Eu Wern Teh
AI Research Scientist
LG Electronics
Toronto, ON, Canada
CV • Google Scholar • Linkedin
About Me
As an AI Research Scientist at LG Toronto AI Lab, I drive advancements in Speech-Driven Animation and Image
Generation & Enhancement (SDR-to-HDR). I leverage my expertise in annotation-efficient learning to innovate in
SCarcely Annotated Data Environments (SCADE), building robust AI models that deliver strong performance with
limited data. My work has made an impact across diverse fields, from Cancer Classification in Digital Pathology
and Fine-Grained Bird Species analysis to various commercial applications. I earned my Ph.D. in Engineering from
the University of Guelph (advised by Prof. Graham Taylor), complementing my degrees from the University of
Manitoba.
Recent News
- NEW 02/2024: My paper about 3D Face Tracking from 2D Videos is accepted to CVPR2024!
- 09/2022: I started my role as an AI Research Scientist with LG Toronto AI Lab
- 04/2022: My paper about understanding image and input resolution for Digital Pathology is accepted to CRV 2022!
- 04/2022: My paper about semi-supervised semantic segmentation is accepted to CRV 2022!
- 01/2022: My paper about annotation-efficient learning via Scribble Supervision is accepted to ISBI 2022!
- 07/2020: My paper about metric learning is accepted to ECCV 2020!
- 05/2020: I have started my research internship with Modiface.
- 01/2020: My paper about annotation-efficient learning is accepted to ISBI 2020!
- 05/2019: I have a paper accepted to MIDL 2019!
- 04/2019: I have a paper accepted to CRV 2019!
- 07/2018: Attended ANR-NSERC Deepvision Meeting in Iceland. (Canada-France research collaboration)
- 07/2018: Presented at the Machine Learning workshop in Iceland
- 07/2018: Attended 2018 Deep Learning Summer School in Toronto
- 08/2017: I have a paper accepted to VCIP 2017!
- 07/2017: I have a paper accepted to BMVC 2017!
- 07/2016: I have a paper accepted to BMVC 2016!
|
|
Research
|
3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow
Felix Taubner, Prashant Raina, Mathieu Tuli, Eu Wern Teh, Chul Lee, Jinmiao Huang
Computer Vision and Pattern Recognition (CVPR), 2024.
[paper]
|
|
Learning with less labels in Digital Pathology via Scribble Supervision from natural images
Eu Wern Teh and Graham Taylor
International Symposium on Biomedical Imaging (ISBI), 2022.
[paper]
|
|
Understanding the impact of image and input resolution on deep digital pathology patch classifiers
Eu Wern Teh and Graham Taylor
Conference on Computer and Robot Vision (CRV), 2022.
[paper]
|
|
The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
Eu Wern Teh and Terrance DeVries and Brendan Duke and Ruowei Jiang and Parham Aarabi and Graham Taylor
Conference on Computer and Robot Vision (CRV), 2022.
[paper]
|
|
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis
Eu Wern Teh and Terrance DeVries and Graham Taylor
European Conference on Computer Vision (ECCV), 2020.
[paper]
[source code]
|
|
Learning with less data via Weakly Labeled Patch Classification in Digital Pathology
Eu Wern Teh and Graham Taylor
International Symposium on Biomedical Imaging (ISBI), 2020.
[paper]
|
|
Metric Learning for Patch Classification in Digital Pathology
Eu Wern Teh and Graham Taylor
Medical Imaging with Deep Learning (MIDL), 2019.
[paper]
|
|
Apparent Age Estimation with Relational Networks
Eu Wern Teh and Graham Taylor
Conference on Computer and Robot Vision (CRV), 2019.
[paper]
[source code]
|
|
Object Localization in Weakly Labeled Data Using Regularized Attention Networks
Eu Wern Teh, Zhenyu Guo and Yang Wang
Vision Communications and Image Processing (VCIP), 2017.
[paper]
|
|
Adapting Object Detectors from Images to Weakly Labeled Videos
Omit Chanda, Eu Wern Teh, Mrigank Rochan, Zhenyu Guo, and Yang Wang
British Machine Vision Conference (BMVC), 2017.
[paper]
|
|
Attention Networks for Weakly Supervised Object Localization
Eu Wern Teh, Mrigank Rochan, and Yang Wang
British Machine Vision Conference (BMVC), 2016.
[paper]
|
|
Visual Analytics of Social Networks: Mining and Visualizing Co-authorship Networks
Carson Leung, Christopher Carmichael, Eu Wern Teh
Foundations of Augmented Cognition. (FAC), 2011.
[paper]
|
|
