Violet: A Vision-Language Model for Arabic Image Captioning with Gemini Decoder.
Abdelrahman MohamedFakhraddin AlwajihEl Moatez Billah NagoudiAlcides Alcoba InciarteMuhammad Abdul-MageedPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- image features
- n gram
- image segmentation
- information retrieval
- query expansion
- image content
- speech recognition
- image classification
- image representation
- query terms
- image retrieval
- language modelling
- context sensitive
- ad hoc information retrieval
- test collection
- probabilistic model
- retrieval model
- retrieval effectiveness
- standard deviation
- document retrieval
- relevance model
- translation model
- bayesian networks
- statistical language models
- feature selection