 |
Jinlong Li (李金龙) |
About Me
I am currently a Senior Research Engineer at OPPO R&D US, specializing in advanced technologies in computer vision and artificial intelligence. I earned my Ph.D. in Computer Science from Cleveland State University in 2024, completing the program in just two and a half years. Prior to that, I received a Master's degree in Computer Science (2021) and a Bachelor's degree in Civil Engineering (2018) from Chang'an University in Xi'an, China.My research interests span broadly across computer vision and machine learning, with a focus on developing innovative and practical solutions for real-world interdisciplinary challenges by integrating diverse methodologies. Currently, my work is concentrated on the following research topics:
- Generative AI and Multi-Modal Large Language Models (LLMs) in Computational Photography and Imaging.
- Transfer learning-based end-to-end 2D/3D perception for autonomous driving and intelligent transportation systems.
- 3D perception for cooperative perception in autonomous vehicles.
- [2024.08] Jinlong started his position as a Postdoctoral Researcher in the TACO Group at Texas A&M University.[TACO-Group]
- [2024.05] Jinlong began his research internship with the AI Visual Team at OPPO US Research Center in Palo Alto, CA.
- [2024.04] Jinlong successfully passed his Computer Science Ph.D. Dissertation Defense April 11, 2024.
- [2024.04] Jinlong received the CSU Outstanding Achievement Award for Doctoral Research.
- [2024.02] One paper has been accepted by CVPR 2024 ! [Project page]
- [2024.02] Three paper has been accepted by ICRA 2024 !
- [2023.05] Jinlong successfully passed the Computer Science Ph.D. Proposal presentation on May 01, 2023. Congratulations.
- [2023.03] One paper has been accepted by IEEE Transactions on Intelligent Vehicles.
- [2023.02] One paper is accepted at CVPR 2023, it is selected as Highlight (2.5% of 9155 submissions)
- [2023.02] Jinlong successfully passed the CS Ph.D. Qualifying Exam on Feb. 02 2023. Now he is a Ph.D. Candidate in Department of Computer Science, Cleveland State University.
- [2022.10] Two papers (Colorizing Old Photos; Domain Adaptive Object Detection) have been accepted by WACV 2023.
- [2021.08] Jinlong successfully arrived at Cleveland, Ohio, USA. Now he is a Ph.D. student in Department of Computer Science, Cleveland State University.
- [2021.06] Jinlong successfully awarded his M.E. degree of Computer Science in Chang'an University in China.
- [2021.01] One paper about Domain Adaptation based Vehicle Detection is accepted by Transportation Research Part C.[Link]
- 2024.08-present Postdoctoral Researcher in TACO-Group @ Texas A&M University. (TACO-Group)
- 2024.05-2024.08 Research intern in AI-Visual Enhancement and Understanding Team, OPPO US Research Center.
- 2021.09-2024.06 Ph.D. in Engineering (Computer Science Track), Cleveland State University.
- 2018.09-2021.06 M.E. in Computer Science and Technology, Chang'an University.
- 2014.09-2018.06 B.E. in Road Bridge and River Crossing Engineering (Excellent Engineer), Chang'an University.
- Received the CSU Outstanding Achievement Award for Doctoral Research in Natural Sciences, Engineering. Spring 2024. [Link] [File]
- Being a guest lecturer&Teaching Assistant and of CIS694/EEC693/CIS593 Deep Learning in Cleveland State University, Spring 2024.
- Invited talk for Cleveland State University & NSF MRI High Performance Computing Workshop, Fall 2023. [Link]
- Being a guest speaker of CIS694/EEC693/CIS593 Deep Learning in Cleveland State University, Spring 2023.
- Being a Judge for Choose Ohio First Symposium at Cleveland State University, in Spring 2022.
- The master's thesis "Research of Urban Road Vehicle Trajectory Tracking and Automatic Generation Algorithm Based on Deep Learning" was selected as an excellent master's thesis of CHTS(CHINA HIGHWAY AND TRANSPORTATION SOCIETY) in 2022.[Link] [File]
- Expert Systems with Applications (ESWA)
- IEEE Transactions on Intelligent Transportation Systems (T-ITS)
- IEEE Transactions on Intelligent Vehicles (T-IV)
- IEEE Transactions on Vehicular Technology (T-VT)
- IEEE Transactions on Multimedia (T-MM)
- IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT)
- IEEE Robotics and Automation Letters (RA-L)
- IEEE Sensor Journal (SJ)
- Neural Networks (NN)
- IET Image Processing (IET IP)
- IEEE Vehicular Technology Magazine (VTM)
- International Journal of Machine Learning and Cybernetics (IJMLC)
- IEEE International Conference on Robotics and Automation, 2024 (ICRA)
- IEEE/CVF Winter Conference on Applications of Computer Vision, 2023 (WACV)
- IEEE/CVF International Conference on Computer Vision, 2023 (ICCV)
- European Conference on Computer Vision, 2024 (ECCV)
- International Conference on Multimedia Information Processing and Retrieval, 2022, 2023 (MIPR)
- IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024 (IROS)
News
Education and Experience
Selected Works
CoMamba: Real-time Cooperative Perception Unlocked with State Space Models [Project Page]
Preprint 2024 [Paper] [Code]
"CoMamba scales remarkably well, achieving linear-complexity costs in GFLOPs, latency, and GPU memory relative to the number of agents, while still maintaining excellent performance."
Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving [Project Page]
CVPR 2024 [Paper] [Code]
"We propose the Lighting Diffusion to enhance low-light camera images, mitigating the need for extensive nighttime data collection and preserving daytime performance."
Domain Adaptation based Object Detection for Autonomous Driving in Foggy and Rainy Weather
TIV 2024 [Paper] [Code]
"This work presents a domain adaptive object detection framework, which is specifically designed for intelligent vehicle perception in foggy and rainy weather conditions."
Breaking Data Silos: Cross-Domain Learning for Multi-Agent Perception from Independent Private Sources
ICRA 2024 [Paper] [Code]
"This work proposes the first research on multi-agent perception to address the Distribution Gap of different independent private data for training distinct agents."
AdvGPS: Adversarial GPS for Multi-Agent Perception Attack
ICRA 2024 [Paper] [Code]
"This work proposes the first research of adversarial GPS signals which are also stealthy for the V2V cooperative perception attacks."
S2R-ViT for multi-agent cooperative perception: Bridging the gap from simulation to reality [Project Page]
ICRA 2024 [Paper] [Code]
"This work proposes the first Simulation-to-Reality transfer learning framework for multi-agent cooperative perception."
Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication
Trans on Intelligent Vehicles 2023 [Paper] [Code]
"This work proposes the first research on V2V cooperative perception under lossy communication."
V2V4Real: A large-scale real-world dataset for Vehicle-to-Vehicle Cooperative Perception
CVPR 2023 Highlight (2.5% of 9155 submissions) [Project] [Paper] [Code]
"This work presents the first large-scale real-world dataset for V2V perception."
Bridging the domain gap for multi-agent perception
ICRA 2023 [Paper] [Code]
"The first work to bridge the domain gap for multi-agent perception."
Publications
Conferences:
[9] Jinlong Li, Baolu Li, Zhengzhong Tu, Xinyu Liu, Qing Guo, Felix Juefei-Xu, Runsheng Xu, Hongkai Yu. Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving[C]. Proceedings of IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR2024), 2024. [Link] [PDF] [BibTeX] [Code]
[8] Jinlong Li, Baolu Li, Xinyu Liu, Runsheng Xu, Jiaqi Ma, Hongkai Yu. Breaking Data Silos: Cross-Domain Learning for Multi-Agent Perception from Independent Private Sources[C]. International Conference on Robotics and Automation (ICRA2024), 2024. [Link] [PDF] [BibTeX] [Code]
[7] Jinlong Li, Baolu Li, Xinyu Liu, Jianwu Fang, Felix Juefei-Xu, Qing Guo, Hongkai Yu. AdvGPS: Adversarial GPS for Multi-Agent Perception Attack[C]. International Conference on Robotics and Automation (ICRA2024), 2024. [Link] [PDF] [BibTeX] [Code]
[6] Jinlong Li, Runsheng Xu, Xinyu Liu, Baolu Li, Qin Zou, Jiaqi Ma, Hongkai Yu. S2R-ViT for multi-agent cooperative perception: Bridging the gap from simulation to reality[C]. International Conference on Robotics and Automation (ICRA2024), 2024. [Link] [PDF] [BibTeX] [Code]
[5] Runsheng Xu, Jinlong Li, Xiaoyu Dong, Hongkai Yu, Jiaqi Ma. Bridging the domain gap for multi-agent perception[C]. International Conference on Robotics and Automation (ICRA2023), 2023. [Link] [PDF] [BibTeX] [Code] [Dataset]
[4] Runsheng Xu, Xin Xia,Jinlong Li, Hanzhao Li, Shuo Zhang, Zhengzhong Tu, Zonglin Meng, Hao Xiang, Xiaoyu Dong, Rui Song, Hongkai Yu, Bolei Zhou, Jiaqi Ma. V2V4Real: A large-scale real-world dataset for Vehicle-to-Vehicle Cooperative Perception[C]. Proceedings of IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR2023), 2023. [Link] [PDF] [BibTeX] [Code] [Dataset]
[3] Jinlong Li, Runsheng Xu, Jin Ma, Qin Zou, Jiaqi Ma, and Hongkai Yu. Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather[C]. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV2023), 2023. [Link] [PDF] [BibTeX] [Code] [Dataset]
[2] Runsheng Xu, Zhengzhong Tu, Yuanqi Du, Xiaoyu Dong, Jinlong Li, Zibo Meng, Jiaqi Ma, Alan Bovik, and Hongkai Yu. Pik-Fix: Restoring and Colorizing Old Photo[C]. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV2023), 2023. [Link] [PDF] [BibTeX] [Code] [Dataset]
[1] Xu, Runsheng, Hao Xiang, Xin Xia, Xu Han, Jinlong Li, and Jiaqi Ma. OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication[C]. IEEE international conference on robotics and automation (ICRA2022), 2022. [Link] [PDF] [BibTeX] [Code] [Dataset]
Journals:
[9] Jinlong Li, Runsheng Xu, Xinyu Liu, Jin Ma, Baolu Li, Qin Zou, Jiaqi Ma, and Hongkai Yu. Domain Adaptation based Object Detection for Autonomous Driving in Foggy and Rainy Weather[J]. IEEE Transactions on Intelligent Vehicles, 2024. [Link] [PDF] [BibTeX] [Code] [Dataset]
[8] Xinyu Liu, Jinlong Li, Jin Ma, Huiming Sun, Zhigang Xu, Tianyun Zhang, Hongkai Yu. Deep transfer learning for intelligent vehicle perception: A survey[J]. Green Energy and Intelligent Transportation, 2023:100125. [Link] [PDF] [BibTeX]
[7] Talha Azfar, Jinlong Li, Hongkai Yu, Ruey L Cheu, Yisheng Lv, Ruimin Ke. Deep Learning-Based Computer Vision Methods for Complex Traffic Environments Perception: A Review[J]. Data Science for Transportation, 2024. [Link] [PDF] [BibTeX]
[6] Jinlong Li, Runsheng Xu, Xinyu Liu, Jin Ma, Zicheng Chi, Jiaqi Ma, Hongkai Yu. Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication[J]. IEEE Transactions on Intelligent Vehicles, 2023. [Link] [PDF] [BibTeX] [Code] [Dataset]
[5] Lan Fu, Hongkai Yu, Felix Juefei-Xu, Jinlong Li, Qing Guo, Song Wang. Let There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021. [Link] [PDF] [BibTeX] [Code] [Dataset]
[4] Ying Gao, Jinlong Li, Zhigang Xu, Zhangqi Liu, Xiangmo Zhao, Jianhua Chen. A novel image-based convolutional neural network approach for traffic congestion estimation[J]. Expert Systems with Applications, 2021:115037. [Link] [PDF] [BibTeX]
[3] Jinlong Li, Zhigang Xu, Lan Fu, Xuesong Zhou, Hongkai Yu. Domain adaptation from daytime to nighttime: A situation-sensitive vehicle detection and traffic flow parameter estimation framework[J]. Transportation Research Part C: Emerging Technologies, 2021, 124: 102946. [Link] [PDF] [BibTeX] [Dataset]
[2] Zhigang Xu, Jinlong Li, et al. A Review on Intelligent Road and Its Related Key Technologies [J]. China Journal of Highway and Transport, 2019, 32(8): 1-24. [Link] [PDF] [BibTeX]
[1] Zhigang Xu,Yanli Che, Jinlong Li, et al. Research progress on automatic image processing technology for pavement distress[J]. Journal of Traffic and Transportation Engineering, 2019,19(01):172-190. [Link] [PDF] [BibTeX]
Services
Academic Activities:
Journal Reviewer:
Conference Reviewer: