Automatic Audio Captioning using Attention weighted Event based Embeddings.

Swapnil Bhosale Rupayan Chakraborty Sunil Kumar Kopparapu

Published in: CoRR (2022)

Keyphrases

multimedia
fully automatic
visual attention
weighted sum
focus of attention
real time
face recognition
dimensionality reduction
high dimensional data
semi automatic
event detection
manifold learning
cross modal
video indexing and retrieval