Aishwarya Agrawal, PhD student at Virginia Tech shares how her team is using NVIDIA GPUs and deep learning to automatically answer a wide range of questions about arbitrary images.
According to Agrawal and her collaborators, the system may one day be used by the visually impaired to help navigate real-world environments, such as informing the user when it is safe to cross the street.
To learn more, try the online demo or read their research paper “VQA: Visual Question Answering”.
Share your GPU-accelerated science with us at http://nvda.ly/Vpjxr and with the world on #ShareYourScience.
Watch more scientists and researchers share how accelerated computing is benefiting their work at http://nvda.ly/X7WpH
Share Your Science: Training a Machine to Answer Questions About Images
May 13, 2016
Discuss (0)
Related resources
- GTC session: Boost your Vision AI Application with Vision Transformer
- GTC session: Scaling Generative AI Features to Millions of Users Thanks to Inference Pipeline Optimizations
- GTC session: Mitigating Spurious Correlations for Medical Image Classification via Natural Language Concepts
- NGC Containers: MATLAB
- Webinar: Isaac Developer Meetup #2 - Build AI-Powered Robots with NVIDIA Isaac Replicator and NVIDIA TAO
- Webinar: Bringing Generative AI to Life with NVIDIA Jetson