Vol-3739⫷ Vol-3740 ⫸Vol-3741
urn:nbn:de:0074-3740-0


Vol-3740/paper-140⫷Vol-3740/paper-141⫸Vol-3740/paper-142

VisualT5: Multitasking Caption and Concept Prediction with Pre-trained ViT, T5 and Customized Spatial Attention in Radiological Images