|
gptkbp:instance_of
|
gptkb:AI_technology
|
|
gptkbp:application
|
content moderation
image classification
image search
text-to-image generation
|
|
gptkbp:architecture
|
gptkb:Transformers
|
|
gptkbp:available_on
|
gptkb:Git_Hub
|
|
gptkbp:collaborations
|
academic institutions
|
|
gptkbp:community_impact
|
open-source contributions
|
|
gptkbp:competitors
|
gptkb:Microsoft_Azure_Computer_Vision
gptkb:Facebook_AI_Research
gptkb:Google_Vision_AI
|
|
gptkbp:contribution
|
bridging vision and language
|
|
gptkbp:developed_by
|
gptkb:Open_AI
|
|
gptkbp:evaluates
|
top-k accuracy
|
|
gptkbp:field_of_study
|
gptkb:machine_learning
computer vision
natural language processing
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Open AI CLIP
|
|
gptkbp:influenced_by
|
gptkb:BERT
|
|
gptkbp:input_output
|
text and images
|
|
gptkbp:license
|
MIT License
|
|
gptkbp:model
|
400 million parameters
|
|
gptkbp:notable_feature
|
multi-modal capabilities
|
|
gptkbp:notable_for
|
gptkb:virtual_reality
gptkb:vehicles
gptkb:advertising
gptkb:robotics
augmented reality
content creation
educational tools
object detection
art generation
social media analysis
image retrieval
e-commerce applications
semantic segmentation
image captioning
image synthesis
style transfer
visual question answering
healthcare imaging
|
|
gptkbp:performance
|
zero-shot learning
|
|
gptkbp:provides_information_on
|
text-image pairs
|
|
gptkbp:purpose
|
image and text understanding
|
|
gptkbp:related_to
|
gptkb:GPT-3
|
|
gptkbp:release_date
|
January 2021
|
|
gptkbp:similarity_measure
|
cosine similarity
|
|
gptkbp:successor
|
gptkb:Open_AI_DALL-E
|
|
gptkbp:training
|
contrastive learning
|
|
gptkbp:bfsParent
|
gptkb:gymnasium
|
|
gptkbp:bfsLayer
|
4
|