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

@inproceedings{carmo-2024-visualt5, author = {Diedre Carmo and Let\'{i}cia Rittner and Roberto A. Lotufo}, editor = {Guglielmo Faggioli and Nicola Ferro and Petra Galusc\'{a}kov\'{a} and Alba Garcia Seco de Herrera}, title = {{VisualT5: Multitasking Caption and Concept Prediction with Pre-trained ViT, T5 and Customized Spatial Attention in Radiological Images}}, booktitle = {{Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2024), Grenoble, France, 9-12 September, 2024}}, series = {CEUR Workshop Proceedings}, volume = {3740}, pages = {1525--1532}, publisher = {CEUR-WS.org}, year = {2024}, url = {https://ceur-ws.org/Vol-3740/paper-141.pdf} }