1 code implementation • 24 Oct 2023 • Xin Xing, Zhexiao Xiong, Abby Stylianou, Srikumar Sastry, Liyu Gong, Nathan Jacobs
In general multi-label learning, a model learns to predict multiple labels or categories for a single input image.
no code implementations • CVPR 2019 • Liyu Gong, Qiang Cheng
The proposed framework can consolidate current graph neural network models, e. g., GCN and GAT.
no code implementations • 28 Jan 2019 • Liyu Gong, Qiang Cheng
Moreover, we derive an intrinsic loss for UTDAT Lie group which can be calculated as l-2 loss in the tangent space.
no code implementations • 7 Sep 2018 • Liyu Gong, Qiang Cheng
The proposed framework can consolidate current graph neural network models; e. g. graph convolutional networks (GCN) and graph attention networks (GAT).
no code implementations • 3 Apr 2013 • Liyu Gong, Meng Chen, Chunlong Hu
Then we vectorize the GMMs based on two facts: (1) components of image-specific GMMs are closely grouped together around their corresponding component of the UBM due to the characteristic of the UBM adaption procedure; (2) Gaussian \emph{pdf}s form a Lie group, which is a differentiable manifold rather than a vector space.