1 code implementation • 21 Nov 2023 • Xiangjian Jiang, Yanyi Pu
Dynamic Graph Neural Networks (DGNNs) have emerged as the predominant approach for processing dynamic graph-structured data.
no code implementations • 21 Jun 2023 • Xiangjian Jiang, Andrei Margeloiu, Nikola Simidjievski, Mateja Jamnik
In this paper, we propose ProtoGate, a prototype-based neural model that introduces an inductive bias by attending to both homogeneity and heterogeneity across samples.
no code implementations • CVPR 2023 • Bonan Li, Yinhan Hu, Xuecheng Nie, Congying Han, Xiangjian Jiang, Tiande Guo, Luoqi Liu
Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.
no code implementations • 4 Oct 2022 • Xiangjian Jiang, Xuecheng Nie, Zitian Wang, Luoqi Liu, Si Liu
Existing methods for human mesh recovery mainly focus on single-view frameworks, but they often fail to produce accurate results due to the ill-posed setup.
no code implementations • 4 Aug 2022 • Bonan Li, Yinhan Hu, Xuecheng Nie, Congying Han, Xiangjian Jiang, Tiande Guo, Luoqi Liu
Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.
1 code implementation • ICCV 2021 • Renshuai Tao, Yanlu Wei, Xiangjian Jiang, Hainan Li, Haotong Qin, Jiakai Wang, Yuqing Ma, Libo Zhang, Xianglong Liu
In this work, we first present a High-quality X-ray (HiXray) security inspection image dataset, which contains 102, 928 common prohibited items of 8 categories.