no code implementations • 25 Sep 2021 • Yajie Sun, Miaohua Zhang, Xiaohan Yu, Yi Liao, Yongsheng Gao
Motivated by these issues, this paper proposes a novel compositional feature embedding and similarity metric (CECS).
no code implementations • 16 Sep 2021 • Zicheng Pan, Xiaohan Yu, Miaohua Zhang, Yongsheng Gao
The advantage of the proposed method is that the feature detection and extraction model only requires a small amount of target region samples with bounding boxes for training, then it can automatically locate the target area for a large number of images in the dataset at a high detection accuracy.
no code implementations • 10 May 2020 • Miaohua Zhang, Yongsheng Gao
Two-dimensional singular decomposition (2DSVD) has been widely used for image processing tasks, such as image reconstruction, classification, and clustering.
no code implementations • 10 May 2020 • Miaohua Zhang, Yongsheng Gao, Changming Sun, Michael Blumenstein
Current orthogonal matching pursuit (OMP) algorithms calculate the correlation between two vectors using the inner product operation and minimize the mean square error, which are both suboptimal when there are non-Gaussian noises or outliers in the observation data.
no code implementations • 10 May 2020 • Miaohua Zhang, Yongsheng Gao, Jun Zhou
For the structured error caused by occlusions or disguises, we propose a GC function based rank approximation to measure the rank of error matrices.
no code implementations • 10 May 2020 • Miaohua Zhang, Yongsheng Gao, Changming Sun, Michael Blumenstein
Traditional tensor decomposition methods, e. g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers.