no code implementations • 15 Apr 2024 • Chong Peng, Liqiang He, Dan Su
Today, there have been many achievements in learning the association between voice and face.
2 code implementations • 12 Apr 2024 • Dongbo Xi, Zhen Chen, Yuexian Wang, He Cui, Chong Peng, Fuzhen Zhuang, Peng Yan
Besides, by personalized integration of domain features from other domains for each user and the innovation in the training mode, the DFEI framework can yield more accurate conversion identification.
no code implementations • 3 Apr 2024 • Mozhi Zhang, Mianqiu Huang, Rundong Shi, Linsen Guo, Chong Peng, Peng Yan, Yaqian Zhou, Xipeng Qiu
Large language models optimized with techniques like RLHF have achieved good alignment in being helpful and harmless.
no code implementations • 30 Sep 2022 • Xinxing Wu, Chong Peng, Richard Charnigo, Qiang Cheng
Interpreting critical variables involved in complex biological processes related to survival time can help understand prediction from survival models, evaluate treatment efficacy, and develop new therapies for patients.
1 code implementation • 25 Aug 2022 • Xinxing Wu, Chong Peng, Gregory Jicha, Donna Wilcock, Qiang Cheng
Then, we apply it to study oscillation patterns in untimed genome-wide gene expression from 19 human brain regions of controls and AD patients.
no code implementations • 25 Aug 2022 • Xinxing Wu, Chong Peng, Peter T. Nelson, Qiang Cheng
Alzheimer's disease (AD), as a progressive brain disease, affects cognition, memory, and behavior.
no code implementations • 20 Jun 2022 • Chenglizhao Chen, Hengsen Wang, Yuming Fang, Chong Peng
The existing state-of-the-art (SOTA) video salient object detection (VSOD) models have widely followed short-term methodology, which dynamically determines the balance between spatial and temporal saliency fusion by solely considering the current consecutive limited frames.
no code implementations • 22 Apr 2022 • Chong Peng, Yiqun Zhang, Yongyong Chen, Zhao Kang, Chenglizhao Chen, Qiang Cheng
Nonnegative matrix factorization (NMF) has been widely studied in recent years due to its effectiveness in representing nonnegative data with parts-based representations.
no code implementations • 8 Jan 2022 • Chong Peng, Yang Liu, Yongyong Chen, Xinxin Wu, Andrew Cheng, Zhao Kang, Chenglizhao Chen, Qiang Cheng
In this paper, we propose a novel nonconvex approach to robust principal component analysis for HSI denoising, which focuses on simultaneously developing more accurate approximations to both rank and column-wise sparsity for the low-rank and sparse components, respectively.
no code implementations • 25 May 2021 • Yang Liu, Qian Zhang, Yongyong Chen, Qiang Cheng, Chong Peng
It is a challenging task to remove heavy and mixed types of noise from Hyperspectral images (HSIs).
no code implementations • 3 Nov 2020 • Chong Peng, Qian Zhang, Zhao Kang, Chenglizhao Chen, Qiang Cheng
It directly uses 2D data as inputs such that the learning of representations benefits from inherent structures and relationships of the data.
no code implementations • 31 Aug 2020 • Zhao Kang, Chong Peng, Qiang Cheng, Xinwang Liu, Xi Peng, Zenglin Xu, Ling Tian
Furthermore, most existing graph-based methods conduct clustering and semi-supervised classification on the graph learned from the original data matrix, which doesn't have explicit cluster structure, thus they might not achieve the optimal performance.
1 code implementation • 7 Aug 2020 • Chenglizhao Chen, Jia Song, Chong Peng, Guodong Wang, Yuming Fang
Consequently, we can achieve a significant performance improvement by using this new training set to start a new round of network training.
1 code implementation • 7 Aug 2020 • Chenglizhao Chen, Guotao Wang, Chong Peng, Dingwen Zhang, Yuming Fang, Hong Qin
In this way, even though the overall video saliency quality is heavily dependent on its spatial branch, however, the performance of the temporal branch still matter.
1 code implementation • 7 Aug 2020 • Chenglizhao Chen, Jipeng Wei, Chong Peng, Hong Qin
The existing fusion based RGB-D salient object detection methods usually adopt the bi-stream structure to strike the fusion trade-off between RGB and depth (D).
Ranked #16 on RGB-D Salient Object Detection on NJU2K
1 code implementation • 7 Aug 2020 • Chenglizhao Chen, Hongmeng Zhao, Huan Yang, Chong Peng, Teng Yu
The screen content images (SCIs) usually comprise various content types with sharp edges, in which the artifacts or distortions can be well sensed by the vanilla structure similarity measurement in a full reference manner.
no code implementations • 19 May 2020 • Chong Peng, Zhilu Zhang, Zhao Kang, Chenglizhao Chen, Qiang Cheng
In particular, projection matrices are sought under the guidance of building new data representations, such that the spatial information is retained and projections are enhanced by the goal of clustering, which helps construct optimal projection directions.
no code implementations • 3 Dec 2019 • Zhao Kang, Xiao Lu, Yiwei Lu, Chong Peng, Zenglin Xu
Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications.
no code implementations • 9 Jul 2019 • Chong Peng, Zhao Kang, Chenglizhao Chen, Qiang Cheng
Existing nonnegative matrix factorization methods focus on learning global structure of the data to construct basis and coefficient matrices, which ignores the local structure that commonly exists among data.
no code implementations • CVPR 2019 • Chong Peng, Chenglizhao Chen, Zhao Kang, Jianbo Li, Qiang Cheng
This drawback has limited the application of RPCA in solving real world problems.
no code implementations • 16 Apr 2019 • Chong Peng, Qiang Cheng
As a special case we focus on a quadratic model that admits a closed-form analytical solution.
1 code implementation • 12 Nov 2017 • Zhao Kang, Chong Peng, Qiang Cheng, Zenglin Xu
Second, the discrete solution may deviate from the spectral solution since k-means method is well-known as sensitive to the initialization of cluster centers.
no code implementations • CVPR 2017 • Chong Peng, Zhao Kang, Qiang Cheng
Spectral clustering based subspace clustering methods have emerged recently.
no code implementations • 1 May 2017 • Zhao Kang, Chong Peng, Qiang Cheng
Thus the learned similarity matrix is often not suitable, let alone optimal, for the subsequent clustering.
1 code implementation • 27 Sep 2016 • Zhao Kang, Chong Peng, Ming Yang, Qiang Cheng
To alleviate this problem, this paper proposes a simple recommendation algorithm that fully exploits the similarity information among users and items and intrinsic structural information of the user-item matrix.
no code implementations • 27 Sep 2016 • Chong Peng, Zhao Kang, Qiang Chen
Our method can be used as a light-weight, scalable tool for RPCA in the absence of the precise value of the true rank.
no code implementations • 19 Jan 2016 • Zhao Kang, Chong Peng, Qiang Cheng
Top-N recommender systems have been investigated widely both in industry and academia.
1 code implementation • 17 Nov 2015 • Zhao Kang, Chong Peng, Qiang Cheng
This approximation to the matrix rank is tighter than the nuclear norm.
1 code implementation • 30 Oct 2015 • Zhao Kang, Chong Peng, Qiang Cheng
For this nonconvex minimization problem, we develop an effective optimization procedure based on a type of augmented Lagrange multipliers (ALM) method.
1 code implementation • 18 Aug 2015 • Zhao Kang, Chong Peng, Qiang Cheng
However, for many real-world applications, nuclear norm approximation to the rank function can only produce a result far from the optimum.
no code implementations • 3 Jul 2015 • Zhao Kang, Chong Peng, Jie Cheng, Qiang Chen
Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator.