For computer vision fans, the Computer Vision and Pattern Recognition (CVPR) conference is a significant annual event, regularly drawing thousands of attendees and paper submissions. The  Georgia Institute of Technology had nine papers by 33 authors accepted in the conference, taking place online this year starting June 14.
 
Accepted papers covered a wide range of topics within computer vision such as improving assistive robotics, visual question answering, and identifying where people in videos are looking.
 
Georgia Tech also participated by organizing four workshops; Visual Question Answering and Dialog Workshop, Learning with Limited Labels, UG2 Challenge, and the Embodied AI Workshop.
 
Machine Learning Center at Georgia Tech (ML@GT) and School of Interactive Computing faculty members Judy Hoffman and James Hays served as area chairs.
 
“ML@GT is proud to be an interdisciplinary center with researchers from across campus working collaboratively on projects. We are pleased to see that work recognized and discussed at a conference as esteemed as CVPR,” said Irfan Essa, ML@GT director.
 
CVPR is highly regarded among students, academics, and industry researchers because of its high quality and low cost. Originally scheduled to take place in Seattle, Wash., the conference has been moved entirely online due to the coronavirus pandemic. The conference will take place June 14-19th.
*|END:WEB_VIDEO|*

Artificially intelligent (AI) systems are continuously improving their understanding of physical human activities such as running, jumping, and biking. Yet, much of people’s lives are spent resting in bed.

 

Researchers at the Georgia Institute of Technology and Stanford University have developed an AI-enabled smart mat and synthetic data set to study people at rest. The data set and smart mat are aimed at improving assistive robotics capabilities for people with disabilities, elderly adults, or hospital patients where people often require assistance in bed.

Watch Our Work

Additional Accepted Papers:

12-in-1: Multi-Task Vision and Language Representation Learning by Jiasen Lu*, Vedanuj Goswami*, Marcus Rohrbach, Devi Parikh, Stefan Lee *equal contribution

MMTM: Multimodal Transfer Module for CNN Fusion by Hamid Reza Vaezi Joze*, Amirreza Shaban*, Michael L. Iuzzolino, Kazuhito Koishida *equal contribution

Our Workshops

Visual Question Answering and Dialog Workshop

More Information
Embodied AI Workshop


More Information
UG2 Prize Challenge


More Information
Visual Learning with Limited Labels

More Information

About ML@GT

The Machine Learning Center at Georgia Tech (ML@GT) was founded in 2016 as an interdisciplinary research center (IRC) at the Georgia Institute of Technology. Since then, we have grown to include over 190 affiliated faculty members and 60 Ph.D. students, all publishing at world-renowned conferences. The center aims to research and develop innovative and sustainable technologies using machine learning and artificial intelligence (AI) that serve our community in socially and ethically responsible ways.

Contact

www.ml.gatech.edu | ml@gatech.edu
 

Our Office

Coda at Tech Square
756 West Peachtree Street, 12E
Atlanta, GA 30308

Follow Us

Subscribe

Connect with us to stay up to date on the latest research and news from the ML@GT.

Machine Learning Center