Joy Arulraj
Georgia Institute of Technology, GA·Computer Science·Early-career
Machine learning models can now find objects and actions in video. But running them over large video collections is slow, and using them to answer questions takes a lot of programming.
- Fields
Computer Science
Engineering
- Topics
video analytics
video database management systems
database systems
- Grants
- 1 known grant, through Mar 2028
What they work on
- Design query optimizers tailored to offline, exploratory video analytics that use accuracy-driven optimization to reduce the cost of running complex computer vision pipelines over large video datasets.
- Broaden video database systems beyond object detection to support richer queries such as action localization and object re-identification across video.
- Develop techniques for generating synthetic video datasets to address the shortage of large datasets caused by privacy concerns.
More about the research
Answering a question such as "find every play that led to a touchdown in this football game" can be very costly. Video database management systems aim to make such questions faster and easier to ask. Applications range from urban planning to astrophysics.
Why it matters
Analyzing large video collections currently takes heavy computing and human effort. Faster, more flexible video database systems could cut the cost of video analysis for scientists and companies in fields from urban planning to astrophysics. Synthetic video datasets could also ease research limits caused by privacy concerns.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Andrew Pavlo
Carnegie Mellon University, PA·Computer Science
Develop automatic code transformations that speed up user-defined functions (UDFs) inside SQL queries without requiring changes to application code.
Dan Suciu
University of Washington, WA·Computer Science
Compute upper bounds on query output size that are guaranteed never to be exceeded, deriving the tightest possible bound from information theory given statistics a database already stores, such as table cardinalities, distinct-value counts, and maximum degrees.
Zeyu Ding
Binghamton University, NY·Computer Science
Build automated tools that analyze an SQL database schema and help users interactively define a customizable privacy model specifying which data elements need differential-privacy protection, and which variant.
The school
Georgia Institute of Technology: 50 labs on PI Pages, $1.5B a year on research, 572 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.