DICKT - Deep Learning-Based Image Captioning using Keras and TensorFlow.

Phung Thao Vi Satyam Mishra Le Anh Ngoc Sundaram Mishra Vu Minh Phuc

Published in: RICE (2023)

Keyphrases

deep learning
input image
image segmentation
image content
image representation
image features
multiscale
test images
image classification
single image
unsupervised learning
bounding box
image retrieval
high resolution
object recognition
model selection
segmentation method
similarity measure
lighting conditions
weakly supervised
machine learning