张淳杰

博士 、教授

基本信息

办公电话： 电子邮件： cjzhang@bjtu.edu.cn
通讯地址：北京交通大学信息科学研究所 邮编：100044

教育背景

2011年博士毕业于中国科学院自动化所模式识别国家重点实验室， 研究方向包括图像处理与理解、计算机视觉、多媒体数据处理与分析等方面；在The Innovation、IEEE TPAMI/TIP、CVPR/ICCV等刊物上发表论文百余篇；主持包括北京市杰出青年基金项目、国自然科面上项目等；获2023年北京市科学技术奖自然科学奖二等奖、2022年福建省科学技术奖科学技术进步奖二等奖、2018年度中国图象图形学学会科学技术奖二等奖，2020年度北京交通大学詹天佑专项奖（科技奖）；中国计算机学会杰出会员、中国电子学会/中国图象图形学学会/中国人工智能学会高级会员、IEEE Senior Member。


申请考核博士、硕博连读博士、直博生招生计划：2-3名

  • 招生要求：对科研工作真正怀有兴趣，具有较强的自我驱动能力和具备较好的编程能力和数学基础，有学术竞赛经验者优先。
  • 招生专业：详见学校研究生院导师在线系统：https://aa.bjtu.edu.cn/discipline/college_show/

工作经历

2019~至今       北京交通大学  计算机与信息技术学院 教授

2017~2019    中国科学院自动化研究所  助理研究员、副研究员

2012~2017    中国科学院大学 计算机与控制学院 博士后、讲师

2011~2012    国家电网河南省电力公司电力科学研究院   工程师

研究方向

  • 数字媒体信息处理与智能分析
  • 新一代电子信息技术
  • 软件工程
  • 人工智能
  • 大数据技术与工程
  • 机器学习与认知计算
  • 计算机技术

招生专业

  • 计算机科学与技术博士
  • 新一代电子信息技术（含量子技术等）博士
  • 人工智能博士
  • 软件工程博士
  • 计算机技术博士
  • 新一代电子信息技术（含量子技术等）硕士
  • 软件工程硕士
  • 人工智能硕士
  • 大数据技术与工程硕士
  • 计算机科学与技术硕士
  • 计算机技术硕士

科研项目

主持/参与国自然基金、北自然基金等。


教学工作

深度学习

论文/期刊


Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection, AAAI 2026.
段韶华, 张淳杰, 等．自回归与反馈驱动的自适应矩形卷积全色锐化网络．航空学报, 2026, 47(3): 632432
Shaohua Duan, Mengyao Sun, Chunjie Zhang et al. Pose estimation of space targets based on keypoint completion and weighted least squares optimization, Space Habitation, 1 (2025) 100016.
Dong Yu, Chunjie Zhang et al, Countering Adversarial Attacks with Multimodal image Fusion,  Machine Intelligence Research, accepted.
曹坪,林树冉,张淳杰,郑晓龙,赵耀，梯度引导的JPEG压缩图像超分辨率重建，自动化学报，2025
段韶华,张淳杰等，面向嫦娥六号采样任务的渐进式椭圆关键特征检测框架设计，中国科学技术科学，2025
苗仕林,唐业鹏,张淳杰等，面向月球空间站的智能时序行为检测，中国图象图形学报， 2025.
Dong Yu, Yepeng Tang, Chunjie Zhang, et al.,IA2GNN: Imbalance-Aware Adaptive Graph Construction for Multi-Modal Image Fusion, IEEE T-MM, accepted.
Shaohua Duan, Chunjie Zhang, Xiaolong Zheng, et.al., 24-h Lane Line Detection via Parallel Scene Information Collaboration, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 26(10):15279-15292, 2025.
Ping Cao, Yepeng Tang, Chunjie Zhang, Xiaolong Zheng, Chao Liang, Yunchao Wei, Yao Zhao. Visual Relation Diffusion for Human-Object Interaction Detection. ICCV, 2025.
Chunjie Zhang, Chuankai Liu, Shaohua Duan, Xiaolong Zheng et al.  Embodied cognitive intelligence guided Moon sample collection, . The Innovation 6(7), 100939.
Man Liu, Huihui Bai, Feng Li, Chunjie Zhang, Yunchao Wei, Meng Wang, Tat-Seng Chua, Yao Zhao: PSVMA+: Exploring Multi-Granularity Semantic-Visual Adaption for Generalized Zero-Shot Learning. IEEE Trans. Pattern Anal. Mach. Intell. 47(1): 51-66 (2025)
Man Liu, Huihui Bai, Feng Li, Chunjie Zhang, Yunchao Wei, Tat-Seng Chua, Yao Zhao: Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning. AAAI 2025: 5504-5512
Guoguang Zhang, Yepeng Tang, Chunjie Zhang, Xiaolong Zheng, Yao Zhao: Entity Dependency Learning Network With Relation Prediction for Video Visual Relation Detection. IEEE Trans. Circuits Syst. Video Technol. 34(12): 12425-12436 (2024)
Man Liu, Chunjie Zhang, Huihui Bai, Yao Zhao: Part-Object Progressive Refinement Network for Zero-Shot Learning. IEEE Trans. Image Process. 33: 2032-2043 (2024)
Yepeng Tang, Weining Wang, Chunjie Zhang, Jing Liu, Yao Zhao: Learnable Feature Augmentation Framework for Temporal Action Localization. IEEE Trans. Image Process. 33: 4002-4015 (2024)
Yepeng Tang, Weining Wang, Chunjie Zhang, Jing Liu, Yao Zhao:Temporal Action Proposal Generation With Action Frequency Adaptive Network. IEEE Trans. Multim. 26: 2340-2353 (2024)
Yepeng Tang, Weining Wang, Yanwu Yang, Chunjie Zhang, et. al., Anchor-free temporal action localization via Progressive Boundary-aware Boosting, Inf. Process. Manag., 60(1): 103141 (2023).
Hongguang Zhu, Chunjie Zhang, Yunchao Wei, Shujuan Huang, and Yao Zhao, ESA: External space attention aggregation for image-text retrieval, IEEE Transactions on Circuits and Systems for Video Technology, 33(10):6131-6143, 2023.
Man Liu, Feng Li, Chunjie Zhang, Yunchao Wei, Huihui Bai, and Yao Zhao, Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning, CVPR, pp.15337-15346, 2023. （highlight paper）
Changkai Xu, Chunjie Zhang, et. al., Accelerate adversarial training with loss guided propagation for robust image classification, Inf. Process. Manag., 60(1): 103143 (2023).
Weijia Li, Saihui Hou, Chunjie Zhang, et. al., An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions, CVPR, pp.13824-13833, 2023.
Shangrong Yang, Chunyu Lin, Kang Liao, Chunjie Zhang, Yao Zhao, Progressively complementary network for fisheye image rectification using appearance flow, CVPR, pp.6348-6357, 2021.
Lingzhi He, Hongguang Zhu, Feng Li, Huihui Bai, Runmin Cong, Chunjie Zhang, Chunyu Lin, Meiqin Liu, Yao Zhao, Towards fast and accurate real-world depth super-resolution: Benchmark dataset and baseline, CVPR, pp.9229-9238, 2021.
Chunjie Zhang, et al, Fine-grained image classification by class and image-specific decomposition with multiple views, IEEE Transactions on Multimedia, vol.25, pp.6756-6766, 2023.
Chunjie Zhang, et. al., Exemplar-based, semantic guided zero-shot visual recognition, IEEE Transactions on Image Processing, vol.31, pp.3056-3065, 2022.
Man Liu, Chunjie Zhang, Huihui Bai, Riquan Zhang, Yao Zhao: Cross-Part Learning for Fine-Grained Image Classification. IEEE Transactions on Image Processing, 31: 748-758 (2022)
Chunjie Zhang, et. al., Multi-view image classification with visual, semantic and view consistency, IEEE Transactions on Image Processing, 29(1):617-627, 2020.
Chunjie Zhang, et. al., Beyond explicit codebook generation: Visual representation using implicitly transferred codebooks, IEEE Transactions on Image Processing, 24(12):5777-5788, Dec. 2015.
Chunjie Zhang, et. al., Structured weak semantic space construction for visual categorization, IEEE Transactions on Neural Network and Learning Systems, 29(8):3442-3451, 2018.
Chunjie Zhang, et. al., Image-specific classification with local and global discriminations, IEEE Transactions on Neural Network and Learning Systems, 29(9):4479-4486, 2018.
Chunjie Zhang, et. al., Object categorization using class-specific representation, IEEE Transactions on Neural Network and Learning Systems, 29(9):4528-4534, 2018.
Chunjie Zhang, et. al., Semantically modeling of object And context for categorization, IEEE Transactions on Neural Network and Learning Systems, 30(4):1013-1024, 2019.
Chunjie Zhang, et. al., Incremental codebook adaptation for visual representation and categorization, IEEE Transactions on Cybernetics, 48(7):2012-2023, 2018.
Chunjie Zhang, et. al., Multi-view, few-labeled object categorization by predicting labels with view consistency, IEEE Transactions on Cybernetics, 49(11):3834-3843, 2019.
Chunjie Zhang, et. al., Multiview semantic representation for visual recognition, IEEE Transactions on Cybernetics, 50(5): 2038-2049, 2020.
Chunjie Zhang, et. al., Multi-view label sharing for visual representations And Classifications, IEEE Transactions on Multimedia, 20(4):903-913, 2018.
Chunjie Zhang, et. al., Unsupervised and semi-supervised image classification with weak semantic consistency, IEEE Transactions on Multimedia, 21(10):2482-2491, 2019.
Chunjie Zhang, et. al., Contextual exemplar classifier-based image representation for classification, IEEE Transactions on Circuits and Systems for Video Technology, 27(8):1691-1699, 2017.
Chunjie Zhang, et. al., Image class prediction by joint object, context and background modeling, IEEE Transactions on Circuits and Systems for Video Technology, 28(2):428-438, 2018.
Chunjie Zhang, et. al., Bundled local features for image representation, IEEE Transactions on Circuits and Systems for Video Technology, 28(8):1719-1726, 2018.
Chunjie Zhang, et. al., Few-shot visual classification using image pairs with binary transformation, IEEE Transactions on Circuits and Systems for Video Technology, 30(9): 2867-2871, 2020.
Congqi Cao, Yifan Zhang, Chunjie Zhang, and Hanqing Lu, Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition, IEEE Transactions on Cybernetics, 48(3):1095-1108, 2018.
Chenggang Yan, Liang, Li, Chunjie Zhang, Bingtao Liu, Yongdong Zhang, Qionghai Dai, Cross-modality bridging and knowledge transferring for image understanding, IEEE Transactions on Multimedia, 21(10):2675-2685, 2019.


专著/译著

专利


软件著作权

获奖与荣誉

  • 2023年北京市科学技术奖自然科学奖二等奖

  • 2022年福建省科学技术奖科学技术进步奖二等奖

  • 2018年度中国图象图形学学会科学技术奖二等奖

  • 2020年度北京交通大学詹天佑专项奖（科技奖）

社会兼职

IEEE Senior Member

中国计算机学会  杰出会员

中国电子学会  高级会员

中国图象图形学学会  高级会员

中国人工智能学会   高级会员

中国科学院青年创新促进会 会员