1.ETV-Attack: Efficient text-driven visual-variable adversarial attacks on visual question answering with pre-trained language models

Xu, QX, Zhou, L, Zho     More...

Xu, QX, Zhou, L, Zhong, X, Zhang, FF, Tian, JY, Yu, XH, Huang, RB     Less

PATTERN RECOGNITION[0031-3203], Published 2026, Volume 176,

收錄情况： WOS SCOPUS

WOS核心合集引用: 0  2024影響因子:  7.6 

2.Refined generation-based framework for consistent and reliable visual question answering

Xu, QX, Zhou, L, Zho     More...

Xu, QX, Zhou, L, Zhong, X, Zhang, FF, Tian, JY, Yu, XH, Huang, RB     Less

PATTERN RECOGNITION[0031-3203], Published 2026, Volume 178,

收錄情况： WOS SCOPUS

WOS核心合集引用: 0  2024影響因子:  7.6