Ming-Ming Cheng

Ming-Ming Cheng is a professor at Nankai University, the Executive Dean of the School of Excellent Engineers, and the academic leader of the media computing team. He received his Ph.D. from Tsinghua University in 2012 and then worked with Prof. Philip Torr in Oxford for two years. He has presided over projects including the National Science Fund for Distinguished Young Scholars, the National Science Fund for Excellent Young Scholars, and major project topics of the Ministry of Science and Technology of China. His main research directions cover artificial intelligence, computer vision, and computer graphics. He has published more than 100 academic papers in top-tier conferences/journals, including more than 40 in IEEE TPAMI. His h-index is 100, with more than 70,000 citations on Google Scholar. He has been selected as a Highly Cited Researcher (2022-2025) by Clarivate. His technical achievements have been applied to flagship products of multiple institutions, including Huawei and the National Disaster Reduction Center of China. He has won 2 first prizes in Natural Science awarded by the Ministry of Education of China and 2 other provincial- and ministerial-level science and technology awards. Four Ph.D. students supervised by him have won the provincial and ministerial-level Outstanding Doctoral Dissertation Award. Currently, he serves as the Director of the Tianjin Key Laboratory of Visual Computing and Intelligent Perception, Vice Chairman of the Tianjin Artificial Intelligence Society, and an editorial board member of top journals, including IEEE TPAMI, IEEE TIP, and Science China Information Sciences. [CV]

程明明，南开大学二级教授，卓越工程师学院执行院长，媒体计算团队学术带头人。主持承担了国家杰出青年科学基金、优秀青年科学基金项目、科技部重大项目课题等。他的主要研究方向是人工智能、计算机视觉和计算机图形学，在SCI一区/CCF A类刊物上发表学术论文100余篇（含IEEE TPAMI论文40余篇），h-index为100，论文谷歌引用7万余次，单篇最高引用5千余次，多次入选全球高被引科学家和中国高被引学者。技术成果被应用于华为、国家减灾中心等多个单位的旗舰产品。获得教育部自然科学一等奖2项、其他省部级科技奖2项。培养的4名博士生获得省部级优秀博士论文奖。现担任天津市视觉计算与智能感知重点实验室主任、中国图象图形学学会副秘书长、天津市人工智能学会副理事长和顶级期刊IEEE TPAMI, IEEE TIP和《中国科学：信息科学》编委。[简历]

招收博士、硕士研究生，来信前请务必阅读：关于研究生招生

Research

I’m currently working on image scene analysis, editing, and retrieval. These works primarily focus on the following aspects: (I) biologically motivated salient region detection and segmentation; (II) sketch-based image retrieval and composition; (III) interactive image analysis and manipulation; (IV) analysis of similar scene elements for smart image manipulation. These works attempted to recover parts of scene object-level information from images, drawing inspiration from biology or utilizing simple user assistance in sketch form. Such scene object-level information includes one or more parts of the following aspects: the object of interest regions, object correspondence, region layering, symmetry, repetition, and 3D relations. Ideally, we expect the automatic extraction of full 3D information, including category names, attributes, and object relations, about the underlying image scene for intelligent image understanding, manipulation, organization, and retrieval. [Research galleries]

Selected Publications

My publications can be found here. See also: DBLP, Google, Scopus, arXiv, Publons. Here are some recent publications.

  1. Large-scale Unsupervised Semantic Segmentation, Shanghua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng*, Junwei Han, Philip Torr, IEEE TPAMI, 45(6):7457-7476, 2023. [pdf | code | bib | 中译版]
  2. A Highly Efficient Model to Study the Semantics of Salient Object Detection, Ming-Ming Cheng*#, Shanghua Gao#, Ali Borji, Yong-Qiang Tan, Zheng Lin, Meng Wang, IEEE TPAMI, 2022. [pdf | bib | project | code | 中译版]
  3. Structure-measure: A New Way to Evaluate Foreground Maps, Ming-Ming Cheng*, Deng-Ping Fan, IJCV,129(9):2622-2638, 2021. [pdf | code | bib |project | ä¸­è¯‘版]
  4. Res2Net: A New Multi-scale Backbone Architecture, Shanghua Gao#, Ming-Ming Cheng*#, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr, IEEE TPAMI, 43(2):652-662, 2021. [pdf | code | project |PPT | bib  | ä¸­è¯‘版]
  5. Richer Convolutional Features for Edge Detection, Yun Liu, Ming-Ming Cheng*, Xiaowei Hu, Jia-Wang Bian, Le Zhang, Xiang Bai, Jinhui Tang, IEEE TPAMI, 41(8):1939-1946, 2019. [pdf|project|bib|code|中译版]
  6. Deeply supervised salient object detection with short connections, Qibin Hou, Ming-Ming Cheng*, Xiaowei Hu, Ali Borji, Zhuowen Tu, Philip Torr, IEEE TPAMI, 41(4):815-828, 2019.  [pdf|project|bib|code]
  7. Structure-Preserving Neural Style Transfer, Ming-Ming Cheng*#, Xiao-Chang Liu#, Jie Wang, Shao-Ping Lu, Yu-Kun Lai, Paul L. Rosin, IEEE TIP, 29:909-920, 2020. [pdf | bib | project | code]
  8. Shifting More Attention to Video Salient Object Detection, Deng-Ping Fan, Wenguan Wang, Ming-Ming Cheng*, Jianbing Shen, IEEE CVPR (Oral & Best Paper Finalist), 2019. [pdf|bib|中译版|code|project]
  9. 互联网图像驱动的语义分割自主学习, 侯淇彬, 韩凌昊, 刘姜江, 程明明*, 中国科学：信息科学, 2021. [pdf | bib | project]
  10. 认知规律启发的物体分割评价标准及损失函数，范登平, 季葛鹏, 秦雪彬, 程明明*, 中国科学：信息科学, 2021. [ pdf | code | bib ]

媒体计算实验室老师

丁丹
教授
国家级高层次人才
杨巨峰
教授
国家级四青人才
李重仪
教授
国家级四青人才
范登平
教授
国家级四青人才
刘云
教授
国家级四青人才
刘夏雷
教授
国家级四青人才
郭青
教授
国家级四青人才
孙国磊
教授
国家级四青人才
侯淇彬
副教授
国家级四青人才
任博
教授
南开百青
李翔
副教授
南开百青
郭春乐
副教授
南开百青
戴一冕
副教授
姜智卓
副教授
南开百青
黄川
副教授.
南开百青

We are looking forward to having elegant students or researchers join us. Positions for Master’s, Ph.D., and post-doc are opening. If you are interested in our research and want to join us, please send your CV (maximum 2 pages) and grades to cmm_AT_nankai.edu.cn.

Research Collaborators (partial)

We collaborate with leading scientists and researchers worldwide, with whom many highly influential pieces of research have been made possible. We encourage faculty and students to continue such collaborations by doing joint research and/or physically visiting these collaborators.

Shi-Min Hu
Tsinghua
中国科学院院士
Philip Torr
Oxford Univ.
Fellow of the Royal Society
Shui-Cheng Yan
NUS
IEEE/IAPR Fellow
Zhuo-Wen Tu
UCSD
Marr Prize winner
Ming-Hsuan Yang
UC Merced
IEEE Fellow
Paul Rosin
Cardiff Univ.
IAPR Fellow
Niloy Mitra
UCL
SIGGRAPH Award Winner

奖励与荣誉

  • 2025: 开放环境自适应视觉感知理论与方法，天津市自然科学奖一等奖，程明明, 侯淇彬, 胡清华, 汪萌, 王煜,高尚华, 刘云, 姜鹏涛
  • 2023: 视觉媒体的层次化内容感知，教育部自然科学一等奖，赵耀, 程明明, 魏云超, 侯淇彬, 韦世奎
  • 2020: 图像场景理解与内容敏感图像处理，吴文俊人工智能科学技术奖自然科学二等奖，程明明, 侯淇彬, 杨巨峰, 范登平, 刘云
  • 2019: 弱监督条件下的图像语义分割研究，中国图象图形学学会科学技术奖一等奖，赵耀，程明明，魏云超
  • 2019: 天津市中青年科技创新领军人才
  • 2019: 天津市青年科技奖
  • 2016年度国家“万人计划”青拔
  • 2016: ACM中国新星奖
  • 2015: 中科协青年人才托举计划
  • 2013: åŒ—京市优秀博士论文奖
  • 2013: å¯è§†åª’体几何计算的理论与方法，教育部自然科学一等奖，胡事民、黄继武、艾海舟、陈韬、黄畅、程明明、来煜昆、毕宁、项世军

博士生

郑兆晖
李震
王家宝
靳鑫
朱子悦
李钟毓
å¼ æ—­è¿Ž

硕士生

武睿祺
陈宇铭
周宇鹏
翟江天
段正鹏

历年毕业生

学制说明：本科直博默认5年学制，普博生默认4年，硕转博转后按照普博生重新计算。实验室到目前为止没有学生超过上述年限，大约20-30%的博士生提前毕业。

范登平
国家级”四青”
普博 2015–2019
侯淇彬
国家级”四青”
普博 2016–2019
刘云
国家级”四青”
直博 2016–2020
赵凯
上海大学副教授
普博 2017-2020
吴宇寰
新加坡AStar研究员
直博 2018-2022
梅杰
博新计划A档
普博 2019-2022
刘姜江
京东
转博 2017-2022
姜鹏涛
研究员@vivo
转博 2017-2022
高尚华
哈佛大学博后
转博 2018-2023
Gang Xu
光明实验室副研
直博 2018-2023
æž—é“®
CCF CAD&CG优博
直博 2018-2023
李震
阿里
普博 2020-2024
郑兆晖
CCF-CV 新秀奖
普博 2021-2025
李钟毓
青云计划@腾讯
直博 2021-2026
å¼ æ—­è¿Ž
TGT@京东
普博 2022-2026
边佳旺
南洋理工助理教授
本科 2012–2016
徐婧祎
Stony Brook
本科 2015–2019
李仕杰
Ph.D. @ Bonn
硕士 2016–2019
胡晓伟
字节跳动
硕士 2016–2019
赵嘉星
阿里星 @ 阿里
硕士 2017–2020
曹洋
Ph.D. @ HKUST
硕士 2017–2020
张长彬
Ph.D. @ HKU
硕士 2018–2021
陈林卓
Ph.D. @ NJU
硕士 2018–2021
韩琦
阶跃星辰
硕士 2018–2021
顾宇超
Nvidia@新加坡
硕士 2019–2022
å¼ é’Š
AI先锋@商汤
硕士 2019–2022
翟江天
天演资本
硕士 2022–2025
杨雨奇
百度
硕士 2022–2025

学术服务

143 thoughts on “Ming-Ming Cheng”

  • UsainBoltFastest
    21/05/2026 at 09:56
    Permalink

    程老师好，请问您或者您团队的其他老师有开展过图片、文本对抗样本的研究吗？这里提的对抗样本是指对原始样本进行一系列变换，使得深度神经网络或者大模型等在分类问题上产生误判的样本。感谢各位老师

    Reply

    • 我们组郭青老师有一些相关的研究

      Reply

  • 老师，你好，暑假招ra吗？

    Reply

  • Hello Professor Cheng,

    I recently read your paper (SANet: A Slice-Aware Network for Pulmonary Nodule Detection) and was impressed by it. I’m interested in researching lung cancer detection with CT image data and was wondering if you could provide me with the PN9 dataset you used. I have tried reaching out to the co-author, Mei Jie, for the dataset, according to the website instructions but haven’t heard back, so I just wanted to check with you if I could get some help with that.
    Thank you very much

    Reply

  • 程老师， 您好，我最近在做视频显著性检测的相关工作，发现您的网址：https://mmcheng.net/davsod/，对视频显著性做了详细的解释，但是网址上相关的图片都失效了，无法显示，能否给我分享下相关的图片和视频呢？（wjx514051264@126.com）

    Reply

  • Pingback: FocusCut: Diving into a Focus View in Interactive Segmentation – Zheng Lin

  • 程老师您好！读了您2015年的《Global Contrast Based Salient Region Detection》，请问下在哪可以找到相关程序代码呢？如果您方便可否麻烦您发至我的邮箱，或者提供下载地址呢？

    Reply
    • MM ChengPost author
      10/01/2024 at 10:25
      Permalink

      这里有，好几个论文的代码都在一个C++ project里面：https://github.com/MingMingCheng/CmCode/

      Reply
  • 海天1度
    21/08/2021 at 13:59
    Permalink

    程老师您好！想要请教一些关于Video Salient Object Detection (VSOD)以及Eye Fixation Prediction(EFP)的问题。（若有什么理解或表达错误的地方，恳请老师指正。）
    （1）我看到一些采用半监督方法做VSOD的工作，但是，目前没有调研到采用半监督方法做EFP的工作，请问采用半监督做EFP，是不是有什么不合理的地方，或者是有哪些难点目前没办法解决？
    （2）在DAVSOD数据集中，我发现少数fixation_map中标注的点，并不在GT_object标注的那个轮廓线内，所以，我就在想，对于Video Salient Object和Eye Fixation，人眼所关注的东西，是不是有些差别？还是说忽略了些什么东西？

    祝好！

    杜丽娜（Dulina@emails.bjut.edu.cn）

    Reply

    • SOD其实是有一些先验的。参考我2015å¹´çš„PAMI论文，仅用对比度先验（无需监督信息）就可以得到很不错的SOD结果。因此，半监督的去做VSOD本质上并不困难。但是Fixation就很难了。Fixation的主观性太强，gt的一致性也要低很多。因此采用半监督的方法弄起来就要困难很多。

      Reply

  • 老师您好，看了2019çš„cpfp后想索要一份该模型在SIP数据集下的结果图片集，不知道能不能分享一下。

    Reply
    • MM ChengPost author
      30/07/2021 at 21:08
      Permalink

      数据和结果都在项目主页上 http://dpfan.net/d3netbenchmark/
      建议由具体问题也在具体paper页面下方留言

      Reply

  • 老师您好，看完您发表的文章《Structure-Preserving Neural Style Transfer》后，我有一些疑问，希望老师在繁忙工作之余，帮我解惑一下，万分感谢。
    1，训练的时，生成网络的输入只有X_content, 是不是每次训练后的网络只能生成特特定style的图片。
    2，训练时将style的图片和content的图片同时输入到网络中，会不会使网络有更好的拓展性。

    Reply
    • MM ChengPost author
      30/07/2021 at 21:07
      Permalink

      这个工作主要是研究如何保持结构。后续有很多工作支持同时输入style和content

      Reply
  • 王华珂
    23/01/2021 at 22:54
    Permalink

    程老师，您的网课《论文写作指导》链接失效，可否更新一下链接？

    Reply
    • MM ChengPost author
      21/02/2021 at 15:04
      Permalink

      我登录腾讯课堂，好像后台也显示已经失效。没找到怎么恢复。估计只能以后重新录制了。

      Reply
  • 吕朝晖
    13/01/2021 at 16:22
    Permalink

    程老师，请问2021 CVPR 还会有 Learning from Imperfect Data Challenge and Workshop 吗？

    Reply
  • 研二宣树星
    13/11/2020 at 16:51
    Permalink

    程老师，您好，我看到您网站的一篇2020eccv的工作，Gradient-Induced Co-Saliency Detection，我看到这篇文章提出的拼图训练策略想实现一下，但不是很理解，发现提供的代码没有train部分，可以分享一下嘛

    Reply

    • 您好，已经发送给您。

      Reply

  • 老师您好，我是澳门大学的研究生，想在您的基础上继续研究Semantic Edge Detection算法，我承诺不将代码或基于您的代码的研究成果商用，请问可以发我一份Semantic Edge Detection with Diverse Deep Supervision训练代码嘛？

    Reply

    • 您好，因为这篇论文仍然在审稿状态（两年了），所以现阶段不方便共享代码。一旦论文被接收，我们一定第一时间开源代码。

      Reply

  • 程老师您好，有幸拜读了您主页publications里展示的2020PAMI弱监督实例分割论文《Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation》，所取得的结果令人印象深刻，请问您能否繁忙的工作之余，分享一下实验所用的代码，十分感激！！！

    留意到github上在1年前已经有这篇文章的项目，但是目前只有Code is coming soon…

    Reply

    • 你好。谢谢提醒。论文录用的时候刚好碰上近期cvpr deadline，没时间快速整理。我们计划cvpr deadline之后整理一下放出来。

      Reply

  • 老师您好，有幸拜读了您发表的文章《Structure-Preserving Neural Style Transfer》，对其应用在所取得的结果令人印象深刻，请问您能否繁忙的工作之余，分享一下在实验所用的代码，十分感激！！！

    Reply
    • MM ChengPost author
      30/09/2020 at 11:17
      Permalink

      谢谢提醒，我们尽快准备。当时做这个项目的学生毕业了，所以进度有点慢。

      Reply

Leave a Reply

Your email address will not be published. Required fields are marked *

@ARTICLE{Gao22LUSS,
  author={Gao, Shanghua and Li, Zhong-Yu and Yang, Ming-Hsuan and Cheng, Ming-Ming and Han, Junwei and Torr, Philip},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={Large-scale Unsupervised Semantic Segmentation}, 
  year={2023},
  volume={45},
  number={6},
  pages={7457-7476},
  doi={10.1109/TPAMI.2022.3218275}
}
No, thank you. I do not want.
100% secure your website.
Powered by 
@ARTICLE{21PAMI-Sal100K,
  author={Ming-Ming Cheng and Shang-Hua Gao and Ali Borji and Yong-Qiang Tan and Zheng Lin and Meng Wang},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={A Highly Efficient Model to Study the Semantics of Salient Object Detection}, 
  year={2022},
  volume={44},
  number={11},
  pages={8006-8021},
  doi={10.1109/TPAMI.2021.3107956}
}
@inproceedings{GaoEccv20Sal100K,
  title={Highly Efficient Salient Object Detection with 100K Parameters},
  author={Shang-Hua Gao and Yong-Qiang Tan and Ming-Ming Cheng and Chengze Lu and Yunpeng Chen and Shuicheng Yan},
  booktitle = {European Conference on Computer Vision (ECCV)},
  pages = {702-721},
  doi = {10.1007/978-3-030-58539-6_42}, 
  year={2020},
}
@article{Cheng2021sMeasure,
  title={Structure-measure: A New Way to Evaluate Foreground Maps},
  author={Ming-Ming Cheng and Deng-Ping Fan},
  journal={International Journal of Computer Vision (IJCV)},
  year={2021},
  volume={129},
  number={9},
  pages={2622-2638},
  doi = {10.1007/s11263-021-01490-8},
}
Powered by 
@ARTICLE{pami21Res2net, 
  author={Shang-Hua Gao and Ming-Ming Cheng and Kai Zhao and Xin-Yu Zhang and Ming-Hsuan Yang and Philip Torr}, 
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={Res2Net: A New Multi-scale Backbone Architecture}, 
  year={2021}, 
  volume={43}, 
  number={2}, 
  pages={652-662}, 
  doi={10.1109/TPAMI.2019.2938758}, 
}

 

@ARTICLE{TIP20_SP_NPR, 
	author={Ming-Ming Cheng and Xiao-Chang Liu and Jie Wang and Shao-Ping Lu and Yu-Kun Lai and Paul L. Rosin}, 
	journal={IEEE Transactions on Image Processing}, 
	title={Structure-Preserving Neural Style Transfer}, 
	year={2020}, 
	volume={29},  
	pages={909-920}, 
	doi={10.1109/TIP.2019.2936746}, 
}

 

@ARTICLE{21SC_WebSegE,
    author={侯淇彬 and 韩凌昊 and 刘姜江 and 程明明},
    journal={中国科学：信息科学}, 
    title={互联网图像驱动的语义分割自主学习}, 
    year={2021},
    volume={51},
    number={7},
    pages={1084-1099},
    doi={10.1360/SSI-2020-0146},
}

@ARTICLE{21SC_WebSeg,
    author={Qibin Hou and Linghao Han and Ming-Ming Cheng},
    journal={Sci Sin Inform}, 
    title={Autonomous Learning of Semantic Segmentation from Internet Images (in Chinese)}, 
    year={2021},
    volume={51},
    number={7},
    pages={1084-1099},
    doi={10.1360/SSI-2020-0146},
}

 

@article{21SC-EmeasureCN,
  author = {范登平 and 季葛鹏 and 秦雪彬 and 程明明},
  title = {认知规律启发的物体分割评价标准及损失函数},
  journal = {中国科学：信息科学},
  year = {2021},
  pages = {1475-1489},
  volume={51},
  number={9},
  doi = {https://doi.org/10.1360/SSI-2020-0370}
}

@article{21SC-Emeasure,
  author = {Dengping Fan and Gepeng Ji and Xuebin Qin and Ming-Ming Cheng},
  title = {Cognitive Vision Inspired Object Segmentation Metric and Loss Function},
  journal = {SCIENTIA SINICA Informationis},
  pages = {1475--1489},
  volume = {51},
  number = {9},
  doi = "https://doi.org/10.1360/SSI-2020-0370",
}