Chen-Yu Lee

Chen-Yu Lee


  • Electrical and Computer Engineering
  • University of California, San Diego
  • chenyulee260 at gmail.com
  • [ CV | Google Scholar ]

About Me

I am a lead software engineer at Magic Leap with a research focus on deep learning. I completed my PhD at UC San Diego in 2016, advised by Professors Zhuowen Tu and Pamela Cosman. My research interests are in computer vision, machine learning, and deep learning.

Publications

RoomNet: End-to-End Room Layout Estimation

Chen-Yu Lee, Vijay Badrinarayanan, Tomasz Malisiewicz, and Andrew Rabinovich
IEEE International Conference on Computer Vision (ICCV), 2017
[ PDF ]

Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree

Chen-Yu Lee, Patrick Gallagher, and Zhuowen Tu
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
[ PDF ]

Recursive Recurrent Nets with Attention Modeling for OCR in the Wild

Chen-Yu Lee and Simon Osindero
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[ PDF ]

Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree

Chen-Yu Lee, Patrick Gallagher, and Zhuowen Tu
International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.
[ PDF | Code ]

Training Deeper Convolutional Networks with Deep Supervision

Liwei Wang, Chen-Yu Lee, Zhuowen Tu, and Svetlana Lazebnik
arXiv:1505.02496, 2015
[ PDF | Code | Performance on MIT Place205 ]

Deeply-Supervised Nets

Chen-Yu Lee*, Saining Xie*, Patrick Gallagher, Zhengyou Zhang, and Zhuowen Tu (*equal contribution)
International Conference on Artificial Intelligence and Statistics (AISTATS), 2015.
Earlier in Advances in Neural Information Processing Systems (NIPS) Workshop on Deep Learning, 2014. (Oral)
[ PDF | Code | arXiv | Link ]

Region-based Discriminative Feature Pooling for Scene Text Recognition

Chen-Yu Lee, Anurag Bhardwaj, Wei Di, Vignesh Jagadeesh, and Robinson Piramuthu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
[ PDF ]

Tracking Epithelial Cell Junctions in C. elegans Embryogenesis with Active Contours Guided by SIFT Flow

Sukryool Kang, Chen-Yu Lee, Monira Goncalves, Andrew Chisholm, and Pamela Cosman
IEEE Transactions on Biomedical Engineering (TBME), 2014.
[ PDF ]

Automated Cell Junction Tracking with Modified Active Contours Guided by SIFT Flow

Chen-Yu Lee, Sukryool Kang, Andrew Chisholm, and Pamela Cosman
IEEE International Symposium on Biomedical Imaging (ISBI), 2014.
[ PDF | Demo ]

Smoke Detection Using Spatial and Temporal Analyses

Chen-Yu Lee, Chin-Teng Lin, Chao-Ting Hong, and Miin-Tsair Su
International Journal of Innovative Computing Information and Control (IJICIC), 2012.
[ PDF ]

Spatio‐temporal Analysis in Smoke Detection

Chen-Yu Lee, Chin‐Teng Lin, and Chao‐Ting Hong
IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 2009.
[ PDF | Project page ]

Patent

System and Method for Scene Text Recognition

Anurag Bhardwaj, Chen-Yu Lee, Robinson Piramuthu, Vignesh Jagadeesh, and Wei Di
US Patent No. 9245191 (2016/1/26)
[ Link ]

Other Projects

Eye Gaze Estimation using Epipolar Geometry [ PDF | Demo ]
Image Warping and Mosaicing [ Link ]
Sparse Stereo Matching [ Link ]
Logistic Regression with Stochastic Gradient Descent [ PDF ]
Conditional Random Fields for Word Hyphenation [ PDF ]
Latent Dirichlet Allocation for Text and Image Topic Modeling [ PDF ]
Learning Meanings for Sentences with Recursive Autoencoders [ PDF ]