OECA-Net: A co-attention network for visual question answering based on OCR scene text feature enhancement

Feng Yan, Wushouer Silamu, Yachuang Chai, Yanbing Li. OECA-Net: A co-attention network for visual question answering based on OCR scene text feature enhancement. Multimedia Tools Appl., 83(3):7085-7096, January 2024. [doi]

Abstract

Abstract is missing.