祝闯 (Chuang Zhu)
副教授，博导
Room702, Mingguang Building, Xitucheng Road, BUPT, Beijing, China
邮箱: czhu@bupt.edu.cn
[Google Scholar] [Researchgate] [Github]
教育背景及研究兴趣
2015年1月获得北京大学电子科学与技术专业博士学位。2015年至2017年在北京大学计算机应用方向从事博士后研究工作。目前在北京邮电大学人工智能学院智能感知与计算教研中心从事机器学习、计算机视觉以及图像处理相关研究工作。曾获得博士后面上一等资助，获得北京大学博雅博士后荣誉资助。主持国家自然青年基金和北京市自然基金各一项，参与科技部重大仪器等项目多项。 曾指导学生获得中国计算机学会计算机视觉专委会（CCF-CV）联合举办的RACV 2016专题竞赛一等奖（模糊车牌图像清晰化挑战赛第一名）, 获得顶会MICCAI 2019图像分类和分割任务冠军（DigestPath2019）。在图像视频领域著名期刊和会议上发表论文多篇，如IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Medical Imaging (TMI), IEEE Transactions on multimedia (TMM)，IJCAI, ECCV等。是IEEE Transactions on Image Processing (TIP),TMM和IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)等期刊的审稿人, AAAI2021 PC成员。
围绕“多模态智能感知”，相关具体研究方向包括：
1. 机器学习算法理论；（需有AI、计算机、通信等背景）
2. 多模态智能感知算法（多模态视频/图像/事件/文本）；（需有AI、计算机等背景）
3. 高能效AI算法及其优化；（需有AI、计算机、通信等背景）
4. 基于嵌入式SoC系统（FPGA、GPU和ARM等）的AI算法部署和应用。（需有电子、集成电路、信通等背景）
招收博士生、硕士生和实习生：招收对科研有热情，能够自驱型成长的博士生(希望申请者有探索欲，热爱科研), 硕士生（希望申请者算法动手能力强或者有过论文发表/投稿经历）和实习生（长期有效，结合兴趣参与相应项目，欢迎大二大三的同学提前进入实验室），欢迎发邮件咨询。
Open! 有电子电路/集成电路背景，考虑未来向AI算法方向（多模态机器学习/深度学习算法及算法优化）交叉发展的同学，有未来读博打算的欢迎咨询。
News
[2025/03] One paper accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (2024 IF=20.8)
[2025/01] One paper accepted to IEEE Transactions on Multimedia (2024 IF=8.4)
[2024/09] One paper accepted to Knowledge-Based Systems (2024 IF=7.2)
[2023/08] One paper accepted to JAMA Network Open (2023 IF=13.8)
[2023/05] One paper accepted to IJCAI 2023 (CCF A)
[2022/04] One paper accepted to Gastric Cancer (2022 IF=7.7)
[2021/11] One paper accepted to IEEE Transactions on Medical Imaging (2022 IF=11)
[2021/09] One paper accepted to Frontiers in Oncology (2021 IF =6.244); two papers accepted to ICCV 2021 workshops
[2021/05] 恭喜梅柯获得北京邮电大学2021年度“校园十大先锋人物” - 学术科研先锋
[2021/04] One paper accepted to The American Journal of Pathology (2021 IF =4.307)
[2021/01] One paper accepted to Neurocomputing (2021 IF =5.7)
[2020] One paper accepted to ECCV 2020
[2019] Champion (Team: "kuanguang") of MICCAI 2019 DigestPath2019 challenge
[2019] Congrats to Wutong: one of the best oral presentations in ICCPR 2019
[2016] Champion (Team: "PrimaryCvVers") of CCF RACV 2016
竞赛获奖
[2022/08] 第八届互联网+北京市一等奖，产业赛道北京市第三名
[2022/07] 国际噪声标签挑战赛 (IJCAI-ECAI 2022)，第三名
[2021/08] 第七届互联网+北京市一等奖，国家铜奖
[2019] 医疗顶会MICCAI比赛 DigestPath2019 国际冠军：Champion (Team: "kuanguang") of MICCAI 2019
[2016] 计算机协会CCF专题竞赛（模糊车牌清晰化挑战赛）冠军：Champion (Team: "PrimaryCvVers") of CCF RACV 2016
Professional Activities
Reviewer, Neural Information Processing Systems (NIPS)
PC member, AAAI Conference on Aritficial Intelligence (AAAI)
Reviewer, International Conference on Machine Learning (ICML)
Reviewer, IEEE Transactions on Cybernetics
Reviewer, IEEE Transactions on Image Processing (TIP)
Reviewer, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Reviewer, IEEE Transactions on Instrumentation & Measurement
Reviewer, IEEE Transactions on multimedia (TMM)
Selected Publications [Detail]
[2025] Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation, Chuang Zhu, Kebin Liu, Wenqi Tang, Ke Mei, Jiaqi Zou，Tiejun Huang, IEEE Transactions on Pattern Analysis and Machine Intelligence （TPAMI）, 2025/3.
[2025] Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation, Xinyang Huang, Chuang Zhu, Ruiying Ren, Shengjie Liu, Tiejun Huang, IEEE Transactions on Multimedia （TMM）, 2025/1.
[2021] [PDF][CODE] Hard Sample Aware Noise Robust Learning for Histopathology Image Classification, Chuang Zhu, Wenkai Chen, Ting Peng, Ying Wang, Mulan Jin, IEEE Transactions on Medical Imaging, 2021/11.
[2021] [PDF][CODE][PROJECT] LLVIP: A Visible-infrared Paired Dataset for Low-light Vision, Xinyu Jia, Chuang Zhu, Minzhen Li, Wenqi Tang, Wenli Zhou, 2021/8, ICCV 2021 workshop.
[2021] [PDF][CODE][PROJECT] Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark, Shuhao Qiu, Chuang Zhu, Wenli Zhou, 2021/8, ICCV 2021 workshop.
[2021] [PDF][CODE][DigestPath2019] Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet, Chuang Zhu, Ke Mei, Ting Peng, Yihao Luo, Jun Liu, Ying Wang, Mulan Jin, 2021/5/28, Neurocomputing, 438, 165-183.
[2021] [PDF][CODE] Hybrid model enabling highly efficient follicular segmentation in thyroid cytopathological whole slide image, Chuang Zhu, Siyan Tao, Huang Chen, Minzhen Li, Ying Wang, Jun Liu, Mulan Jin, Intelligent Medicine, 2021.
[2020] [PDF][CODE] Instance adaptive self-training for unsupervised domain adaptation, Ke Mei, Chuang Zhu, Jiaqi Zou, Shanghang Zhang, ECCV 2020.
[2020] [PDF][CODE] Cross-stained segmentation from renal biopsy images using multi-level adversarial learning，Ke Mei, Chuang Zhu, Lei Jiang, Jun Liu, Yuanyuan Qiao, ICASSP 2020.
[2020] [PDF] A novel tool to provide predictable alignment data irrespective of source and image quality acquired on mobile phones: what engineers can offer clinicians, Teng Zhang, Chuang Zhu, Qiaoyun Lu, Jun Liu, Ashish Diwan, Jason Pui Yin Cheung, European Spine Journal, 2020.
[2019] [PDF][CODE] Breast cancer histopathology image classification through assembling multiple compact CNNs, Chuang Zhu, Fangzhou Song, Ying Wang, Huihui Dong, Yao Guo, Jun Liu, BMC Medical Informatics and Decision Making, 2019.
[2019] [PDF][CODE] Breast cancer image classification on WSI with spatial correlations, Jiandong Ye, Yihao Luo, Chuang Zhu, Fang Liu, Yue Zhang, ICASSP 2019.
[2018] [PDF] Breast cancer histology image classification based on deep neural networks, Yao Guo, Huihui Dong, Fangzhou Song, Chuang Zhu, Jun Liu, ICIAR 2018.
[2017] [PDF][CODE] LLCNN: A convolutional neural network for low-light image enhancement, Li Tao, Chuang Zhu, Guoqing Xiang, Yuan Li, Huizhu Jia, Xiaodong Xie, VCIP 2017.
[2017] [PDF] Low-light image enhancement using CNN and bright channel prior, Li Tao, Chuang Zhu, Jiawen Song, Tao Lu, Huizhu Jia, Xiaodong Xie, ICIP 2017.
[2016] [PDF] Smart query expansion scheme for CDVS based on illumination and key features, Tao Lu, Chuang Zhu, Huizhu Jia, Lingyu Duan, Li Tao, Jiawen Song, Xiaodong Xie, Wen Gao, ICPR 2016.
[2014] [PDF] Multi-level low-complexity coefficient discarding scheme for video encoder, Chuang Zhu, Huizhu Jia, Jie Liu, Xianghu Ji, Hao Lv, Xiaodong Xie, Wen Gao, ISCAS 2014.
[2013] [PDF] On a highly efficient RDO-based mode decision pipeline design for AVS, Chuang Zhu, Huizhu Jia, Shanghang Zhang, Xiaofeng Huang, Xiaodong Xie, Wen Gao, IEEE Transactions on Multimedia, 2013.
[2011] [PDF] A highly efficient pipeline architecture of RDO-based mode decision design for AVS HD video encoder, Chuang Zhu, Yuan Li, Hui-zhu Jia, Xiao-dong Xie, Hai-bing Yin, ICME 2011.