Large web-sourced multimodal datasets have powered a slew of new methods for learning
general-purpose visual representations, advancing the state of the art in computer vision …

Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of
training on large amounts of noisy image-text data, without relying on expensive accurate …

Multimodal semantic understanding often has to deal with uncertainty, which means the
obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our …

Recent Vision-Language Pre-trained (VLP) models based on dual encoder have attracted
extensive attention from academia and industry due to their superior performance on various …

The success of large-scale contrastive vision-language pretraining (CLIP) has benefited
both visual recognition and multimodal content understanding. The concise design brings …

Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily
available supervision of natural language. It improves the performance of downstream vision …

Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn
the correct corresponding information across different modalities. For this purpose, inspired …

Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced
research and applications in computer vision, fueling modern recognition systems and …

Recent pretrained vision-language models have achieved impressive performance on cross-
modal retrieval tasks in English. Their success, however, heavily depends on the availability …

Scaling up contrastive language-image pretraining (CLIP) is critical for empowering both
vision and multimodal models. We present EVA-CLIP-18B, the largest and most powerful …