.png){kind=icon}
Return
Knowledge-based visual question classification using quaternion hypergraph consistent network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2025.104591.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A quaternion hypergraph consistent network is proposed to integrate three fine-grained properties. • Independence loss is designed to make textual features and visual features maintain modality-specific and distinct from each other. • Knowledge consistency loss is proposed to constrain the textual-knowledge features and visual-knowledge features. • Experimental results demonstrate that our method achieves better performance comparable to existing mainstream approaches.
Journal
I
IF:
6.9
Papers:
562
Citations:
0
Organization
View more organizations
Cited Papers
Explainable Knowledge reasoning via thought chains for knowledge-based visual question answering
PREAI
ShareSaveShareSave
Hypergraph based multi-task feature selection for multimodal classification of Alzheimer's disease
PREAI
ShareSaveUnbiased VQA via modal information interaction and question transformation.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveShareSave View more