Cross on Cross Attention: Deep Fusion Transformer for Image Captioning

Jing Zhang 0041, Yingshuai Xie, Weichao Ding, Zhe Wang 0002. Cross on Cross Attention: Deep Fusion Transformer for Image Captioning. IEEE Trans. Circuits Syst. Video Techn., 33(8):4257-4268, August 2023. [doi]

Abstract

Abstract is missing.