AAFormer: A Multi-Modal Transformer Network for Aerial Agricultural Images.

Yao Shen Lei Wang Yue Jin

Published in: CVPR Workshops (2022)

Keyphrases

multi modal
image annotation
fusing multiple
image data
multiple modalities
aerial images
image database
image collections
audio visual
satellite images
image classification
image analysis
cross modal
object recognition
image retrieval
edge detection
single modality
high dimensional
input image
video search
automatic image annotation
multi modality
auto annotation
face recognition
image regions
mutual information
image features