Back to researchers
Junnan Li
Bootstrapped vision-language pretraining (BLIP)
Co-authored BLIP: a high-impact recipe for unified vision-language understanding and generation.
Highlights
MultimodalVision-languagePretraining
Focus: Bootstrapped vision-language pretraining (BLIP)
Why it matters: Co-authored BLIP: a high-impact recipe for unified vision-language understanding and generation.
Research Areas
MultimodalVision-languagePretraining