Yun-Chun Chen






Unsplashed background img 1

About me

I am a first-year Ph.D. student in the Department of Computer Science at the University of Toronto, advised by Animesh Garg. I am also a student researcher at the Vector Institute. I received my Bachelor of Science degree in Electrical Engineering from National Taiwan University in 2018.

My research interests are in the areas of computer vision, robotics, and machine learning. I am particularly interested in transfer learning, meta learning, self-supervised learning, representation learning, video vision, and 3D vision.

Previously, I was fortunate to work with Ming-Hsuan Yang at UC Merced, Jia-Bin Huang at Virginia Tech, Yen-Yu Lin at Academia Sinica, and Winston Hsu at NTU.

If you would like to collaborate, feel free to send me an email.


News

  • 01 / 2021:   I am serving as a conference reviewer for ICCV 2021, ICML 2021, CVPR 2021, ICLR 2021, and ICRA 2021.
  • 01 / 2021:   I am working as a teaching assistant for CSC 413/2516: Neural Networks and Deep Learning (Instructor: Jimmy Ba).
  • 12 / 2020:   I am serving as a journal reviewer for International Journal of Computer Vision (IJCV).
  • 10 / 2020:   I am serving as a senior program committee for IJCAI 2021.
  • 09 / 2020:   Start my Ph.D. study at the University of Toronto and the Vector Institute.
  • 09 / 2020:   I am serving as a journal reviewer for IEEE Transactions on Image Processing (TIP).
  • 08 / 2020:   I am serving as a program committee for AAAI 2021 and WACV 2021.
  • 08 / 2020:   I am serving as a conference reviewer for CVPR 2020, ECCV 2020, NeurIPS 2020, CoRL 2020, BMVC 2020, and ACCV 2020.
  • 07 / 2020:   Two papers on neural architecture search and meta-learning are accepted to ECCV 2020.
  • 03 / 2020:   One paper on joint semantic matching and object co-segmentation is accepted to PAMI 2020.
  • 09 / 2019:   I am serving as a program committee for AAAI 2020.
  • 07 / 2019:   One paper on cross-resolution generative modeling is accepted to ICCV 2019.
  • 03 / 2019:   I am serving as a conference reviewer for ICCV 2019, BMVC 2019, and ICIP 2019.
  • 02 / 2019:   One paper on unsupervised domain adaptation is accepted to CVPR 2019.
  • 11 / 2018:   One oral paper on representation learning is accepted to AAAI 2019.
  • 10 / 2018:   We won the Third Place in IEEE Video and Image Processing (VIP) Cup.
  • 07 / 2018:   One paper on semantic matching is accepted to ACCV 2018.

Selected Publications

Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos
Submitted to IEEE International Conference on Robotics and Automation (ICRA), 2021
[Paper] [Project page] [Video]
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
European Conference on Computer Vision (ECCV), 2020
[Paper] [Project page] [GitHub] [Colab] [Highlight video] [Highlight slides] [Full video] [Full slides]
Learning to Learn in a Semi-Supervised Fashion
European Conference on Computer Vision (ECCV), 2020
[Paper]
Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2020
[Paper] [Project page] [Code] [Slides]
Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)
Major Revision
[Paper]
Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
IEEE International Conference on Computer Vision (ICCV), 2019
[Paper] [Slides] [Poster]
CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[Paper] [Project Page] [Code] [Slides] [Poster]
Learning Resolution-Invariant Deep Representations for Person Re-Identification
AAAI Conference on Artificial Intelligence (AAAI), 2019
Oral Presentation
[Paper] [Slides] [Poster]
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Asian Conference on Computer Vision (ACCV), 2018
[Paper] [Project Page] [Code] [Poster]