An alternative EQA paradigm and informative benchmark + models (BMVC 2019, ViGIL 2019 spotlight)
-
Updated
Jun 22, 2022 - Python
An alternative EQA paradigm and informative benchmark + models (BMVC 2019, ViGIL 2019 spotlight)
This is the implementation of the 'VSGRU' model mentioned in our paper 'Automated Radiology Report Generation using Conditioned Transformers'.
INSIDE: Steering Spatial Attention with Non-Imaging Information in CNNs
Transformer architecture conditioned by metadata
Kitten Reinforcement add-on for Anki
Our "hello, world!" -- a simple clam-like agent that can learn when to open to particular stimuli
Add a description, image, and links to the conditioning topic page so that developers can more easily learn about it.
To associate your repository with the conditioning topic, visit your repo's landing page and select "manage topics."