3 datasets found

FS-COCO: A large-scale scene sketch dataset with fine-grained alignment among sketch, text, and photo.

SketchyCOCO: A large-scale scene sketch dataset with fine-grained alignment among sketch, text, and photo.

Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture...