Lluís Gómez, Ali Furkan Biten, Rubèn Pérez Tito, Andrés Mafla, Marçal Rusiñol, Ernest Valveny, Dimosthenis Karatzas. Multimodal grid features and cell pointers for scene text visual question answering. Pattern Recognition Letters, 150:242-249, 2021. [doi]
Abstract is missing.