Abstract: The current image-text cross-modal retrieval faces challenges due to the heterogeneous nature of different modalities. This paper proposes an improved model based on multi-scale modal ...

A YOLOv8-based detector for manga speech bubbles and text boxes. This project uses computer vision and deep learning to automatically detect and classify different types of text elements in manga ...

Abstract: Detecting text within natural environments presents a considerable computer vision challenge due to the wide variations in text scale, orientation, and shape. Many current methods are ...

January 12 - Everywhere you look, "food systems transformation" is the new buzzword. From U.N. conferences to corporate boardrooms, the term is gaining momentum. But behind the headlines, real change ...