RESEARCH AREA
Vision-Language Models
Models trained on paired image-text data like CLIP and GPT-4V.
1500+ papers1 researchers
Key Papers
Learning Transferable Visual Models from Natural Language (CLIP)
ICML202125,000 citations
RESEARCH AREA
Models trained on paired image-text data like CLIP and GPT-4V.
Learning Transferable Visual Models from Natural Language (CLIP)