Home
I am an engineer and researcher broadly interested in the areas of computer vision, machine learning and signal processing. I am currently a Technical Lead at Google.
[Google Scholar] [Linkedin] [Resume]
I can be reached at arvindganesh [AT] gmail [DOT] com.
Bio
I have been at Google since June 2014. I started out with the Video Search team where I worked on video annotations in Google Photos. This work powered personal video search and automatic creation of short animation videos. I currently work in the Feed Ads team at Google India. In the past, I have worked in Google Maps on designing and building ML pipelines for extracting useful semantic information from user-contributed images. I have also worked on building explainable ML models for detecting abuse in Google Ads traffic.
Prior to Google, I was the Lead Computer Vision Engineer at Baarzo, where I worked on architecting scalable algorithms for semantic understanding of videos. Baarzo was acquired by Google in June 2014.
I was a Research Scientist in the Business Analytics and Mathematical Sciences team at IBM India Research Lab in Bengaluru in 2012-13. I worked on predictive modeling in incomplete or missing data.
I graduated with a Ph.D. in Electrical & Computer Engineering at the University of Illinois, Urbana-Champaign in 2012. I worked under the guidance of Prof. Yi Ma on the topic of using compressed sensing and low-rank matrix recovery methods for applications in computer vision.
I graduated from IIT-Madras in 2006 with a Dual Degree (B.Tech & M.Tech) in Electrical Engineering.