Research

Preprints

• A Denoising Loss Bound for Neural Network based Universal Discrete Denoisers
  Taesup Moon
  Submitted
• Supervised Neural DUDE for adaptive discrete denoising
  Sungmin Cha, Seonwoo Min, Byunghan Lee, Sungroh Yoon, and Taesup Moon Submitted

2021

• [C28] Fair Feature Distillation for Visual Recognition
  Donggyu Lee, Sangwon Jung, Taeeon Park, and Taesup Moon
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
• [C27] FBI: Fast Blind Image Denoiser for Source-Dependent Noise (Oral)
  Jaeseok Byun, Sungmin Cha, and Taesup Moon
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
• [J19] Prediction Model for Random Variation in FinFET Induced by Line-Edge-Roughness (LER)
  Jinwoong Lee, Taeeon Park, Hongjoon Ahn, Jihwan Kwak, Taesup Moon, and Changhwan Shin
  Electronics (IF=2.412), 10(4), 455, February 2021
• [J18] Deep Learning Aided Blind Synchronization Word Estimation
  Yong-sung Kil, Jun Min Song, Sang-Hyo Kim, Taesup Moon, and Seok-Ho Chang
  IEEE Access (IF=3.745), February 2021
• [C26] CPR: Classifier-projection regularization for continual learning
  Sungmin Cha, Hsiang Hsu, Taebaek Hwang, Flavio P. Calmon, and Taesup Moon
  International Conference on Learning Representations (ICLR), May 2021
  4th Lifelong Learning Workshop (LifelongML) at ICML 2020, July 2020
• [C25] GAN2GAN: Generative noise learning for blind image denoising with single noisy images
  Sungmin Cha, Taeeon Park, Byeongjoon Kim, Jongduk Baek, and Taesup Moon
  International Conference on Learning Representations (ICLR), May 2021
  NeurIPS 2020 Workshop on Deep Learning and Inverse Problems, December 2020
• [J17] Continual Learning of Micro-Doppler Signatures based Human Activity Classification
  Donggyu Lee, Hyeongmin Park, Taesup Moon, and Youngwook Kim
  IEEE Geoscience and Remote Sensing Letters (IF=3.833), January 2021 (Early Access)

2020

• [C24] Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
  Sangwon Jung, Hongjoon Ahn, Sungmin Cha, and Taesup Moon
  Neural Information Processing Systems (NeurIPS), December 2020
  CVPR Workshop on Continual Learning in Computer Vision (CLVISION), June 2020
• [J16] Learning blind pixelwise affine image denoiser with single noisy images
  Jaeseok Byun and Taesup Moon
  IEEE Signal Processing Letters (IF=3.268), 10.1109/LSP.2020.3002652, June 2020
• [C23] Iterative channel estimation for discrete denoising under channel uncertainty
  Hongjoon Ahn and Taesup Moon
  Conference on Uncertainty in Artificial Intelligence (UAI), August 2020
• [C22] Unsupervised neural universal denoiser for finite-input general-output noisy channel
  Taeeon Park and Taesup Moon
  International Conference on Artificial Intelligence and Statistics (AISTATS), August 2020
• [J15] Interpreting machine learning models in neuroimaging: Towards a unified framework
  Lada Kohoutova, Juyeon Heo, Sungmin Cha, Sungwoo Lee, Taesup Moon, Tor D. Wager, and Choong-Wan Woo
  Nature Protocols (IF=11.334), https://doi.org/10.1038/s41596-019-0289-5, March 2020
• [J14] Estimating PM2.5 concentration of the conterminous United States via interpretable convolutional neural networks (press)
  Yongbee Park, Byungjoon Kwon, Juyeon Heo, Xuefei Hu, Yang Liu, and Taesup Moon
  Environmental Pollution (IF=5.714), https://doi.org/10.1016/j.envpol.2019.113395, January 2020
• [W] A simple class decision balancing for incremental learning
  Hongjoon Ahn and Taesup Moon
  CVPR Workshop on Continual Learning in Computer Vision (CLVISION), June 2020

2019

• [C21] Uncertainty-based continual learning with adaptive regularization (code,press)
  Hongjoon Ahn, Sungmin Cha, Donggyu Lee and Taesup Moon
  Proceedings of Neural Information Processing Systems (NeurIPS), December 2019
• [C20] Fooling neural network interpretations via adversarial model manipulation (code,press)
  Juyeon Heo, Sunghwan Joo, and Taesup Moon
  Proceedings of Neural Information Processing Systems (NeurIPS), December 2019
  ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models (VXAI), November 2019
• [C19] Working vacation scheduling of M^X/M/1/N system using neural networks
  Yongbee Park and Taesup Moon
  7th International Conference on Robot Intelligence Technology and Applications (RiTA), November 2019
• [C18] Fully convolutional pixel adaptive image denoiser (code)
  Sungmin Cha and Taesup Moon
  Proceedings of IEEE International Conference on Computer Vision (ICCV), October 2019
• [J13] Skip-connected 3D DenseNet for volumetric infant brain MRI segmentation
  Toan Duc Bui, Taesup Moon, and Jitae Shin
  Biomedical Signal Processing and Control, Vol.54, September 2019, 101613
• [C17] Subtask gated networks for non-intrusive load monitoring
  Changho Shin, Sunghwan Joo, Jaeryun Yim, Hyoseop Lee, Taesup Moon, and Wonjong Rhee
  Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), January 2019
• [C16] DoPAMINE: Double-sided masked CNN for pixelwise adaptive multiplicative noise despeckling (Oral)
  Sunghwan Joo, Sungmin Cha, and Taesup Moon
  Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), January 2019

2018

• [C15] UDLR Convolutional Network for Adaptive Image Denoiser
  Sungmin Cha and Taesup Moon
  International Conference on Robot Intelligence Technology and Applications (RiTA), December 2018
• [C14] Fast DCNN-based human activity classification with on-body antenna using generative models
  Hyeongmin Park and Taesup Moon
  International Symposium on Antennas and Propagation (ISAP), October 2018
• [J12] Dynamic functional connectivity analysis reveals improved association between brain networks and eating behaviors compared to static analysis
  Bo-yong Park, Taesup Moon and Hyunjin Park
  Behavioural Brain Research, vol. 337, p.114-121, January 2018
• [C13] Neural adaptive image denoiser
  Sungmin Cha and Taesup Moon
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2018

2017

• [J11] DUDE-Seq: Fast, flexible, and robust denoising for targeted amplicon sequencing
  Byunghan Lee, Taesup Moon, Sungroh Yoon and Tsachy Weissman
  PLoS ONE (doi.org/10.1371/journal.pone.0181463), July 2017

2016

• [J10] Micro-Doppler based classification of human aquatic activities via transfer learning of convolutional neural networks
  Jinhee Park, Rios Jesus Javier, Taesup Moon, and Youngwook Kim
  Sensors, 2016,16,1990, November 2016
• [C12] Neural universal discrete denoiser
  Taesup Moon, Seonwoo Min, Byunghan Lee, and Sungroh Yoon
  Proceedings of Neural Information Processing Systems (NIPS), December 2016
• [C11] Classification of human activity on water through micro-Dopplers using deep convolutional neural networks
  Youngwook Kim and Taesup Moon
  Proceedings of SPIE 9829, Radar Sensor Technology XX, 982917, May 2016
• [J9] Regularization and kernelization of the maximin correlation approach
  Taehoon Lee, Taesup Moon, Seung Jean Kim and Sungroh Yoon
  IEEE Access, vol. 4, pp. 1385-1392, April 2016
• [J8] Human detection and activity classification based on micro-Dopplers using deep convolutional neural networks (3rd most downloaded paper (Aug 2016, July 2016) in IEEE GRSL)
  Youngwook Kim and Taesup Moon
  IEEE Geoscience and Remote Sensing Letters, vol.13, no.1, pp.8-12, January 2016

2015

• [C10] RNNDrop: A novel dropout for RNNs in ASR
  Taesup Moon, Heeyoul Choi, Hoshik Lee, and Inchul Song
  Proceedings of 2015 IEEE Automatic Speech Recognition and Understanding (ASRU) Workshop, December 2015
• [J7] Evaluation of a MISR-based high-resolution aerosol retrieval method using AERONET DRAGON campaign data
  Taesup Moon, Yueqing Wang, Yang Liu, and Bin Yu
  IEEE Transactions on Geoscience and Remote Sensing, vol.53, no.8, pp.4328-4339, August 2015

Before 2015

• [J6] Exploiting user preference for online learning in recommender systems
  Jiang Bian, Bo Long, Lihong Li, Taesup Moon, Anlei Dong, and Yi Chang
  ACM Transactions on Intelligent Systems and Technology, vol.5, no.2, April 2014
• [J5] An online learning framework for refining recency search results with user click feedback
  Taesup Moon, Lihong Li, Wei Chu, Zhaohui Zheng, and Yi Chang
  ACM Transactions on Information Systems, vol. 30, no.4, 20:1-20:28, November 2012
• [J4] Universal switching FIR filtering
  Taesup Moon
  IEEE Transactions on Signal Processing, vol.60, no.3, pp.1460-1464, March 2012
• [C9] An unbiased offline evaluation of contextual bandit algorithms with generalized linear models
  Lihong Li, Wei Chu, John Langford, Taesup Moon, Xuanhui Wang
  Journal of Machine Learning Research - Workshop and Conference Proceedings 26: On-line Trading of Exploration and Exploitation 2, pp.19-36, May 2012
• [C8] Discrete denoising of heterogeneous two-dimensional data
  Taesup Moon, Tsachy Weissman, and Jae-Young Kim
  Proceedings of 2011 IEEE International Symposium on Information Theory (ISIT), pp.966–970, St. Petersburg, Russia, August 2011
• [C7] Learning to model relatedness for news recommendation
  Yuanhua Lv, Taesup Moon, Pranam Kolari, Zhaohui Zheng, Xuanhui Wang, and Yi Chang
  Proceedings of the 20th International World Wide Web (WWW) Conference, pp.57-66, Hyderabad, India, March 2011
• [C6] User behavior driven ranking without editorial judgments
  Taesup Moon, Shihao Ji, Georges Dupret, Ciya Liao, and Zhaohui Zheng
  Proceedings of the 19th ACM International Conference on Information and Knowledge Management (CIKM) (short paper), pp.1473–1476, Toronto, Canada, October 2010
• [C5] Online learning for recency search ranking using real-time user feedback
  Taesup Moon, Lihong Li, Wei Chu, Zhaohui Zheng, and Yi Chang
  Proceedings of the 19th ACM International Conference on Information and Knowledge Management (CIKM) (short paper), pp.1501–1504, Toronto, Canada, October 2010
• [C4] IntervalRank - Isotonic regression with listwise and pairwise constraints
  Taesup Moon, Alex Smola, Yi Chang, and Zhaohui Zheng
  Proceedings of the 3rd ACM International Conference on Web Search and Data Mining (WSDM), pp.151–159, New York, NY, February 2010
• [J3] Discrete denoising with shifts
  Taesup Moon and Tsachy Weissman
  IEEE Transactions on Information Theory, vol. 55, no.11, pp.5284–5301, November 2009
• [J2] Universal FIR MMSE filtering
  Taesup Moon and Tsachy Weissman
  IEEE Transactions on Signal Processing, vol.57, no.3, pp.1068-1083, March 2009
• [J1] Universal filtering via hidden Markov modeling
  Taesup Moon and Tsachy Weissman
  IEEE Transactions on Information Theory, vol.54, no.2, pp.692–708, February 2008
• [C3] Discrete denoising with shifts
  Taesup Moon and Tsachy Weissman
  Proceedings of the 45th Annual Allerton Conference on Communication, Control, and Computation, Monticello, Illinois, September 2007
• [C2] Competitive on-line linear FIR MMSE filtering
  Taesup Moon and Tsachy Weissman
  Proceedings of 2007 IEEE International Symposium on Information Theory (ISIT), pp.1126–1130, Nice, France, June 2007
• [C1] Discrete universal filtering via hidden Markov modeling
  Taesup Moon and Tsachy Weissman
  Proceedings of 2005 IEEE International Symposium on Information Theory (ISIT), pp.1285–1289, Adelaide, Australia, September 2005

Patents and Defensive Publications

• Denoiser, and control method thereof
  Taesup Moon
  US Patent Application 20180137405 A1, May 2018
• Neural network training method and apparatus, and data processing apparatus
  Taesup Moon, Yeha Lee, and Heeyoul Choi
  US Patent Application 20160026913 A1, Jan 2016
• Related news articles
  Taesup Moon, Pranam Kolari, Zhoahui Zheng, Xuanhui Wang, Yi Chang, and Yuanhua Lv
  US Patent US8713028 B2, April 2014
• A method of using a pairwise learning model in an online recommendation system
  Jiang Bian, Bo Long, Lihong Li, Taesup Moon, Anlei Dong, and Yi Chang
  IP.com Prior Art Database Disclosure, Disclosure Number IPCOM000216302D, March 2012
• Method and system of online learning for recency search ranking using real-time user feedback
  Taesup Moon, Wei Chu, Lihong Li, Zhaohui Zheng, and Yi Chang
  IP.com Prior Art Database Disclosure, Disclosure Number IPCOM000203007D, January 2011

Thesis

• Learning from noisy data with applications to filtering and denoising
  PhD Thesis, Stanford University, September 2008
  Reading committee: Tsachy Weissman, Thomas M. Cover, Abbas El Gamal