Login / Signup
Towards Captioning an Image Collection from a Combined Scene Graph Representation Approach.
Itthisak Phueaksri
Marc A. Kastner
Yasutomo Kawanishi
Takahiro Komamizu
Ichiro Ide
Published in:
MMM (1) (2023)
Keyphrases
</>
graph representation
image collections
image set
graph model
image content
dictionary learning for sparse
photo collections
image retrieval
visual features
video sequences
image browsing
visual concepts
image annotation
visual information
image regions
machine learning
input image
knn
image data
computer vision