MMCosine: Multi-Modal Cosine Loss Towards Balanced Audio-Visual Fine-Grained Learning.

Ruize Xu Ruoxuan Feng Shi-Xiong Zhang Di Hu

Published in: CoRR (2023)

Keyphrases

multi modal
audio visual
fine grained
coarse grained
multi modality
access control
high dimensional
databases
video search
data lineage
uni modal