IM2City: image geo-localization via multi-modal learning.

Meiliu Wu Qunying Huang

Published in: GeoAI@SIGSPATIAL (2022)

Keyphrases

multi modal
auto annotation
image analysis
image data
image segmentation
segmentation method
multi modality
input image
image content
image collections
image classification
audio visual
image retrieval
multiscale
humanoid robot
watershed segmentation
image representation
edge detection
mean shift
image regions
image annotation
computer vision
low level
visual recognition
high resolution
object recognition
fusing multiple
uni modal
multimedia