Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment.
Angelos ZavrasDimitrios MichailBegüm DemirIoannis PapoutsisPublished in: CoRR (2024)
Keyphrases
- remote sensing
- language model
- cross modal
- multi modal
- image processing
- language modeling
- probabilistic model
- n gram
- document retrieval
- high resolution
- image analysis
- image fusion
- information retrieval
- computer vision
- retrieval model
- test collection
- query expansion
- image annotation
- multimedia databases
- search engine
- feature vectors
- multiscale