Xiaodong Yu

Summary: ▪ 13 years of industry experience and 8 years of research experience in machine learning, data science, and computer vision ▪ 7 years of experience of managing and leading development teams in industries ▪ 7 years of experience of mentoring less experienced team members in algorithms, software development, project management, etc

Research Interests: ▪ Machine learning: deep learning, graphical models and Bayesian networks, transfer learning ▪ Computer vision: object recognition and detection, image understanding and segmentation, video event detection, 3D reconstruction

Technology stacks: ▪ Machine learning software packages: scikit-learn, PyMC3, TensorFlow ▪ Data manipulation and visualization: Pandas, Matplotlib, seaborn ▪ Database: Snowflake, SQL Server, Oracle, MySQL ▪ Computer vision, computer graphics and computational geometry: OpenCV, OpenMVG, PCL, Three.js, Babylon.js, Blender/Cycles+Python ▪ Programming: Python, JavaScript, C/C++, Matlab

Mentoring and Teaching Experience: ▪ Taught IT 450 Database Concepts at Old Dominion University in Fall semester 2019 ▪ Mentored junior data scientists and interns in company ▪ Tutorials on deep learning and computer vision on Norfolk Data Science meetup ▪ Oral presentations at international machine learning and computer vision conferences

Education

• Doctor of Philosophy (PhD) University of Maryland College Park (2004 — 2011)
• Master of Science (MSc) National University of Singapore (1999 — 2001)
• Bachelor's degree University of Science and Technology of China (1994 — 1999)

Companies

• Senior Data Scientist (remote) Evolve (2021)
• Data Science Manager PRA Group (Nasdaq: PRAA) (2019 — 2021)
• Adjunct Professor Old Dominion University (2019 — 2019)
• Founder Nebulae 3D, LLC (2015 — 2019)
• Senior Researcher Comcast (2011 — 2014)
• Research Assistant University of Maryland (2004 — 2011)
• Summer Intern, Research and Development Engineer ADF Solutions Inc. (2006 — 2008)
• Research Associate Nanyang Technological University (2003 — 2004)
• Research And Development Engineer Vislog (2001 — 2003)

Publications

Journal Articles

• G. Zhu, X. Yu, Y. Li, and D. Doermann, "Language Identi.cation for Handwritten Document Images Using A Shape Codebook", Pattern Recognition, vol. 42, no. 12, pp. 3184-3191, 2009.
• X. Yu, L. Duan, P. Xue, and Q. Tian, "An Algorithm to Estimate Mean Vehicle Speed from MPEG Skycam Video", Multimedia Tools and Applications, vol. 34, no. 1, pp. 85-105, 2007.
• X. Yu, L. Wang, Q. Tian, and P. Xue, "A Novel Multi-Resolution Video Representation Scheme Based on Kernel PCA", The Visual Computer: International Journal of Computer Graphics, vol. 22, no. 5, pp. 357-370, 2006.

Selected Conference Papers

• X. Yu, C. Fermuller, C. L. Teo, Y. Yang and Y. Aloimonos, "Active Scene Recognition with Vision and Language", International Conference on Computer Vision (ICCV), 2011
• X. Yu and Y. Aloimonos, "Attribute-based Transfer Learning for Object Categorization with Zero or One Training Example", European Conference on Computer Vision (ECCV), 2010
• G. Zhu, X. Yu, Y. Li and D. Doermann, "Learning Visual Shape Lexicon for Document Image Content Recognition", European Conference on Computer Vision (ECCV), 2008
• X. Yu, D. DeMenthon and D. Doermann, "Support Vector Data Description for Image Categorization From Internet Images", (oral), International Conference on Pattern Recognition (ICPR), 2008
• X. Yu, Y. Li, C. Fermuller, and D. Doermann, "Object Detection Using a Shape Codebook", (oral), British Machine Vision Conference (BMVC), University of Warwick, UK, 2007.