BLIP: Bootstrapped Language-Image Pre-training for Unified Vision-Language Understanding and Generation

GPTKB entity

Statements (34)
Predicate Object
gptkbp:instanceOf gptkb:model
vision-language model
gptkbp:architecture gptkb:transformation
gptkb:Vision_Transformer
gptkbp:author gptkb:Silvio_Savarese
Dongxu Li
Junnan Li
Steven Hoi
gptkbp:designedFor unified vision-language understanding
vision-language generation
gptkbp:field gptkb:artificial_intelligence
computer vision
natural language processing
https://www.w3.org/2000/01/rdf-schema#label BLIP: Bootstrapped Language-Image Pre-training for Unified Vision-Language Understanding and Generation
gptkbp:input gptkb:illustrator
gptkb:text
gptkbp:memiliki_tugas image captioning
image-text retrieval
visual question answering
gptkbp:notableFor unified vision-language pre-training
state-of-the-art performance on vision-language tasks
gptkbp:organization gptkb:Salesforce_Research
gptkbp:output gptkb:text
visual question answering
image caption
gptkbp:pre-trainingMethod bootstrapped pre-training
gptkbp:publicationYear 2022
gptkbp:publishedIn gptkb:arXiv
gptkbp:relatedTo gptkb:ALIGN
gptkb:CLIP
gptkb:ViLT
gptkbp:repository https://github.com/salesforce/BLIP
gptkbp:bfsParent gptkb:BLIP
gptkbp:bfsLayer 7