朱文成,天津大学人工智能学院副研究员,水木学者,硕士生导师,55教学楼B519。 2014和2017年取得天津大学学士和硕士学位,导师是胡清华教授和朱鹏飞教授; 2021年6月取得清华大学博士学位,导师是鲁继文教授; 2021年7月清华大学水利系做博士后研究,合作导师是张建民院士。 2023年11月入职天津大学人工智能学院, 主要关注视觉-语言大模型的感知、推理与强化学习策略。招收有自驱力和好奇心的硕士生,一起点亮未知,让科研成为一场充满惊喜的旅程!

I obtained my Bachelor and Master degrees from Tianjin University of Computer Science and Technology, advised by Prof. Qinghua Hu and Pengfei Zhu. I received my Doctoral degree at the Department of Automation, Tsinghua University, in Intelligent Vision Group, under the supervision of Prof. Jiwen Lu. I conducted postdoctoral research at Civil and Hydraulic Engineering, Tsinghua University, under the supervision of Prof. Jian-Min Zhang, an academician of the Chinese Academy of Engineering.

I joined the School of Artificial Intelligence at Tianjin University in November 2023, focusing on perception, reasoning, and reinforcement learning strategies of vision-language large models.

Google Scholar  /  GitHub  /  Email

Drop me an email (wenchengzhu AT tju dot edu dot cn) for the 2025 and 2026 master and phd application !!!

profile photo
News

  • 2025-03: One paper on video recognition is submitted to Arxiv.
  • 2024-08: The National Natural Science Foundation Youth Fund was funded.
  • 2024-05: One paper on knowledge distillation is submitted to Arxiv.
  • 2022-03: One paper on video summarization is accepted to IEEE Transactions on Image Processing 2022.
  • 2021-09: One paper on video summarization is accepted to Pattern Recognition 2021.
  • 2021-06: Selected into the Shuimu Tsinghua Scholar Program.
  • 2021-02: One paper on video object segmentation is accepted to IEEE Transactions on Circuits and Systems for Video          Technology 2021.
  • 2020-11: One paper on video summarization is accepted to IEEE Transactions on Image Processing 2020.
  • 2019-09: One paper on subspace clustering is accepted to Pattern Recognition 2019.
  • 2017-01: One paper on subspace clustering is accepted to Pattern Recognition 2017
  • 2016-08: One paper on visual tracking is nominated for the best paper PRICAI 2016.
  • Selected Publications

    dise VTD-CLIP: Video-to-Text Discretization via Prompting CLIP
    Wencheng Zhu, Yuexin Wang, Hongxuan Li, Pengfei Zhu, and Qinghua Hu
    Arxiv , 2025

    [PDF] [Code] [bibtex]

    Our method repurposes the frozen text encoder to construct a visual codebook from video class labels due to the many-to-one contrastive alignment between visual and textual embeddings in multimodal pretraining.

    dise CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective
    Wencheng Zhu, Xin Zhou, Pengfei Zhu, Yu Wang, and Qinghua Hu
    Arxiv , 2024

    [PDF] [Code] [bibtex]

    We propose a sample-wise contrastive knowledge distillation approach.

    dise Relational Reasoning over Spatial-Temporal Graphs for Video Summarization
    Wencheng Zhu, Yucheng Han, Jiwen Lu, and Jie Zhou
    IEEE Transactions on Image Processing (TIP), 2022

    [PDF] [bibtex]

    We conduct relational reasoning over spatial-temporal graphs for video summarization.

    dise Learning Multiscale Hierarchical Attention for Video Summarization
    Wencheng Zhu, Jiwen Lu, Yucheng Han, and Jie Zhou
    Pattern Recognition (PR), 2021

    [PDF] [bibtex]

    We propose a multiscale hierarchical attention approach for supervised video summarization.

    dise Separable Structure Modeling for Semi-supervised Video Object Segmentation
    Wencheng Zhu, Jiahao Li, Jiwen Lu, and Jie Zhou
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021

    [PDF] [Code] [Video]

    We propose a separable structure modeling approach for semi-supervised video object segmentation.

    dise DSNet: A Flexible Detect-to-Summarize Network for Video Summarization
    Wencheng Zhu, Jiwen Lu, Jiahao Li, and Jie Zhou
    IEEE Transactions on Image Processing (TIP), 2020

    [PDF] [Code] [bibtex]

    We propose a Detect-to-Summarize network for video summarization.

    dise Structured General and Specific Multi-view Subspace Clustering
    Wencheng Zhu, Jiwen Lu, and Jie Zhou
    Pattern Recognition (PR), 2019
    [PDF] [bibtex]

    A multiple subspace clustering approach.

    dise Nonlinear Subspace Clustering for Image Clustering
    Wencheng Zhu, Jiwen Lu, and Jie Zhou
    Pattern Recognition Letters (PRL), 2018

    [PDF] [bibtex]

    We propose a nonlinear subspace clustering approach for image clustering.

    dise Nonlinear Subspace Clustering
    Wencheng Zhu, Jiwen Lu, and Jie Zhou
    IEEE International Conference on Image Processing (ICIP), 2017
    [PDF] [bibtex]

    We propose a nonlinear subspace clustering approach.

    dise Subspace Clustering guided Unsupervised Feature Selection
    Pengfei Zhu, Wencheng Zhu, Qinghua Hu, Changqing Zhang, Wangmeng Zuo
    Pattern Recognition (PR), 2017
    [PDF] [Code] [bibtex]

    We propose a feature selection approach based on subspace clustering.

    dise Non-convex Regularized Self-representation for Unsupervised Feature Selection
    Pengfei Zhu, Wencheng Zhu, Weizhi Wang, Wangmeng Zuo, Qinghua Hu
    Image and Vision Computing (IVC), 2016
    [PDF] [Code] [bibtex]

    We propose a non-convex regularized feature selection approach.

    dise Set to Set Visual Tracking
    Wencheng Zhu, Pengfei Zhu, Qinghua Hu, Changqing Zhang
    Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2016
    [PDF] [Code] [bibtex]

    We propose a visual tracking approach by using set to set distance.

    Honors and Awards

  • The Shuimu Tsinghua Scholar Program, Tsinghua University, 2021.
  • Outstanding Graduate, Tianjin University, 2017.
  • National Scholarship, Tianjin University, 2016-2017.
  • Best Paper Nomination on PRICAI 2016.
  • Outstanding Graduate, Tianjin University, 2014.
  • Fundings and Projects

  • The National Natural Science Foundation Youth Fund, 2025-2027.
  • Professional Activities

  • Young editorial board of Intelligent Security.
  • Journal Reviewer of TIP, TNNLS, TKDE, TCYB, TMM, TCSVT, TOMM, TCSS, PR, PRL.
  • Conference Reviewer of CVPR, ICCV, ICLR, ICME, WACV, FG, ICIP, ICPR, VCIP, IScIDE.
  • Students

  • Hongxuan Li, Master candidate, 2025-2028.
  • Jiazhen Ma, Master candidate, 2025-2028.
  • Xiaokun Wang, Master candidate, 2025-2028.
  • Wenchang Xu, Master candidate, 2025-2028.

  • Website Template