OpenAI CLIP Research

GPTKB entity

Statements (13)
Predicate Object
gptkbp:instanceOf research
gptkbp:aimsTo connect vision and language
gptkbp:conductedBy gptkb:OpenAI
gptkbp:demonstrates zero-shot learning capabilities
gptkbp:enables image classification without task-specific training
gptkbp:focusesOn contrastive language–image pre-training
https://www.w3.org/2000/01/rdf-schema#label OpenAI CLIP Research
gptkbp:influenced multimodal AI research
gptkbp:publishedIn 2021
gptkbp:resultedIn CLIP model
gptkbp:usedDataset 400 million image-text pairs
gptkbp:bfsParent gptkb:OpenAI,_Inc.
gptkbp:bfsLayer 7