Top-down framework for weakly-supervised grounded image captioning.

Chen Cai Suchen Wang Kim-Hui Yap Yi Wang

Published in: Knowl. Based Syst. (2024)

Keyphrases

weakly supervised
image data
input image
object detectors
multiscale
weakly labeled
image segmentation
image regions
image representation
image features
region of interest
image retrieval
object detection
single image
image content
high resolution
domain specific
keypoints
multi class
lighting conditions
object model