Bridging the visual gap in VLN via semantically richer instructions.

Joaquín Ossandón Benjamín Earle Álvaro Soto

Published in: CoRR (2022)

Keyphrases

visual information
visual features
low level
semantically relevant
visual perception
human vision
semantic gap
medical images
visual appearance
semantic content
eye movements
data sets
mobile robot
computer vision
artificial intelligence
information retrieval
machine learning
real world
databases