Crossmark

VTFCGNet: a novel cross-modal reasoning network integrating Fourier self-attention and graph attention for visual text question answering

Published Online: 2026-02-03

Published Print: 2026-02

Authors

Huo, Yujie https://orcid.org/0009-0001-3123-2803
Chan, Weng Howe

Yu, Song

Gao, Hongyu
Funding

Funding for this research was provided by:

Universiti Teknologi Malaysia
License Information

Text and Data Mining valid from 2026-02-01

Version of Record valid from 2026-02-03
More Information

Article History

Received: 25 May 2025

Accepted: 1 December 2025

First Online: 3 February 2026

Declarations

:

: The authors declare no Conflict of interest.

Document is current