Mgsc: multimodal generation and self-supervised contrast learning for mitigating language bias in visual question answering
Multimedia Systems · 2026-08 · 32 (7)
DOI: 10.1007/s00530-026-02537-x ↗Kurz gefasst
Fachartikel in der Zeitschrift Multimedia Systems, online erschienen am 27.07.2026. Verfasst von Xinyu Jiang und 7 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Gefördert von: Humanities and Social Sciences Youth Foundation, Ministry of Education,China, “20 New Universities”Project of Jinan City.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Humanities and Social Sciences Youth Foundation, Ministry of Education,China
- “20 New Universities”Project of Jinan City
Zitieren
APA
Jiang, X., Zhu, Z., Lu, Q., Qi, J., Sun, Y., Zhao, L., Zhao, D., & Wang, X. (2026). Mgsc: multimodal generation and self-supervised contrast learning for mitigating language bias in visual question answering. Multimedia Systems, 32(7). https://doi.org/10.1007/s00530-026-02537-x
Vancouver
Jiang X, Zhu Z, Lu Q, Qi J, Sun Y, Zhao L, et al. Mgsc: multimodal generation and self-supervised contrast learning for mitigating language bias in visual question answering. Multimedia Systems. 2026;32(7). doi:10.1007/s00530-026-02537-x
BibTeX
@article{Jiang2026,
author = {Jiang, Xinyu and Zhu, Zhenfang and Lu, Qiang and Qi, Jiangtao and Sun, Yanhan and Zhao, Liang and Zhao, Dawei and Wang, Xuejuan},
title = {Mgsc: multimodal generation and self-supervised contrast learning for mitigating language bias in visual question answering},
journal = {Multimedia Systems},
year = {2026},
volume = {32},
number = {7},
doi = {10.1007/s00530-026-02537-x}
}
EUVIMED