A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism.
Rashid KhanM. Shujah IslamKhadija KanwalMansoor IqbalMd. Imran HossainZhongfu YePublished in: CoRR (2022)
Keyphrases
- attention mechanism
- input image
- image segmentation
- high resolution
- multiscale
- image data
- image features
- image classification
- visual attention model
- image content
- computer vision
- image representation
- visual attention
- biologically inspired
- multi modal
- software engineering
- saliency map
- bounding box
- active learning
- image sequences
- caption text