Unaiza Ahsan, Ph.D.

Assistant Professor, Computer Science
Dhanani School of Science & Engineering

Education

  • Ph.D. Computer Science, Georgia Institute of Technology, Atlanta, GA
  • MEngg Computer and Information Systems, NED University of Engineering and Technology, Karachi, Pakistan
  • B.E Telecommunications, NED University of Engineering and Technology, Karachi, Pakistan

Teaching Experience

  • Graduate Research and Teaching Assistant, Georgia Institute of Technology, Atlanta, GA, 2012-2019

Courses Taught

  • Computer Vision
  • Computational Photography
  • Algorithmic Problem Solving

Biography

Unaiza Ahsan is a computer scientist and researcher interested broadly in areas within Machine Learning, Computer Vision and Recommendation Systems.

Unaiza obtained her Ph.D. at the Georgia Institute of Technology in Atlanta, where she pursued her doctorate in Computer Science. Her research involved complex activity recognition, specifically focusing on leveraging mid-level representations to enhance the accuracy and efficiency of video recognition systems without requiring large labeled datasets.

Unaiza’s professional experience includes serving as a Lead Data Scientist at The Home Depot in Atlanta, where she worked on cutting-edge recommendation algorithms using computer vision and natural language processing techniques.

As a Graduate Research Assistant at the Georgia Institute of Technology, she worked with programs such as Data Science for Social Good, where she developed web applications to address real-world challenges. Her work has spanned a wide range of topics, from event recognition in images to generating visually compatible recommendations for home décor.

During her studies, Unaiza was awarded the Schlumberger Faculty for the Future Fellowship which provided full funding for her Ph.D. at Georgia Tech.

Beyond her professional achievements, Unaiza possesses a creative spirit and enjoys expressing herself through writing poetry.


Research Interests

  • Video Recognition, Semi-Supervised Learning, Transfer Learning, Complex Event Recognition, Few-shot Learning, Action Recognition, Multi-modal Recommendations

  • Selected Publications

  • Wang, Yuanbo, Unaiza Ahsan, Hanyan Li, and Matthew Hagen. ”A Comprehensive Review of Modern Object Segmentation Approaches.” Foundations and Trends in Computer Graphics and Vision 13, no. 2-3 (2022): 111-283.
  • Unaiza Ahsan, Yuanbo Wang, Alexander Guo, Kevin D. Tynes Jr., Tianlong Xu, Estelle Afshar and Xiquan Cui. ”Visually Compatible Home Decor Recommendations Using Object Detection and Product Matching” The 2021 International Conference on Computational Science and Computational Intelligence (CSCI), 2021.
  • Al Jadda, Khalifeh, Unaiza Ahsan, and Huiming Qu. ”Complementary item recommendations based on multi-modal embeddings.” U.S. Patent Application 17/011,543, filed March 11, 2021.
  • Unaiza Ahsan, Rishi Madhok and Irfan Essa, Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition, IEEE Winter Conference on Applications of Computer Vision (WACV) 2019.
  • Bookmark the permalink.