Scholar
Rohan Bali
Google Scholar ID: WJe4gBoAAAAJ
PhD student at the University of Arizona
Citations & Impact
Citations
134
H-index
4
i10-index
3
Publications
13
Co-authors
9
list available
Publications
Resume (English only)
Research Experience
- - Research Engineer at Facebook Reality Labs (April 2017 - Present)
- - Part of a team focused on building virtual telepresence, working on data capture software, large-scale data processing, and implementing computer vision and machine learning research.
- - Improved keypoint detection quality by 10% through changes to the training pipeline for the keypoint detection ML model (PyTorch).
- - Made architectural updates to the keypoint detection ML model (PyTorch).
- - Designed and implemented a failure detection and retraining pipeline for state-of-the-art keypoint and segmentation detectors, leading to a 20% improvement in predicted keypoint quality (PyTorch).
- - Developed a speech to facial animation prediction model using Bi-LSTM (PyTorch).
- - Developed Computer Vision-based metrics to evaluate the quality of keypoint annotations (Python).
- - Designed and implemented a pipeline for early evaluation of data capture quality (Python).
- - Created monitoring and alerting solutions for fast detection of issues in the data capture pipeline (Python, SQL, PHP).
- - Created a data management system to support PII data captured during user studies (ReactJS, PHP).
- - Created a data management system to support large scale data annotation (Python, PHP).
- - Developed and upgraded 2D and 3D annotation tools for annotating over one million data points (JavaScript - ReactJS, PHP, SQL, Python, C++).
- - Collaborated in designing a user study capture process that has captured over a thousand hours of data.
- - Led the development of multiple custom software solutions to help Research Assistants interact with research tools and software (C++, Python).
- - Independent Contractor (Jan 2016 - Mar 2017)
- - Worked with researchers, clinics, and corporations to develop software and hardware solutions at the intersection of physical movement and machine learning.
- - Co-founder and CTO of Kite & Canary (Aug 2013 - Jan 2016)
- - Co-founded and led a healthcare software startup from infancy to producing $300k yearly revenue.
- - Planned project roadmap and supervised the development of iOS, WatchOS, Web, and Server Side projects.
- - Collaborated with hospitals and researchers in Toronto to produce technical innovations in health care by providing recording, hosting, and analysis solutions for human kinematic and physiological data.
Education
- - Master of Applied Science (M.A.Sc.) in Computer Engineering, University of Toronto
- - Thesis: Mapping Acoustics to Kinematics in Speech
- - GPA: 3.7/4
- - Bachelor of Science (B.S.) in Electrical Engineering (minor Computer Science), University of Illinois at Urbana-Champaign
- - GPA: 3.5/4
Background
- Skilled Research Engineer with over 7 years of hands-on experience in implementing research and creating systems which support research.
