1 code implementation • 25 Mar 2024 • Qianru Zhang, Lianghao Xia, Xuheng Cai, SiuMing Yiu, Chao Huang, Christian S. Jensen
To address these challenges, we propose a principled framework called GraphAug.
1 code implementation • 19 Jun 2023 • Qianru Zhang, Chao Huang, Lianghao Xia, Zheng Wang, SiuMing Yiu, Ruihua Han
In addition, we introduce a cross-view contrastive learning paradigm to model the inter-dependencies across view-specific region representations and preserve underlying relation heterogeneity.
1 code implementation • 6 May 2023 • Qianru Zhang, Chao Huang, Lianghao Xia, Zheng Wang, Zhonghang Li, SiuMing Yiu
In this paper, we tackle the above challenges by exploring the Automated Spatio-Temporal graph contrastive learning paradigm (AutoST) over the heterogeneous region graph generated from multi-view data sources.
no code implementations • 25 Sep 2019 • Xin Wang, SiuMing Yiu
In this paper, we explore the correlation between flows' likelihood and image semantics.
no code implementations • 25 Sep 2019 • Xin Wang, SiuMing Yiu
The supervised probabilistic constraints are equivalent to a generative classifier on high-level data representations, where class conditional log-likelihoods of samples can be evaluated.