Image caption generation using a dual attention mechanism.
Roshni PadateAmit JainMukesh KallaArvind SharmaPublished in: Eng. Appl. Artif. Intell. (2023)
Keyphrases
- software engineering
- attention mechanism
- image data
- input image
- image content
- image retrieval
- image segmentation
- image features
- low level
- image classification
- image regions
- multiscale
- image representation
- visual attention
- bounding box
- saliency map
- image structure
- similarity metric
- caption text
- high resolution
- keypoints
- human computer interaction
- visual features
- multi modal
- higher order