RecViT: Enhancing Vision Transformer with Top-Down Information Flow

Stefan Pócos, Iveta Becková, Igor Farkas. RecViT: Enhancing Vision Transformer with Top-Down Information Flow. In Petia Radeva, Antonino Furnari, Kadi Bouatouch, A. Augusto de Sousa, editors, Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2024, Volume 3: VISAPP, Rome, Italy, February 27-29, 2024. pages 749-756, SCITEPRESS, 2024. [doi]

Abstract

Abstract is missing.