Login / Signup
RobotVQA - A Scene-Graph- and Deep-Learning-based Visual Question Answering System for Robot Manipulation.
Franklin Kenghagho Kenfack
Feroz Ahmed Siddiky
Ferenc Balint-Benczedi
Michael Beetz
Published in:
IROS (2020)
Keyphrases
</>
deep learning
unsupervised learning
machine learning
unsupervised feature learning
video sequences
mental models
natural language
single image
graph structure
multiple images
image sequences
visual features
question answering
spatial relations
object recognition
vision system
data mining