Joint feature representation and classification via adaptive graph semi-supervised nonnegative matrix factorization

Yi, Yugen; Chen, Yuqi; Wang, Jianzhong; Lei, Gang; Dai, Jiangyan; Zhang, Huihui

doi:10.1016/j.image.2020.115984

Cited by 15 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Measurement Model. Smart PLS 3.0 software was used for the empirical study to check for reliability and validity [53][54][55]. To assess the reliability of the constructs, we checked Cronbach's alpha, the composite reliability (CR), and the average variance extracted (AVE) (Table 4).…”

Section: Discussionmentioning

confidence: 99%

Mobile Users’ Online Luxury Consumption in China: The Moderating Role of Face Consciousness

Xin

2021

Mobile Information Systems

View full text Add to dashboard Cite

Attracting more consumers through mobile online platforms has become the most important thing for luxury brands. However, few studies have explored how cultural context, as exemplified by face consciousness and source credibility, influences the online luxury consumption and promotion of mobile users. To fill that research gap, this study constructed a research model of Chinese consumers to examine the effect of source credibility on the online luxury purchase and recommendation intentions of mobile consumers, and the moderating effects of face consciousness were examined. A structural equation model was also employed in our study. Furthermore, a field survey with 168 mobile online shopping customers was conducted to test the research model and hypotheses. The empirical results confirm the following: (1) the source credibility of online reviews had a positive effect on the online luxury purchase intentions of mobile customers but increased their intention to recommend the shopping site even more in a luxury environment; (2) face consciousness had a negative moderating effect between source credibility and the online luxury purchase intention of mobile consumers; and (3) face consciousness had a negative moderating effect between source credibility and the luxury recommendation intention of mobile consumers. The implications for theory and practice and suggestions for future research were also discussed.

show abstract

Section: Discussionmentioning

confidence: 99%

Mobile Users’ Online Luxury Consumption in China: The Moderating Role of Face Consciousness

Xin

2021

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…This method mainly detects by comparing the gray value difference between the crack road and its background. However, the detection rate is low due to the complex background of pavement, various lighting, and the diversity of crack types [5,6]. Therefore, this method can only be used as auxiliary detection.…”

Section: Introductionmentioning

confidence: 99%

Pavement Crack Detection Method Based on Deep Learning Models

Yang

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Severe weather and long-term driving of vehicles lead to various cracks on asphalt pavement. If these cracks cannot be found and repaired in time, it will have a negative impact on the safe driving of vehicles. Traditional artificial detection has some problems, such as low efficiency and missing detection. The detection model based on machine learning needs artificial design of pavement crack characteristics. According to the pavement distress identification manual proposed by the Federal Highway Administration (FHWA), these categories have three different types of cracks, such as fatigue, longitudinal crack, and transverse cracks. In the face of many types of pavement cracks, it is difficult to design a general feature extraction model to extract pavement crack features, which leads to the poor effect of the automatic detection model based on machine learning. Object detection based on the deep learning model has achieved good results in many fields. As a result, those models have become possible for pavement crack detection. This paper discusses the latest YOLOv5 series detection model for pavement crack detection and is to find out an effective training and detection method. Firstly, the 3001 asphalt crack pavement images with the original size of 2976 × 3978 pixels are collected using a digital camera and are randomly divided into three types according to the severity levels of low, medium, and high. Then, for the dataset of crack pavement, YOLOv5 series models are used for training and testing. The experimental results show that the detection accuracy of the YOLOv5l model is the highest, reaching 88.1%, and the detection time of the YOLOv5s model is the shortest, only 11.1 ms for each image.

show abstract

“…With the rapid development of computer technology, the collected multimedia data from many research fields, such as computer vision, image processing, and natural language processing, always have features with high dimension and complex structures. These high-dimensional data can not only provide abundant information but also bring some problems such as the "curse of dimensionality" [1,2]. Therefore, how to effectively deal with high-dimensional data has become a widespread concern [3].…”

Section: Introductionmentioning

confidence: 99%

Adaptive‐Weighted Multiview Deep Basis Matrix Factorization for Multimedia Data Analysis

Liu

Dai

et al. 2021

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

Feature representation learning is a key issue in artificial intelligence research. Multiview multimedia data can provide rich information, which makes feature representation become one of the current research hotspots in data analysis. Recently, a large number of multiview data feature representation methods have been proposed, among which matrix factorization shows the excellent performance. Therefore, we propose an adaptive-weighted multiview deep basis matrix factorization (AMDBMF) method that integrates matrix factorization, deep learning, and view fusion together. Specifically, we first perform deep basis matrix factorization on data of each view. Then, all views are integrated to complete the procedure of multiview feature learning. Finally, we propose an adaptive weighting strategy to fuse the low-dimensional features of each view so that a unified feature representation can be obtained for multiview multimedia data. We also design an iterative update algorithm to optimize the objective function and justify the convergence of the optimization algorithm through numerical experiments. We conducted clustering experiments on five multiview multimedia datasets and compare the proposed method with several excellent current methods. The experimental results demonstrate that the clustering performance of the proposed method is better than those of the other comparison methods.

show abstract

Joint feature representation and classification via adaptive graph semi-supervised nonnegative matrix factorization

Cited by 15 publications

References 32 publications

Mobile Users’ Online Luxury Consumption in China: The Moderating Role of Face Consciousness

Mobile Users’ Online Luxury Consumption in China: The Moderating Role of Face Consciousness

Pavement Crack Detection Method Based on Deep Learning Models

Adaptive‐Weighted Multiview Deep Basis Matrix Factorization for Multimedia Data Analysis

Contact Info

Product

Resources

About