Loading...

Jiaxu Leng

Jiaxu Leng
CQUPT Wenfeng Young Scholars "Hundred Talents" Program

lengjx cqupt.edu.cn

About Me

Jiaxu Leng

Jiaxu Leng, Associate Professor with the School of Computer Science and Technology, Chongqing University of Posts and Telecommunications (CQUPT), Chongqing, China. Dr. Leng is the director of the Trustworthy Visual Intelligence Group (TVI Group), which is affiliated with the Smart Mind and Super Vision Group. He received the Ph.D. degree in Computer Application Technology from the University of Chinese Academy of Sciences, Beijing, China, in 2020. His current research interests include Computer Vision, Face Super-Resolution, Person Re-Identification, Video Anomaly Detection, Autonomous Driving, and Embodied Intelligence. In the past three years, he has led one General Program and one Young Scientists Fund project from the National Natural Science Foundation of China (NSFC), one General Program from the China Postdoctoral Science Foundation, and four provincial or ministerial-level general/key projects. Currently, he has published over 40 papers in NeurIPS, ACM CSUR, ACM MM, IEEE TIFS, IEEE TMM, IEEETITS, IEEE TCSVT, IEEE TGRS, etc. He has served as the Local Chair of VALSE 2024 and has served as the reviewer for prestigious journals and conferences, including CVPR, ECCV, IEEE TIP, and IEEE TMM.

每年预计招收硕士生6名,博士生1-2名。2025年可信视觉小组招新QQ群:654128384,具体招生要求如下:

  • 1、唯有热爱,唯有热爱才能让你在面对困境、挑战和诱惑的时候坚定地走下去!
  • 2、态度端正,态度决定了你是否能够在科研中严于律己、实事求是、精益求精!
  • 3、勇攀高峰,在生活和学习中勇敢自信、敢于挑战自我、突破自我,勇攀科研高峰!
Research

Research Projects

  • 国家自然科学基金面上项目:基于联想记忆与上下文联合推理的视频异常检测与预测研究, 62472060, 50万, 2025.01-2028.12. 主持.
  • 国家自然科学基金青年项目: 基于上下文特征图推理的小目标检测方法研究, 62102057, 30万, 2022.01-2024.12. 主持.
  • 中国博士后科学基金面上项目:基于复杂场景理解的视频异常检测, 8万, 2022-2024. 主持.
  • 重庆市博新计划项目:基于多视角上下文图推理的视频异常检测与预测, 60万, 2022-2024. 主持.
  • 重庆市自然科学基金面上项目:面向无人机高分辨率图像的低功耗目标检测, CSTB2022NSCQ-MSX1024, 5万, 2022-2025. 主持.
  • 重庆市教委重点项目:基于上下文感知的视频异常分析技术研究, KJZD-K202300604, 6万, 2023.10-2026.10. 主持.
  • 重庆市教委青年目:基于区域感知和关系推理的困难目标检测研究, KJQN202100627, 4万, 2021.07-2024.06. 主持.
  • 装备预研教育部联合基金重点项目: 8091B012112, 387万, 2022.01-2024.12. 参与.
  • 国家自然科学基金重点项目: 面向跨设备多场景视频理解的可视分析技术研究, 62036007, 301万, 2021.01-2024.12. 参与.
  • 国家自然科学基金区域联合项目:视觉大数据内容安全分析与隐私保护研究, U22A2096, 257万, 2023.01- 2026.12, 参与.
  • 国家自然科学基金面上项目:面向孤独症早期辅助诊断的婴幼儿大脑磁共振图像分割方法研究, 62276041, 53万, 2023.01-2026.12, 参与.
  • 国家重点研发计划课题:面向开放场景与动态任务的元学习示范应用, 2022YFA1004100, 340万, 2022-2026, 参与.
  • 江苏省社会安全图像与视频理解重点实验室开放课题: 基于记忆引导和视角转换的视频异常检测研究, J2021-1, 2万, 2021.1-2022.12. 主持.
  • 重庆邮电大学人才引进项目: 复杂场景下的小目标检测方法研究, E012A2021206, 50万, 2021.4-2024.4. 主持.
    Dual-Space Video Person Re-Identification[J] [ Paper ]
    Jiaxu Leng, Changjiang Kuang, Shuang Li, Ji Gan, Haosheng Chen and Xinbo Gao*
    International Journal of Computer Vision, 2025. (CCF A, 计算机视觉领域顶级期刊,影响因子11.6)

    Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection [ Paper ]
    Jiaxu Leng, Zhanjie Wu, Mingpi Tan, Yiran Liu, Ji Gan, Haosheng Chen, and Xinbo Gao*
    Advances in Neural Information Processing Systems (NeurIPS), 2024. (CCF A, 机器学习领域顶级会议)

    Difficulty-Guided Variant Degradation Learning for Blind Image Super-Resolution[J] [ Paper ]
    Jiaxu Leng, Jia Wang, Mengjingcheng Mo, Ji Gan, Wen Lu, and Xinbo Gao*
    IEEE Transactions on Neural Networks and Learning Systems, 2024. (SCI一区TOP, 影响因子10.4)

    Recent Advances for Aerial Object Detection: A Survey[J] [ Paper ]
    Jiaxu Leng, Yongming Ye, Mengjingcheng Mo, Chenqiang Gao, Ji Gan, Bin Xiao, and Xinbo Gao*
    ACM Computing Surveys, 2024. (SCI一区TOP, 理论计算机科学NO.1综述期刊 ,影响因子23.8)

    CRNet: Context-guided Reasoning Network for Detecting Hard Objects[J] [ Paper ]
    Jiaxu Leng, Yiran Liu, Xinbo Gao* and Zhihui Wang
    IEEE Transactions on Multimedia, 2023. (SCI一区TOP,多媒体领域顶刊)

    Anomaly Warning: Learning and Memorizing Future Semantic Patterns for Unsupervised Ex-ante Potential Anomaly Prediction [ Paper ]
    Jiaxu Leng, Mingpi Tan, Xinbo Gao*, Wen Lu and Zongyi Xu
    ACM Multimedia (ACM MM), 2022. (CCF A,多媒体领域顶会)

    ICNet: Joint Alignment and Reconstruction via Iterative Collaboration for Video Super-Resolution [ Paper ]
    Jiaxu Leng, Jia Wang, Xinbo Gao*, Bo Hu, Ji Gan and Chengqiang Gao
    ACM Multimedia (ACM MM), 2022. (CCF A, 多媒体领域顶会)

    Pareto Refocusing for Drone-view Object Detection[J] [ Paper ]
    Jiaxu Leng, Mengjingcheng Mo, Yinghua Zhou, Chenqiang Gao, Weisheng Li and Xinbo Gao*
    IEEE Transactions on Circuits and Systems for Video Technology, 2022. (SCI一区TOP, 视频技术领域顶刊)

    CrossNet: Detecting Objects as Crosses[J] [ Paper ]
    Jiaxu Leng*, Yin Liu, Zhihui Wang, Haibo Hu and Xinbo Gao
    IEEE Transactions on Multimedia, 2021, 24: 861-875. (SCI一区TOP, 多媒体领域顶刊)

    Robust Obstacle Detection and Recognition for Driver Assistance Systems[J] [ Paper ]
    Jiaxu Leng, Yin Liu*, Dawei Du, Tianlin Zhang and Pei Quan
    IEEE Transactions on Intelligent Transportation Systems, 2020, 21(4): 1560-1571. (SCI一区TOP, 智能交通领域顶刊)

    Selective Domain-invariant Feature Alignment Network for Face Anti-spoofing[J] [ Paper ]
    Lifang Zhou, Jun Luo, Xinbo Gao, Weisheng Li, Bangjun Lei, and Jiaxu Leng*
    IEEE Transactions on Information Forensics & Security, 2021. (SCI一区TOP, 信息安全领域顶刊)

    Correlation Filter Tracker with Sample-Reliability Awareness and Self-Guided Update[J] [ Paper ]
    Lifang Zhou, Jiaqi Li, Bangjun Lei, Weisheng Li and Jiaxu Leng*
    IEEE Transactions on Circuits and Systems for Video Technology, 2022. (SCI一区TOP, 视频技术领域顶刊)

    MTCNet: Multi-Task Collaboration Network for Rotation-Invariance Face Detection[J] [ Paper ]
    Lifang Zhoua, Hui Zhao, Jiaxu Leng*
    Pattern Recognition, 2021. (SCI一区TOP, 人工智能领域顶刊)

    Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection [ Paper ]
    Feng Gao, Jiaxu Leng*, Ji Gan and Xinbo Gao*
    ACM Multimedia (ACM MM), 2023. (CCF A, 多媒体领域顶会)

    Characters as Graphs: Interpretable Handwritten Chinese Character Recognition via Pyramid Graph Transformer[J] [ Paper ]
    Ji Gan, Yuyan Chen, Bo Hu, Jiaxu Leng*, Weiqiang Wang and Xinbo Gao*
    Pattern Recognition, 2023. (SCI一区TOP, 人工智能领域顶刊)

    HiGAN+: Handwriting Imitation GAN with Disentangled Representations[J] [ Paper ]
    Ji Gan, Weiqiang Wang*, Jiaxu Leng, Xinbo Gao*
    ACM Transactions on Graphics, 2022, 42(1): 1-17. (SCI一区TOP, 计算机图形学领域顶刊)

    RC-DETR: Improving DETRs in crowded pedestrian detection via rank-based contrastive learning [ Paper ]
    Feng Gao, Jiaxu Leng*, Ji Gan and Xinbo Gao*
    Neural Networks, 2024. (SCI一区TOP)