Learning to Reason on Tree Structures for Knowledge-Based Visual Question Answering

Learning to Reason on Tree Structures for Knowledge-Based Visual Question Answering

Collaborative reasoning for knowledge-based visual question answering is challenging but vital and efficient in understanding the features of the images and questions. While previous methods jointly fuse all kinds of features by attention mechanism or use handcrafted rules to generate a layout for p...

Full description

Bibliographic Details
Main Authors: Qifeng Li, Xinyi Tang, Yi Jian
Format: Article
Language:English
Published: MDPI AG 2022-02-01
Series:Sensors
Subjects:
tree structure
knowledge base
compositional reasoning
neural module network
attention mechanism
Online Access:https://www.mdpi.com/1424-8220/22/4/1575

Internet

https://www.mdpi.com/1424-8220/22/4/1575

Similar Items