no code implementations • 27 Feb 2024 • Yang Liu, Xiaomin Yu, Gongyu Zhang, Christos Bergeles, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin
We train models for these tasks in a zero-shot cross-modal transfer setting, a domain where the previous state-of-the-art method relied on the fixed scale noise injection, often compromising the semantic content of the original modality embedding.
no code implementations • 9 Apr 2023 • Ye Jiang, Xiaomin Yu, Yimin Wang, Xiaoman Xu, Xingyi Song, Diana Maynard
First, we incorporate prompt learning into multimodal fake news detection.
no code implementations • 1 Jan 2021 • Panfeng Chen, Yisong Wang, Renyan Feng, Xiaomin Yu, Quan Yu
The insight of this work enlightens the notion of dense feature model design for KGC which is a new alternative to Deep Neural networks (DNN) in this task or even a better choice.