DSGEM: Dual scene graph enhancement module‐based visual question answering

Abstract Visual Question Answering (VQA) aims to appropriately answer a text question by understanding the image content. Attention‐based VQA models mine the implicit relationships between objects according to the feature similarity, which neglects the explicit relationships between objects, for exa...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Boyue Wang, Yujian Ma, Xiaoyan Li, Heng Liu, Yongli Hu, Baocai Yin
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	Wiley 2023-09-01
סדרה:	IET Computer Vision
נושאים:	image representation question answering (information retrieval)
גישה מקוונת:	https://doi.org/10.1049/cvi2.12186
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!