Visual Question Answering Model Based on Spatial Relation and Frequency Feature

As an important task in multimodal data processing, Visual Question Answering(VQA) needs to associate and represent information from different modalities.However, existing VQA models can not effectively distinguish similar target objects and can not accurately express the spatial relationship betwee...

Ausführliche Beschreibung

Bibliografische Detailangaben

1. Verfasser:	FU Pengcheng, YANG Guan, LIU Xiaoming, LIU Yang, ZHANG Ziming, CHENG Xi
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Editorial Office of Computer Engineering 2022-09-01
Schriftenreihe:	Jisuanji gongcheng
Schlagworte:	discrete cosine transform(dct)|fine-grained identification|relation network(rn)|attention mechanism|feature fusion
Online-Zugang:	https://www.ecice06.com/fileup/1000-3428/PDF/20220912.pdf
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!