FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions.
Noam RotsteinDavid BensaïdShaked BrodyRoy GanzRon KimmelPublished in: WACV (2024)
Keyphrases
- language model
- fused image
- image fusion
- data fusion
- language modeling
- fusion method
- source images
- multiple images
- human vision
- wavelet transform
- probabilistic model
- document retrieval
- n gram
- information retrieval
- multiresolution
- language modelling
- retrieval model
- discrete wavelet transform
- multi sensor
- multispectral images
- visual features
- statistical language models
- test collection
- information fusion
- remote sensing
- query expansion
- video content
- multiscale
- perceptual quality
- spatial resolution
- feature extraction
- language models for information retrieval
- human visual system
- image registration
- image processing