Кодировщик изображения
method
ID: visionencoder
Related Papers
End-to-End Unsupervised Vision-and-Language Pre-training with Referring Expression Matching
AbstractRecently there has been an emerging interest in unsupervised vision-and-language pre-training (VLP) that learns multimodal representations without parallel image-caption data. These pioneering works significantly reduce the cost of VLP on …...