Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:image_captioning_model
|
| gptkbp:application |
image captioning
image-text retrieval visual question answering vision-language tasks |
| gptkbp:developedBy |
gptkb:Salesforce_Research
|
| gptkbp:fullName |
gptkb:Bootstrapped_Language_Image_Pretraining
|
| gptkbp:language |
gptkb:Python
|
| gptkbp:license |
gptkb:BSD-3-Clause
|
| gptkbp:notablePublication |
gptkb:BLIP:_Bootstrapped_Language-Image_Pre-training_for_Unified_Vision-Language_Understanding_and_Generation
https://arxiv.org/abs/2201.12086 |
| gptkbp:openSource |
true
|
| gptkbp:relatedTo |
gptkb:ALIGN
gptkb:CLIP gptkb:ViLT |
| gptkbp:releaseYear |
2022
|
| gptkbp:repository |
https://github.com/salesforce/BLIP
|
| gptkbp:uses |
transformer architecture
contrastive learning language modeling |
| gptkbp:bfsParent |
gptkb:CLIP
|
| gptkbp:bfsLayer |
6
|
| https://www.w3.org/2000/01/rdf-schema#label |
BLIP
|