2025 Progress Bar (13%)

Research on AI

Christian Simon

Hi, my name is Christian Simon and I grew up in Indonesia with lovely people and cultures. Currently, I am a machine learning and audio-visual researcher, and my research problems focus on multi-modal learning for discriminative and generative models, also did meta-learning, life-long learning, and continual-learning in the past.

• Email : u6562565@anu.edu.au
• Google Scholar

News

• January 2025: Our paper with a title “Mining your own secrets: Diffusion classifier scores for continual personalization of text-to-image diffusion models” has been accepted to ICLR2025. Congratulations Saurav!
• January 2024: Our paper with a title “FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing” has been accepted to ICLR2024. Congratulations Yuren!
• October 2023: Our paper with a title “On Manipulating Scene Text in the Wild with Diffusion Models” has been accepted to WACV2024. Congratulations Joshua!
• September 2022: Our CVPR 2021 paper with a title “On learning the geodesic path for incremental learning” won the Scientific Paper Challenge 2022 organized by Dolby Australia.
• July 2022: You can call me Dr. Christian Simon now :)
• June 2022: Our team (ORBITRON) won the few-shot learning competition in the VizWiz workshop. See the leaderboard of the ORBIT Few-Shot Object Recognition Challenge HERE. You can check our published code HERE and video presentation HERE.
• March 2022: One paper is accepted to CVPR 2022, thanks to all co-authors and reviewers!

Publications

Journals

• Reflection removal under fast forward camera motion
  [pdf]
  J.Y. Cheong, C. Simon, C. S. Kim, and I. K. Park
  IEEE Transaction on Image Processing (TIP), 2018.

• Correcting geometric and photometric distortion of document images on a smartphone
  [pdf]
  C. Simon, Williem, and I. K. Park
  Journal of Electronic Imaging (JEI), 2015.

Conferences

• Mining your own secrets: Diffusion classifier scores for continual personalization of text-to-image diffusion models
  [pdf]
  S. Jha, S. Yang, M. Ishii, M. Zhao, C. Simon, M. J. Mirza, D. Gong, L. Yao, S. Takahashi, Y. Mitsufuji
  International Conference on Learning Representations (ICLR), 2025.
  

• On FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
  [pdf]
  Y Cong, M Xu, C. Simon, S Chen, J Ren, Y Xie, JM Perez-Rua,…, T. Xiang, S. He
  International Conference on Learning Representations (ICLR), 2024.
  

• On Manipulating Scene Text in the Wild with Diffusion Models
  [pdf]
  J. Santoso, C. Simon, and Williem
  IEEE Conference on Computer Vision and Pattern Recognition (WACV), 2024.
  

• On Generalizing Beyond Domains in Cross-Domain Continual Learning
  [pdf]
  C. Simon, M. Faraki, Y.-H. Tsai, X. Yu, S. Schulter, Y. Suh, M. Harandi, and M. Chandraker
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  

• Meta-Learning for Multi-Label Few-Shot Classification
  [pdf]
  C. Simon, P. Koniusz, and M. Harandi
  IEEE Winter Conference on Applications of Computer Vision (WACV), 2022.
  

• Towards a Robust Differentiable Architecture Search under Label Noise
  [pdf]
  C. Simon, P. Koniusz, and M. Harandi
  IEEE Winter Conference on Applications of Computer Vision (WACV), 2022.
  

• On learning the geodesic path for incremental learning (oral)
  [pdf]
  C. Simon, P. Koniusz, and M. Harandi
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  

• Reinforced attention for few-shot learning and beyond
  [pdf]
  J. Hong, P. Fang, W. Li, T. Zhang, C. Simon, M. Harandi, and L. Petersson
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  

• On modulating the gradient for meta-learning
  [pdf] [Supp. Mat.]
  C. Simon, P. Koniusz, R. Nock, and M. Harandi
  European Conference on Computer Vision (ECCV), 2020.
  

• Adaptive subspaces for few-shot learning
  [pdf] [Supp. Mat.]
  C. Simon, P. Koniusz, R. Nock, and M. Harandi
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
  

• Reflection removal for in-vehicle black box videos
  [pdf] [Video]
  C. Simon and I. K. Park
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
  

Awards

• The winner of Dolby Australia Scientific Paper Competition 2022.
• The winner of the ORBIT Few-Shot Object Recognition Challenge 2022 (Vizwiz workshop).
• Outstanding Reviewer ICML 2022
• Outstanding Reviewer ICLR 2021
• Outstanding Reviewer ICCV 2019 URL

Teaching Assistant:

• COMP4670/8600 Statistical Machine Learning - ANU
• ENG6528 Computer Vision - ANU

Services

Program Committee / Reviewer:

• ICLR
• Neurips
• CVPR
• ICCV
• WACV
• AAAI
• TIP
• ICML
• BMVC