Director of R&D, SenseTime
jiangqhmail@gmail.com
Google Scholar / CV
Short Bio
Currently, I am leading the Perception R&D Center in SenseAuto(绝影). Previously, I was also responsible for the Prediction Team.
At the same time, I am also in charge of the development of our L2++ system SenseAuto Pilot, and the tech lead of the GAC Mass Production Project. I am also the head of 3 mass production related departments, including SLAM R&D Center, Mass Production System Development and Mass Production Delivery Test.
I got my M.S. degree in the State Key Lab of CAD&CG, Zhejiang University in 2018, supervised by Prof. Guofeng Zhang. Before that, I received the B.S. degree of Digital Media Technology in Zhejiang University.
R&D Interest
I’m a big believer in data-driven algorithms. My research topics are all related to autonoumous driving, including
- Perception, especially vision-centric related
- Doamin Adaption related to object3d
- Motion Prediction
- Sensor Fusion
- End2End AD
NEWS
- [2023] I was invited by leiphone(雷锋网) to give a talk on our R&D of SenseAuto Pilot.
- [2023] Our L2++ mass production team won the company’s highest technology award, SenseTime Original Award !
- [2023] I was awarded as a candidate for the company’s highest award, the SenseTime Award !
- [2023] 1 paper related to BEV accepted by ICLR 2023 !
- [2022] 5 papers related to vision based bev perception, domain adapation accepted by ECCV/IJCAI/ACM MM/AAAI 2022 !
- [2021] 3 papers related to vision based object3d detection, motion prediction accepted by TPAMI/CVPR 2021 !
- [2020] 4 papers related to motion prediction accepted by CVPR/ECCV 2020 !
Publications
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection
Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao
ICLR 2023.
Towards Model Generalization for Monocular 3D Object Detection
Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, Junjun Jiang
Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, and Junjun Jiang
ECCV 2022.
AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection
Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao
ECCV 2022.
AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection
Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinghong Jiang, Feng Zhao, Bolei Zhou, Hang Zhao
IJCAI 2022.
Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection
Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao
ACM MM 2022.
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, Junjun Jiang, Bolei Zhou, Hang Zhao
AAAI 2022.
Shape Prior Guided Instance Disparity Estimation for 3D Object Detection
Linghao Chen, Jiaming Sun, Yiming Xie, Siyu Zhang, Qing Shuai, Qinhong Jiang, Guofeng Zhang, Hujun Bao, Xiaowei Zhou
TPAMI 2021.
Monocular 3D Object Detection: An Extrinsic Parameter Free Approach
Yunsong Zhou, Yuan He, Hongzi Zhu, Cheng Wang, Hongyang Li, Qinhong Jiang
CVPR 2021.
Multimodal Motion Prediction with Stacked Transformers
Yicheng Liu*, Jinghuai Zhang*, Liangji Fang, Qinhong Jiang, Bolei Zhou
CVPR 2021.
Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction
Chaofan Tao, Qinhong Jiang, Lixin Duan, Luo Ping
ECCV 2020.
TPNet: Trajectory Proposal Network for Motion Prediction
Liangji Fang*, Qinhong Jiang*, Jianping Shi, Bolei Zhou (* equal contribution)
CVPR 2020.
Recursive Social Behavior Graph for Trajectory Prediction
Jianhua Sun, Qinhong Jiang, Cewu Lu
CVPR 2020.
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
Jiaming Sun, Linghao Chen, Yiming Xie, Siyu Zhang, Qinhong Jiang, Xiaowei Zhou, Hujun Bao
CVPR 2020.