no code implementations • CVPR 2022 • Marco Cipriano, Stefano Allegretti, Federico Bolelli, Federico Pollastri, Costantino Grana
By combining a segmentation model trained on the 3D annotated data and label propagation, we significantly improve the state of the art in the Inferior Alveolar Nerve segmentation.
1 code implementation • 4 Mar 2019 • Stefano Pini, Marcella Cornia, Federico Bolelli, Lorenzo Baraldi, Rita Cucchiara
Current movie captioning architectures are not capable of mentioning characters with their proper name, replacing them with a generic "someone" tag.