13 Result(s)
within
Kewei Yang
Computer Science
-
Chapter and Conference Paper
ARE-CAM: An Interpretable Approach to Quantitatively Evaluating the Adversarial Robustness of Deep Models Based on CAM
Evaluating the adversarial robustness of deep models is critical for training more robust models. However, few methods are both interpretable and quantifiable. Interpretable evaluation methods cannot quantify ...
-
Article
MICAR: nonlinear association rule mining based on maximal information coefficient
Association rule mining (ARM) is an important research issue in data mining and knowledge discovery. Existing ARM methods cannot discover nonlinear association rules, despite nonlinearity being common and sign...
-
Chapter and Conference Paper
A Novel Investment Strategy for Mixed Asset Allocation Based on Entropy-Based Time Series Prediction
In recent years, the combinational investment of gold and Bitcoin has become a hot spot, and it is expected to achieve a balance between risk aversion and maximum income. Some existing methods lack of timeline...
-
Chapter and Conference Paper
\(\text {Face2Face}^\rho \) : Real-Time High-Resolution One-Shot Face Reenactment
Existing one-shot face reenactment methods either present obvious artifacts in large pose transformations, or cannot well-preserve the identity information in the source images, or fail to meet the requirement...
-
Article
Optimization framework and applications of training multi-state influence nets
Influence nets (INs) are proposed on the basis of causal logic for the purpose of depicting causal relationship strengths in complex systems. However, it is difficult to accurately determine the causal strengt...
-
Article
Similarity measures for time series data classification using grid representation and matrix distance
Two similarity measures are proposed that can successfully capture both the numerical and point distribution characteristics of time series. More specifically, a novel grid representation for time series is fi...
-
Article
Paint with stitches: a style definition and image-based rendering method for random-needle embroidery
Random-needle Embroidery is a graceful Chinese art designated as Intangible Cultural Heritage, which “draws” beautiful images with thousands of free-form threads. In this paper, we explore techniques for autom...
-
Chapter and Conference Paper
Image Stylization for Thread Art via Color Quantization and Sparse Modeling
We present an image stylization method to simulate a graceful Chinese art—Random-needle Embroidery designated as Intangible Cultural Heritage. We first develop an effective way to simulate a single thread, and...
-
Chapter and Conference Paper
Stitch-Based Image Stylization for Thread Art Using Sparse Modeling
Random-needle Embroidery (RNE) is a graceful Chinese Embroidery art enrolled in the World Intangible Heritage. In this paper, we propose a rendering method to translate a reference image into an art image with...
-
Article
A Bayesian approach for sleep and wake classification based on dynamic time war** method
Sleep plays a significant role in human’ smental and physical health. Recently, the associations between lack of sleep and weight gain, development of cancer and many other health problems have been recognized...
-
Chapter and Conference Paper
Online User Modeling for Interactive Streaming Image Classification
Regarding of the explosive growth of personal images, this paper proposes an online user modeling method for the categorization of the streaming images. In the proposed framework, user interaction is brought i...
-
Chapter and Conference Paper
Unsupervised Multiple Object Cosegmentation via Ensemble MIML Learning
Multiple foreground cosegmentation (MFC) has being a new research topic recently in computer vision. This paper proposes a framework of unsupervised multiple object cosegmentation, which is composed of three c...
-
Chapter and Conference Paper
Progressive Image Segmentation Using Online Learning
This article proposed a progressive image segmentation, which allow users to segment images according to their preferences without any boring pre-labeling or training stages. We use an online learning method t...
