Zhongzheng (Jason) Ren
PhD Student
Department of Computer Science
University of Illinois Urbana-Champaign (UIUC)
Email: zr5 [at] illinois [dot] edu
GitHub / CV / Google Scholar / LinkedIn

Aloooha! I am currently a PhD student in the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC), working with Alex Schwing. Previously, I obtained Master's in Computer Science from UC Davis after spending two wonderful years with Yong Jae Lee. I completed Bachelor of Software Engineering at Sun Yat-sen University (中山大学).

I spent summer 2020 at Facebook AI Research (FAIR) working with Ishan Misra and Rohit Girdhar, summer 2018 and 2019 at NVIDIA Research working with Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz. I worked as machine learning researcher at EgoVid with Michael S. Ryoo from 2017 to 2018.

My research wouldn't be possible without support made by Yee Memorial Fund Fellowship, Yunni & Maxine Pao Memorial Fellowship, Amazon AWS, UC Davis, and UIUC. Thanks so much!

Research Interests: Computer Vision and Machine Learning.
I am particularly interested in 4D reconstruction and visual learning from limited labeled data.

News

  • One paper is accepted into CVPR'21 on 3D weakly-supervised recognition. Stay tuned!
  • I'll join Adobe Research for 2021 summer internship!
  • Thrilled to receive the 2021 Yee Fellowship. Thanks!
  • Received an outstanding reviewer award by ICLR 2021! Thanks!
  • Check out our recent work on semi-supervised, weakly-supervised, and omni-supervised learning.
  • Publications

    3D Spatial Recognition without Spatially Labeled 3D
    Zhongzheng Ren, Ishan Misra, Alexander G. Schwing, Rohit Girdhar
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
    BIBTEX
    Not All Unlabeled Data are Equal: Learning to Weight
    Data in Semi-supervised Learning

    Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing
    (* indicates equal contribution)

    Neural Information Processing Systems (NeurIPS), 2020
    PDF | BIBTEX | Project
    UFO2: A Unified Framework towards Omni-supervised Object Detection
    Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu,
    Alexander G. Schwing, Jan Kautz

    European Conference on Computer Vision (ECCV), 2020
    PDF | BIBTEX | Project
    Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
    Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu,
    Yong Jae Lee, Alexander G. Schwing, Jan Kautz

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    PDF | BIBTEX | Project
    Also presented at CVPR'20 Visual Learning with Limited Labels Workshop.
    Learning to Anonymize Faces for Privacy Preserving Action Detection
    Zhongzheng Ren, Yong Jae Lee, Michael S. Ryoo
    European Conference on Computer Vision (ECCV), 2018
    PDF | BIBTEX | Project YouTube
    Also presented at CVPR'18 workshop on The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security.
    Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery
    Zhongzheng Ren, Yong Jae Lee
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
    PDF | BIBTEX | Project
    Who moved my cheese? Automatic Annotation of Rodent Behaviors with Convolutional Neural Networks
    Zhongzheng Ren, Adriana Noronha, Annie Vogel Ciernia, Yong Jae Lee
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2017
    PDF | BIBTEX | Project

    Teaching

    We (mostly Alex) developed an efficient tool PDFCrop for creating Compass/Blackboard online exam from pdf files. Check out this demo video and reach out if you need access!

  • ECE 544: Pattern Recognition (Fall 2020), UIUC
    Teaching Assistant (TA) with Alex Schwing
  • CS 446/ECE 449: Machine Learning (Spring 2020), UIUC
    Teaching Assistant (TA) with Alex Schwing
  • ECS 174: Computer Vision (Spring 2017), UC Davis
    Teaching Assistant (TA) with Yong Jae Lee
  • Misc.

  • My Chinese name is 任中正.
  • I maintain awesome-self-supervised-learning on Github. You are more than welcome to contribute and share :)
  • My Erdős number is 4 computed by csauthors.net. Try yours:)
    Paul Erdős -> Ronald L. Graham -> Chung-Kuan Cheng -> Xiaodong Yang -> Zhongzheng Ren.