022.

Selected Grants

Student Advising

Ph.D. Graduates

  • Deyuan Qu (2025) — Toyota North America
  • Sudip Dhakal (2024) — Florida Gulf Coast University
  • Jingda Guo (2021) — HillStone Networks
  • Qi Chen (2020) — Toyota North America
  • Guangchi Liu (2017) — Southeastern University

Current Ph.D. Students

  • Dominic Carrillo
  • Michael Nutt
  • Mohammad Dehghani Tezerjani
  • Yongqi Zhu
  • Yihao Zhu
  • Morui Zhu
  • Xu Gao
  • Yongshuo Liu

Professional Service