Cong Ma’s Homepage

I am Cong Ma (马璁), and I obtained my Ph.D. degree from National Engineering Research Center of Visual Technology, Peking University in 2021 advised by Prof. Xiaodong Xie and Prof. Wen Gao. I completed my bachelor’s degree at School of Artificial Intelligence, Xidian University in 2016 supervised by Prof. Licheng Jiao. I received a visiting student researcher position at Stanford Vision and Learning Lab under the supervision of Prof. Silvio Savarese in 2020.

Currently, I am working at SenseAuto where I lead a team dedicated to researching the Roadside Holographic Intersection Perception Algorithm such as 2D/Monocular3D/Lidar3D Detection and Tracking, Multi-Sensor Tracking, Multi-Modality Representation, Trajectory Post-processing. Recently, I focus on World Model to simulate large-scale data for End-to-end Perception Model in Autonomous Driving Scenes.

In addition to this role, I also serves as the Chief Technical Adviser for projects involving Smart-Surveillance Systems, Intelligent Transportation and Vehicle-Infrastructure Cooperation. I am leading a team consisting of 4 full-time employees, two internships, and six students, who are all dedicated to advancing the field of our projects. Together, we have been actively involved in cutting-edge research.

I have published 18 top-tier academic papers and serve as a reviewer for journals and conferences such as ICCV, CVPR, ECCV, AAAI, IJCV, and TCSVT, and other venues, hold 10+ national patents, Additionally, in 2016, I was nominated for the prestigious “Person of the Year” award by People’s Daily Online (人民网) (only one student annually across the entire university) during my college years.

Any academic and project cooperation intentions are welcome to contact me: macong[at]senseauto(dot)com / Cong-Reeshard.Ma[at]pku(dot)edu(dot)cn

Experience

SenseAuto (2022-present)
Senior Scientist & Technical Adviser
Projects: Smart Transportation, Vehicle-Infrastructure Cooperation, World Model
Research Fields: 2D/Monocular3D/Lidar3D Detection and Tracking, Multi-Sensor Tracking, Multi-Modality Representation, Trajectory Post-processing, AIGC+LLM+3DGS

Sensetime (2021-2022)
Senior Scientist
Projects: AI CITY, Smart Surveillance System
Research Fields: Lidar3D Detection, Multi-Object Tracking, Multi-agent Interaction

Stanford University (2020-2021)
Visiting Student Researcher (Remote, due to Covid-19)
Projects: JackRabbot
Research Fields: Lidar3D Detection, Multi-Object Tracking

Aibee (2018-2019)
Research Intern
Projects: Smart Shopping Mall
Research Fields: Multi-Object Tracking, Person Re-identification

Education

Peking University (2016-2021)
Ph.D. (Computer Applied Technology)
Projects: Smart City, Intelligent Park
Research Fields: Multi-Object Tracking, Segmentation, Person Re-identification

Xidian University (2012-2016)
Bachelor of Engineering (Articial Intelligence)
Projects: Wise-wheelchair, Smart Spinning
Research Fields: View Synthesis, Virual Reality, BrainWave Recognition

Publication (Under Review)

DyCPA: Online Constrainted Dynamic Clique Partitioning and Allocation Framework for Multi-Sensor Multi-Object Tracking Ruining Yang*, Cong Ma*, Kai Liu, Tianxiang Zhou, Xin Jin, Fei HUI, Wei Wu Journal on Information Fusion (Under Review)

Publication

GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer Xin Jin, Haisheng Su, Cong Ma*, Kai Liu, Wei Wu, Fei Hui, Junchi Yan The IEEE International Conference on Computer Vision (ICCV), 2025 Paper, Github

RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments Haisheng Su, Feixiang Song, Cong Ma*, Wei Wu, Junchi Yan The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025 Paper, Github

UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection Xin Jin, Haisheng Su, Kai Liu, Cong Ma*, Wei Wu, Fei Hui, Junchi Yan The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025 Paper, Github

HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative Cong Ma, Qiao Lei, Chengkai Zhu, Kai Liu, Zelong Kong, Liqing, Xueqi Zhou, Yuheng KAN, Wei Wu The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024 Paper, Github, Benchmark

Roadside Camera-LiDAR Calibration without Annotation Xiangmo Zhao, Shaojie Jin, Cong Ma, Ying Gao, Fei Hui IEEE Sensors Journal, 2024

SwiftPillars High-efficiency Pillar Encoder for Lidar-based 3D Detection Xin Jin*, Kai Liu*, Cong Ma*, Ruining Yang, Fei Hui, Wei Wu, Association for the Advancement of Artificial Intelligence (AAAI), 2024 Paper

Deep trajectory post-processing and position projection for single & multiple camera multiple object tracking Cong Ma, Fan Yang, Yuan Li, Huizhu Jia, Xiaodong Xie, Wen Gao International Journal of Computer Vision (IJCV), 2021 Paper

Deep human-interaction and association by graph-based learning for multiple object tracking in the wild Cong Ma, Fan Yang, Yuan Li, Huizhu Jia, Xiaodong Xie, Wen Gao International Journal of Computer Vision (IJCV), 2021 Paper

High-level task-driven single image deraining: Segmentation in rainy days [Best Paper Nomination] Mengxi Guo, Mingtao Chen, Cong Ma, Yuan Li, Xianfeng Li, Xiaodong Xie, The International Conference on Neural Information Processing (ICONIP), 2020 Paper

Optical flow-guided mask generation network for video segmentation Yunyi Li, Fangping Chen, Fan Yang, Cong Ma, Yuan Li, Huizhu Jia, Xiaodong Xie, IEEE International Symposium on Circuits and Systems (ISCAS), 2020 Paper

Bba-net: A bi-branch attention network for crowd counting Yi Hou, Chengyang Li, Fan Yang,Cong Ma, Liping Zhu, Yuan Li, Huizhu Jia, Xiaodong Xie, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020 Paper, Github

Deep association: End-to-end graph-based learning for multiple object tracking with conv-graph neural network [Oral Presentation] Cong Ma, Yuan Li, Ziwei Zhang, Yueqing Zhuang, Huizhu Jia, Xiaodong Xie, International Conference on Multimedia Retrieval (ICMR), 2019 Paper, Github

Dense relation network: Learning consistent and context-aware representation for semantic image segmentation Yueqing Zhuang, Fan Yang, Li Tao, Cong Ma, Ziwei Zhang, Yuan Li, Huizhu Jia, Xiaodong Xie, Wen Gao IEEE international conference on image processing (ICIP), 2018 Paper

Relationnet: Learning deep-aligned representation for semantic image segmentation Yueqing Zhuang, Li Tao, Fan Yang, Cong Ma, Ziwei Zhang, Huizhu Jia, Xiaodong Xie, International Conference on Pattern Recognition (ICPR), 2018 Paper

Trajectory factory Tracklet cleaving and re-connection by deep siamese bi-gru for multiple object tracking [Oral Presentation] Cong Ma, Changshui Yang, Yueqing Zhuang, Ziwei Zhang, Huizhu Jia, Xiaodong Xie, IEEE International Conference on Multimedia and Expo (ICME), 2018 Paper, Github

Awards and Honors

Patents

1.Virtual View Synthesis Method and Device, Patent No.: CN106162137B,
Inventors: Changshui Yang, Huizhu Jia, Cong Ma, Xiaodong Xie, Chen Rui
2.Image denoising method and image denoising device, Patent No.: CN106162137A,
Inventors: Changshui Yang, Cong Ma, Huizhu Jia, Xiaodong Xie, Rui Chen, Wen Gao
3.A Stereoscopic Image Acquisition Device, Patent No.: CN202043213U,
Inventor: Cong Ma
4.A Wheelchair Controlled by Eye-Tracking, Patent No.: CN204863717U,
Inventor: Cong Ma, Yi Zhu, Yanfang Guo, Jingyan Geng
5.Multifunctional Somatosensory Synchronous Bicycle Fitness and Entertainment System, Patent No.: CN204073263U,
Inventors: Yi Zhu, Cong Ma, Yicong Cao