There has been a recent surge of interest in cross-modal pre-training. However, existed
approaches pre-train a one-stream model to learn joint vision-language representation …

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed
rapid progress for learning cross-modal representations. Existing pre-training methods …

While large scale pre-training has achieved great achievements in bridging the gap
between vision and language, it still faces several challenges. First, the cost for pre-training …

Vision-and-language pre-training has achieved impressive success in learning multimodal
representations between vision and language. To generalize this success to non-English …

Abstract Vision-and-Language (V+ L) pre-training models have achieved tremendous
success in recent years on various multi-modal benchmarks. However, the majority of …

Large-scale vision-language pre-training has shown promising advances on various
downstream tasks and achieved significant performance in multi-modal understanding and …

Vision-language representation learning largely benefits from image-text alignment through
contrastive losses (eg, InfoNCE loss). The success of this alignment strategy is attributed to …

Large-scale single-stream pre-training has shown dramatic performance in image-text
retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers …

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 …

Much of vision-and-language research focuses on a small but diverse set of independent
tasks and supporting datasets often studied in isolation; however, the visually-grounded …