Contrastive Multimodal Fusion with TupleInfoNCE.

Yunze Liu Qingnan Fan Shanghang Zhang Hao Dong Thomas A. Funkhouser Li Yi

Published in: CoRR (2021)

Keyphrases

multimodal fusion
high robustness
audio visual
relevance feedback
multimodal interfaces
gait recognition
multi modal
artificial intelligence
active learning
machine learning
human computer interaction
image sequences
semantic information
visual information