Grounding Symbols in Multi-Modal Instructions.

Yordan Hristov Svetlin Penkov Alex Lascarides Subramanian Ramamoorthy

Published in: RoboNLP@ACL (2017)

Keyphrases

multi modal
audio visual
cross modal
multi modality
high dimensional
video search
multimedia
object recognition
image annotation
humanoid robot
semantic concepts
single modality
fusing multiple