Login / Signup
HM-Transformer: Hierarchical Multi-modal Transformer for Long Document Image Understanding.
Xi Deng
Shasha Li
Jie Yu
Jun Ma
Published in:
APWeb/WAIM (4) (2023)
Keyphrases
</>
multi modal
document image understanding
fault diagnosis
fuzzy logic
multi modality
cross modal
power transformers
high dimensional
audio visual
video search
document images
image annotation
semantic concepts
e learning
video sequences
partial discharge