Image Data

Image Classification and Recognition – (object classification, scene recognition)
Object Detection and Segmentation – (bounding boxes, instance/semantic segmentation)
Image Captioning and Generation – (captioning, image-to-text generation)
Vision-Language Tasks – (Visual Question Answering (VQA), referring expressions)
Image-to-Image Tasks – (style transfer, super-resolution, restoration)
Document Understanding – (OCR, layout analysis, form understanding)