5 janv. 2021 - OpenAI's CLIP Image-Text Model
Description:
OpenAI introduces CLIP (Contrastive Language-Image Pretraining), a model that learns visual concepts from textual descriptions, enabling cross-modal understanding and advancing AI capabilities in vision and language.Ajouté au bande de temps:
Date:
5 janv. 2021
Maintenaint
~ Il y a 4 ans et 9 mois