Co-reference via Pointing and Haptics in Multi-Modal Dialogues.

Lin Chen Barbara Di Eugenio

Published in: HLT-NAACL (2012)

Keyphrases

multi modal
multi modality
audio visual
image processing
high dimensional
computer vision
video search
cross modal
uni modal
machine learning
feature extraction
medical images
image representation
humanoid robot
semantic concepts
multiple modalities