Multi-Modal Image Captioning for the Visually Impaired.

Hiba Ahsan Daivat Bhatt Kaivankumar Shah Nikita Bhalla

Published in: NAACL-HLT (Student Research Workshop) (2021)

Keyphrases

multi modal
input image
uni modal
image data
image features
multiscale
audio visual
image representation
image retrieval
image analysis
auto annotation
cross modal
multi modality
image regions
segmentation method
image classification
image annotation
segmentation algorithm
fusing multiple
image collections
image content
image segmentation
edge detection
low level
vector field
single modality
high resolution
similarity measure