MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding.

Geondo Park Chihye Han Wonjun Yoon Daeshik Kim

Published in: CoRR (2020)

Keyphrases

selective attention
visual field
real time
visual features
complex networks
network model
neural network
low level
semantic search
digital images
semantic web
visual information
low level features
communication networks
semantic content