徐婧林

北京科技大学智能科学与技术学院，特聘教授，国家级青年人才入选者，北京图象图形学学会理事、副秘书长，中国图象图形学学会青托俱乐部副主席。主要研究方向为计算机视觉、视频理解、细粒度运动分析，已发表TPAMI、IJCV、CVPR等ACM/IEEE Trans.和CCF A类论文30余篇。主持国家自然科学基金青年基金B类（原优青）、C类（原青年基金）、面上、北京市自然科学基金面上等项目；主持腾讯犀牛鸟专项研究计划；作为课题负责人参与国家自然科学基金重点（序2）、北京市自然科学基金联合基金重点（序2）等项目。入选中国科协青年人才托举工程，获中国图象图形学学会石青云女科学家奖、优秀博士学位论文奖，获中国自动化学会自然科学奖一等奖（4/5）、中国图象图形学学会自然科学奖二等奖（3/5）等奖励。担任《Chinese Journal of Electronics》青年编委、《电子与信息学报》编委、《计算机科学》执行编委、IJCAI/AAAI程序委员会委员等。

常年招收博士后、博士、硕士和科研实习生！（联系方式：xujinglin@ustb.edu.cn）

谷歌学术  /  GitHub

profile photo
News

  • 2025-11-08：2篇论文被AAAI 2026接收
  • 2025-10-09：1篇论文被CJE 2025接收
  • 2025-07-10：1篇论文被IEEE TCSVT 2025接收
  • 2025-03-28：1篇论文被IEEE TPAMI 2025接收
  • 2025-03-01：1篇论文被IEEE TCSVT 2025接收
  • 2025-02-27：1篇论文被CVPR 2025接收
  • 2025-01-25：1篇论文被TPAMI 2025接收

    • 项目

  • 国家自然科学基金青年科学基金B类（原优青），2025，项目负责人
  • 北京市自然科学基金面上项目，2025，项目负责人
  • 国家自然科学基金面上项目，2023，项目负责人
  • 国家自然科学基金重点项目，2024，合作单位负责人
  • 北京市自然科学基金重点项目，2024，合作单位负责人
  • 国家自然科学基金青年基金，2021，项目负责人

    • 奖励与荣誉

  • 中国图象图形学学会石青云女科学家奖，2024
  • 第九届中国科协青年人才托举工程，2023
  • 中国图象图形学学会优秀博士学位论文奖，2022
  • 中国自动化学会自然科学奖一等奖，2023，排第四
  • 中国图象图形学学会自然科学奖二等奖，2024，排第三

    • 代表性论文

    dise Human-centric Fine-grained Action Quality Assessment
    Jinglin Xu, Sibo Yin, Yuxin Peng*
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
    [Paper]
    dise Transferable Unintentional Action Localization with Language-guided Intention Translation
    Jinglin Xu, Yongming Rao, Jie Zhou, Jiwen Lu*
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
    [Paper]
    dise PoseTrack: Enhancing Multi-Object Tracking with 3D Pose-Visual Fusion and Adaptive Trajectory Management
    Jinglin Xu, Xudong Zhang, Ziyi Liu, Hongmin Liu*
    Chinese Journal of Electronics (CJE), 2025.
    [Paper]
    dise TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding
    Canhui Tang, Zifan Han, Hongbo Sun, Sanping Zhou, Xuchong Zhang, Xin Wei, Ye Yuan, Jinglin Xu, Hao Sun
    The Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026). (Accepted)
    [Paper] [Github]
    dise MCMoE: Completing Missing Modalities with Mixture of Experts for Incomplete Multimodal Action Quality Assessment
    Huangbiao Xu, Huanqi Wu, Xiao Ke, Junyi Wu, Rui Xu, Jinglin Xu
    The Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026). (Accepted)
    [Paper] [Github]
    dise DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding
    Geng Li, Jinglin Xu, Yunzhen Zhao, Yuxin Peng*
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    [Paper] [Github]
    dise Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
    Hulingxiao He, Geng Li, Zijun Geng, Jinglin Xu, Yuxin Peng*
    International Conference on Learning Representations (ICLR), 2025
    [Paper] [Github] [中文解读]
    dise MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval
    Yanzhe Chen, Zhiwen Yang, Jinglin Xu, Yuxin Peng*
    International Conference on Learning Representations (ICLR), 2025
    [Paper] [中文解读]
    dise BFSTAL: Bidirectional Feature Splitting with Cross-Layer Fusion for Temporal Action Localization
    Jinglin Xu, Yaqi Zhang, Wenhao Zhou, Hongmin Liu*
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025
    [Paper]
    dise BRTAL: Boundary Refinement Temporal Action Localization via Offset-Driven Diffusion Models
    Hongmin Liu, Xueli Li, Bin Fan, Jinglin Xu*
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025
    [Paper] [bibtex]
    dise Pro2Diff: Proposal Propagation for Multi-Object Tracking via Diffusion Models
    Hongmin Liu, Canbin Zhang, Bin Fan, Jinglin Xu*
    IEEE Transactions on Image Processing (TIP), 2024
    [Paper]
    dise SIM-OFE: Structure Information Mining and Object-aware Feature Enhancement for Fine-Grained Visual Categorization
    Hongbo Sun, Xiangteng He, Jinglin Xu, Yuxin Peng*
    IEEE Transactions on Image Processing (TIP), 2024
    [Paper] [中文解读]
    dise SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
    Zishuo Wang, Wenhao Zhou, Jinglin Xu, Yuxin Peng*
    ACM International Conference on Multimedia (ACM MM), 2024
    [Paper] [Github]
    dise Procedure-aware Action Quality Assessment: Datasets and Performance Evaluation
    Jinglin Xu, Yongming Rao, Jie Zhou, Jiwen Lu*
    International Journal of Computer Vision (IJCV), 2024
    [Paper]
    dise ScalableTrack: Scalable One-stream Tracking via Stage-continual Learning
    Hongmin Liu, Yuefeng Cai, Bin Fan, Jinglin Xu*
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024
    [Paper]
    dise FineFMPL: Fine-grained Feature Mining Prompt Learning for Few-Shot Class Incremental Learning
    Hongbo Sun, Jiahuan Zhou, Xiangteng He, Jinglin Xu, Yuxin Peng*
    33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024
    [Paper] [Github]
    dise FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models
    Jinglin Xu, Yijie Guo, Yuxin Peng*
    37th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    [Paper] [Github]
    dise FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding
    Jinglin Xu, Guohao Zhao, Sibo Yin, Wenhao Zhou, Yuxin Peng*
    37th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    [Paper] [Github]
    dise FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment
    Jinglin Xu, Sibo Yin, Guohao Zhao, Zishuo Wang, Yuxin Peng*
    37th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    [Paper] [Github]
    dise FE-VAD: High-Low Frequency Enhanced Weakly Supervised Video Anomaly Detection
    Ruoyan Pi, Jinglin Xu, Yuxin Peng*
    IEEE International Conference on Multimedia and Expo (ICME), 2024
    [Paper] [bibtex]
    dise FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment
    Jinglin Xu#, Yongming Rao#, Xumin Yu, Guangyi Chen, Jie Zhou, Jiwen Lu*
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    Oral Presentation
    [项目主页] [Paper] [Github] [bibtex] [中文解读]
    dise Unintentional Action Localization via Counterfactual Examples
    Jinglin Xu#, Guangyi Chen#, Jiwen Lu*, and Jie Zhou
    IEEE Transactions on Image Processing (TIP), 2022, DOI: 10.1109/TIP.2022.3166278
    [Paper] [bibtex]
    dise Probabilistic Temporal Modeling for Unintentional Action Localization
    Jinglin Xu#, Guangyi Chen#, Nuoxing Zhou, Wei-Shi Zheng, Jiwen Lu*
    IEEE Transactions on Image Processing (TIP), 2022, DOI: 10.1109/TIP.2022.3163544
    [Paper] [bibtex]
    dise Multi-view K-Means Clustering with Adaptive Sparse Memberships and Weight Allocation
    Junwei Han, Jinglin Xu*, Feiping Nie, and Xuelong Li
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020
    [Paper] [Github] [bibtex]
    dise Joint multi-view 2D convolutional neural networks for 3D object classification
    Jinglin Xu, Xiangsen Zhang, Wenbin Li, Xinwang Liu, Junwei Han
    International Joint Conference on Artificial Intelligence (IJCAI) , 2020
    [Paper] [bibtex]
    dise Deep Embedded Complementary and Interactive Information for Multi-View Classification
    Jinglin Xu#, Wenbin Li#, Xinwang Liu, Dingwen Zhang, Ji Liu, Junwei Han*
    AAAI Conference on Artificial Intelligence (AAAI), 2020
    [Paper] [Github] [bibtex]
    dise Multi-view Scaling Support Vector Machines for Classification and Feature Selection
    Jinglin Xu, Junwei Han*, Feiping Nie, Xuelong Li
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019
    [Paper] [bibtex]
    dise Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
    Wenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Yang Gao, and Jiebo Luo
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    [Paper] [Github] [bibtex]
    dise Distribution consistency based covariance metric networks for few-shot learning
    Wenbin Li#, Jinglin Xu#, Jing Huo, Lei Wang, Yang Gao, Jiebo Luo
    AAAI Conference on Artificial Intelligence (AAAI), 2019
    [Paper] [Github] [bibtex]
    dise Feature Selection via Scaling Factor Integrated Multi-Class Support Vector Machines
    Jinglin Xu, Feiping Nie, Junwei Han
    International Joint Conference on Artificial Intelligence (IJCAI), 2017
    [Paper] [bibtex]
    dise Multi-view Feature Learning with Discriminative Regularization
    Jinglin Xu, Junwei Han, Feiping Nie
    International Joint Conference on Artificial Intelligence (IJCAI), 2017
    [Paper] [bibtex]
    dise Re-Weighted Discriminatively Embedded K-Means for Multi-View Clustering
    Jinglin Xu, Junwei Han*, Feiping Nie, Xuelong Li
    IEEE Transactions on Image Processing (TIP), 2017
    [Paper] [bibtex]
    dise Robust and sparse fuzzy k-means clustering
    Jinglin Xu, Junwei Han*, Kai Xiong, Feiping Nie
    International Joint Conference on Artificial Intelligence (IJCAI), 2016
    [Paper] [bibtex]
    dise Discriminatively embedded k-means for multi-view clustering
    Jinglin Xu, Junwei Han*, Feiping Nie
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016
    Spotlight Presentation
    [Paper] [bibtex]
    学术服务

  • 担任《Chinese Journal of Electronics》青年编委、《电子与信息学报》编委、《计算机科学》青年编委、《人工智能》编委
  • IJCAI、AAAI程序委员会委员
  • 国际顶级期刊和会议（IEEE TPAMI、TIP、TCSVT、TMM、CVPR等）审稿人

    • 指导学生

  • 硕士生:
    周汶昊 (2023.09-), 张雅琦 (2023.09-), 张旭东 (2023.09-)
    马晨阳 (2024.09-), 雷宇隆 (2024.09-)
    母星宏 (2025.09-), 李京选 (2025.09-), 王加博 (2025.09-)
    蔡越峰 (2021.09-2024.07; 刘红敏教授学生), 张灿彬 (2022.09-2025.07; 刘红敏教授学生)
  • 博士生:
    李雪梨 (2022.09-2024.07; 刘红敏教授学生), 刘宏坤 (2023.05-2024.07; 刘红敏教授学生)