Search Results

Group sparse residual constraint model with nonlocal priors (GSRC-NLP) has made great success in image restoration and produce state-of-the-art performance, realized through reducing the group sparsity residual. In the GSRC-NLP model, $L_1$ norm is ...${}_{\mathrm{}}$

In the field of image restoration, non-convex penalties and non-local self-similarity (NSS) prior have been found to enhance image edges and textures. However, NSS-based methods often overlook the inherent variations within patch groups by ...

• Utilizing the weighted log-sum function as the regularization term.
• Incorporating the non-local self-similarity prior into the weight design.
• NSS prior driven adaptive adjustment of the convexity of the objective function.

Robustness to malicious attacks is of paramount importance for distributed learning. Existing works often consider the classical Byzantine attacks model, which assumes that some workers can send arbitrarily malicious messages to the server and disturb ...

This paper studies Byzantine-robust stochastic optimization over a decentralized network, where every agent periodically communicates with its neighbors to exchange local models, and then updates its own local model with one or a mini-batch of ...

• Byzantine-robust decentralized stochastic optimization aid by variance reduction.
• Optimal learning errors for TV-norm penalized decentralized stochastic optimization.
• Extensive numerical experiments to demonstrate effectiveness of ...

We present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline training time, are prone to visual ...

• This paper aims to solve a distributed learning problem under Byzantine attacks.

This paper aims to solve a distributed learning problem under Byzantine attacks. In the underlying distributed master-worker architecture, there exist a number of unknown but malicious workers that can send arbitrary messages to the ...

Continuous tracking of patient's health data through electronic health records (EHRs) has created an opportunity to predict healthcare policies' long-term impacts. Despite the advances in EHRs, data may be missing or sparsely collected. In this article, ...

High-dimensional data is generated in a wide range of scientific, social and economic life. Identifying and analyzing these high-dimensional data efficiently can improve the scientificity of decisions. Visualization can transform abstract data or large ...

We propose a gesture-based 3D modeling system, which allows the user to create and sculpt a 3D model with hand-gestures. The goal of our system is to provide a more intuitive 3D user interface than the traditional 2D ones such as mouse or touch pad. ...