♨️ SUMMARY

I obtained my Ph.D. degree in Computer Vision and Image Processing from Université Paris-Saclay, France. My research interests include semantic segmentation, object detection and tracking, unsupervised domain adaptation, and multi-modal visual data fusion. Recently, I am also interested in the application of multi-modal visual-language modeling for image understanding. In addition, I also have a rich experience in the field of industrial computer vision, including machine vision, deep learning, and robotics. I am passionate about applying my knowledge and skills to solve real-world problems.
You can check the selected projects and publications for more details.

🎓 EDUCATION

Postdoctoral Researcher, Computer Vision, Robotics, and Machine Learning

  • Systems Analysis and Architecture Laboratory (LAAS), National Centre for Scientific Research (CNRS), France. From 2024

Ph.D., Computer Vision

  • School of Sciences and Technologies of Information and Communication, Université Paris-Saclay, France
    Sept. 2020 - Oct. 2023

  • School of Engineering Sciences, Arts et Métiers (ENSAM), ParisTech, France.
    Sept. 2019 - Aug. 2020

M.Eng., Mechanical Engineering and Automation

  • School of Mechanical Engineering, Hefei University of Technology, China.
    Sept. 2014 - May. 2017
    GPA: 3.62/4.0 (rank the top 5%)​

B.Eng., Mechanical Engineering and Automation

  • School of Mechanical Engineering, Anhui Agriculture University, China.
    Sept. 2009 - Jul. 2013
    GPA: 3.68/4.0 (rank the top 10%)​

📚 RESEARCH EXPERIENCE

  • Université Paris-Saclay, STIC, Paris, France.
    Sept. 2020 - present
    Ph.D Student (IBISC Lab)

    • Research on the topic of multi-modal visual data fusion for outdoor scene understanding.
    • Investigating the influence of multi-modal visual data on the domain adaptation for semantic segmentation.
    • Studying the different fusion strategies and developing novel visual data fusion strategies for scene understanding.
    • Exploring the potential of multi-modal visual data fusion for different computer vision tasks, such as object detection, semantic segmentation, and multiple object tracking.

    Publications: [1], [2], [4], [5]

  • Arts et Métiers (ENSAM), ParisTech, Aix-en-Provence, France.
    Sept. 2019 - Aug. 2020
    Ph.D Student (LISPEN Lab)

    • Research on the topic of deep learning for multi-modal segmentation of point clouds for reverse engineering of mechanical assemblies.
    • Investigating the pipeline of deep learning-based reverse engineering.
    • Studying and designing novel algorithms for point cloud segmentation.
    • Designing and developing automatic synthetic 3D CAD models and point clouds generation tools for reverse engineering.

    Publications: [3]

  • National Institute of Informatics, Tokyo, Japan.
    Nov. 2022 - Apr. 2023
    Computer Vision Research Intern. (Prendinger Lab)

    • Investigating object detection and tracking algorithms with stereo camera from drone’s perspective.
    • Developing drone collision avoidance system based on the designed multiple object tracking algorithm.

    Publications: [6]

  • Hefei University of Technology, Hefei, China.
    Sept. 2014 - May. 2017
    M.Eng

    • Research on the application of various measurement methods in non-destructive testing, including laser triangulation, time-of-flight, spectral confocal, and monocular vision measurement methods.
    • Developing DSP-based control platforms and systems, including the design of electrical schematics, development of detection algorithms, software development for the control system, porting of communication protocols, and user interface design.

💼 WORK & LEADERSHIP EXPERIENCE

  • Cognex, Beijing, China.
    Jun. 2017 - Aug. 2019
    Machine Vision Software Engineer.

    • Responsible for over 5 industrial projects, involving the development and maintenance of applications related to vision positioning and defect detection.
    • Developed machine vision algorithms to guide robotic arms in object grasping. (A patent was filed)
    • Trained collaborative clients on artificial intelligence and its industrial applications.

    Achievements: Obtained a software copyright and an invention patent in China.

  • School of Mechanical Engineering, Hefei University of Technology, Hefei, China.
    Sept. 2015 - Jun. 2016
    Header of Party Branch.

    • Organizing discussion group (30+ members) focusing on sharing events and ideas.
    • Leading and organizing volunteer activities to foster community engagement and social responsibility.

    Achievements: Excellent Student Leaders, Hefei University of Technology, 2016​

  • Hefei University of Technology, Hefei, China.
    Mar. 2014 - Sept. 2014
    CIMS Institute Intern.

    • 3D modeling from 2D sketch and finite element analysis.

More details please check Projects.

💻 TECHNICAL SKILLS

  • Programming Languages:
     Python, C#, LaTeX, C++, C
  • Deep Learning Frameworks:
     PyTorch, TensorFlow
  • Robotics Frameworks:  ROS2
  • Software:
     OpenCV, Git, VSCode, PyCharm, Microsoft Office, SolidWorks,
     FreeCAD, AutoCAD, MATLAB
  • Operating Systems:
     Windows, Linux, MacOS

📝 PUBLICATIONS

  Get more details on Publications page.

  1. Drone-based airborne object tracking using a stereo camera for collision avoidance, IEEE Trans. on Intelligent Transportation Systems, (Q1, IF: 9.5). Sijie Hu, Desire Sidibe, Helmut Prendinger.

  2. Rethinking Self-Attention for Multispectral Object Detection, IEEE Trans. on Intelligent Transportation Systems, (Q1, IF: 9.5).
    Sijie Hu, Fabien Bonardi, Samia Bouchafa, Helmut Prendinger, Desire Sidibe.

  3. Multi-modal unsupervised domain adaptation for semantic image, Pattern Recognition 2023, (Q1, IF: 8.5).
    Sijie Hu, Fabien Bonardi, Samia Bouchafa, Desire Sidibe.

  4. SMA-Net: Deep learning-based identification and fitting of CAD models from point clouds, Enginnering with Computers 2022, (Q1, IF: 8.7).
    Sijie Hu, Arnaud Polette, Jean-Philippe Pernot

  5. A Hybrid Multi-modal Visual Data Cross Fusion Network for Indoor and Outdoor Scene Segmentation, ICPR 2022.
    Sijie Hu, Fabien Bonardi, Samia Bouchafa, Desire Sidibe.

  6. A General Two-Branch Decoder Architecture for Improving Encoder-Decoder Image Segmentation Models, VISAPP 2022.
    Sijie Hu, Fabien Bonardi, Samia Bouchafa, Desire Sidibe.

📣 TALKS & PRESENTATIONS

  • The 26th International Conference on Pattern Recognition, (Aug. 2022.)
    Topic: A Hybrid Multi-modal Visual Data Cross Fusion Network for Indoor and Outdoor Scene Segmentation.

  • IBISC Lab Seminar, Université Paris-Saclay, (Jul. 2022.)
    Topic: Multi-modal Unsupervised Domain Adaptation for Semantic Segmentation.

  • The 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. (Feb. 2022.)
    Topic: A General Two-Branch Decoder Architecture for Improving Encoder-Decoder Image Segmentation Models.

🌐 LANGUAGES

   🇨🇳 Mandarin: Native    🇬🇧 English: Fluent

🏆 AWARDS

  • “Doctoral students” Prize, Université Paris Saclay & Institut Polytechnique de Paris, 2023
  • Outstanding Graduates, Hefei University of Technology, 2017​
  • First -class scholarship, Hefei University of Technology, 2016
  • Enterprise scholarship of Anhui HELI, Hefei University of Technology, 2016
  • Excellent Student Leaders, Hefei University of Technology, 2016​
  • Advanced individual, Hefei University of Technology, 2015​
  • First -class scholarship, Hefei University of Technology, 2015​
  • First -class scholarship, Hefei University of Technology, 2014​