1 code implementation • 5 Dec 2023 • Shuangquan Feng, Junhua Ma, Virginia R. de Sa
Firstly, we can automatically annotate user preferences between image pairs with substantial difference in these AU responses with an accuracy significantly outperforming state-of-the-art scoring models.
no code implementations • 11 Mar 2022 • Junhua Ma, Jiajun Li, Xueming Li, Xu Li
To address these problems, we propose a model called PathSAGE, which can learn high-order topological information and improve the model's performance by expanding the receptive field.
no code implementations • 11 Mar 2022 • Junhua Ma, Jiajun Li, Yuxuan Liu, Shangbo Zhou, Xue Li
Recent progress on parse tree encoder for sentence representation learning is notable.