Junyang Chen
Biographic Data
| ID | 6721708 |
|---|---|
| NAME | Junyang Chen |
| GIVEN NAMES | Junyang |
| FAMILY NAME | Chen |
| SIGNATURE | CHEN J |
| AFFILIATIONS | Shenzhen University |
| ORCID | 0000-0002-5258-9035 |
| VERIFIED | Yes |
| TOTAL WORKS | 14 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 14 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2022 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
Inhibiting Informal Social Control: How Callous–Unemotional Traits and Body Shame Impede Bystander Intervention in Cyber Delinquency
Bystander intervention acts as a critical mechanism of informal social control against cyber delinquency. Grounded in Social Information Processing theory, this study examines the barriers impeding students from acting as capable guardians. Analysis of 423 university students supported a serial mediation model: Callous–unemotional (CU) traits inhibit intervention by eroding perceived social support, subsequently desensitizing individuals to harm …
Adaptive Density Estimation for Personalized Recommendations Across Varied User Activity Levels
Top-N recommendation systems are recognized as highly effective for delivering personalized services that cater to the varied interests of users. Nonetheless, current state-of-the-art (SOTA) analyses reveal a marked variability in their performance across users with differing levels of activity, which substantially undermines the quality of personalized recommendation services. Prevailing research tends to overlook this discrepancy, often presumi…
Cig2s: A Cross-View Image Geo-Localization Model Based on G2S Transform Suitable for Center-Misaligned Scenarios
In multimedia social networks, the user's geo-location can be inferred by matching his shared images with the referenced satellite images, viz. cross-view image geo-localization. Although the existing most cross-view image geo-localization methods perform well in the center-misaligned scenario, in practical application, the shooting location of the query ground image is most likely not aligned with the center point of satellite images. Then, thei…
A Review of Few-Shot and Zero-Shot Learning for Node Classification in Social Networks
Node classification tasks aim to assign labels or categories to entire graphs based on their structural properties or node attributes. It can be adopted for various types of graph systems, including but not limited to network traffic, biological networks, knowledge graphs, etc., especially to social networks. This problem is well-studied, and solutions have demonstrated significant success in numerous real-world applications. However, in the situ…
CGraphNet: Contrastive Graph Context Prediction for Sparse Unlabeled Short Text Representation Learning on Social Media
Unlabeled text representation learning (UTRL), encompassing static word embeddings such as Word2Vec and contextualized word embeddings such as bidirectional encoder representations from transformer (BERT), aims to capture semantic word relationships in a low-dimensional space without the need for manual labeling. These word embeddings are invaluable for downstream tasks such as document classification and clustering. However, the surge of short t…
The Invisible Catalyst: How Belonging Collapse and Bystander Complicity Mediate Toxic Disinhibition’s Path to Cyberbullying
This study investigates how toxic online disinhibition influences cyberbullying through the mediating roles of belonging collapse and bystander complicity. Using a cross-sectional survey of 379 Chinese university students, we tested a sequential mediation model with structural equation modeling. Results indicate that higher levels of toxic disinhibition predict lower perceived belonging and greater passive bystander behavior, both of which are as…
Huaxian formula prevents the progression of radiation-induced pulmonary fibrosis by inhibiting the pro-fibrotic effects of macrophages
HXF's preventive effects on RIPF involve multiple targets and mechanisms, including the modulation of Arg1, Mmp10, and Fgf23 expression. By inhibiting the pro-fibrotic capacity of macrophages, HXF suppresses fibroblast activation and collagen production, thereby alleviating lung fibrosis. These findings underscore the potential of HXF as a preventive strategy in managing RIPF
Compressing the Multiobject Tracking Model via Knowledge Distillation
Recent multiobject tracking (MOT) methods usually use very deep neural networks to achieve competitive accuracy, which inevitably results in degraded inference speed. To strike a better balance between tracking accuracy and speed, in this work, we propose to compress the MOT model via knowledge distillation (KD), enabling the more lightweight student model to obtain similar performance as the teacher model. Nonetheless, despite KD has been well s…
Multidocument Aspect Classification for Aspect-Based Abstractive Summarization
Multidocument aspect-based summarization (AspSumm) aims to generate focused summaries based on the target aspects from a cluster of relevant documents. Generating such summaries can better satisfy readers’ specific points of interest, as readers may have different concerns about the same articles. However, previous methods usually generate aspect-based summaries based on the given aspects without using the relationship among aspects to assist in …
SiamATTRPN: Enhance Visual Tracking With Channel and Spatial Attention
Visual tracking is an important research topic in the field of computer vision. The current Siamese tracker based on the region proposal network (SiamRPN) has achieved promising tracking results in terms of efficiency and performance. However, through our empirical study, we have observed that deep features learned by SiamRPN are of substandard quality, as the salient regions within the deep features fail to correspond accurately with meaningful …
TFC: Transformer Fused Convolution for Adversarial Domain Adaptation
In unsupervised domain adaptation (UDA), a classifier is applied to the target domain without or with limited labels, when the target domain has no or few labels. Recently, inspired by their capabilities of long-distance feature dependencies, vision transformer (ViT)-based methods have been used in UDA, however, they ignore the fact that ViT lacks strength in extracting local feature details. To handle the above problems, the purpose of this arti…
Assessing provincial environment governance efficiency in China: A multi-agents participation perspective
Irlm: Inductive Representation Learning Model for Personalized POI Recommendation
With the rapid development of the Internet of Things technology, the concept of smart cities that aims to help residents improve their quality of life has raised much attention in several application areas. In the context of smart cities, the provision of point of interest (POI) recommendations become an important requirement because a wide range of POIs are available for urban dwellers. Location-based social networks (LBSNs) such as Foursquare a…
Robust Matrix Factorization via Minimum Weighted Error Entropy Criterion
Learning the intrinsic low-dimensional subspace from high-dimensional data is a key step for many social systems of artificial intelligence. In practical scenarios, the observed data are usually corrupted by many types of noise, which brings a great challenge for social systems to analyze data. As a commonly utilized subspace learning technique, robust low-rank matrix factorization (LRMF) focuses on recovering the underlying subspaces in a noisy …
No prominent works on this page.
Robust Matrix Factorization via Minimum Weighted Error Entropy Criterion
Learning the intrinsic low-dimensional subspace from high-dimensional data is a key step for many social systems of artificial intelligence. In practical scenarios, the observed data are usually corrupted by many types of noise, which brings a great challenge for social systems to analyze data. As a commonly utilized subspace learning technique, robust low-rank matrix factorization (LRMF) focuses on recovering the underlying subspaces in a noisy …
Irlm: Inductive Representation Learning Model for Personalized POI Recommendation
With the rapid development of the Internet of Things technology, the concept of smart cities that aims to help residents improve their quality of life has raised much attention in several application areas. In the context of smart cities, the provision of point of interest (POI) recommendations become an important requirement because a wide range of POIs are available for urban dwellers. Location-based social networks (LBSNs) such as Foursquare a…
Compressing the Multiobject Tracking Model via Knowledge Distillation
Recent multiobject tracking (MOT) methods usually use very deep neural networks to achieve competitive accuracy, which inevitably results in degraded inference speed. To strike a better balance between tracking accuracy and speed, in this work, we propose to compress the MOT model via knowledge distillation (KD), enabling the more lightweight student model to obtain similar performance as the teacher model. Nonetheless, despite KD has been well s…
Multidocument Aspect Classification for Aspect-Based Abstractive Summarization
Multidocument aspect-based summarization (AspSumm) aims to generate focused summaries based on the target aspects from a cluster of relevant documents. Generating such summaries can better satisfy readers’ specific points of interest, as readers may have different concerns about the same articles. However, previous methods usually generate aspect-based summaries based on the given aspects without using the relationship among aspects to assist in …
SiamATTRPN: Enhance Visual Tracking With Channel and Spatial Attention
Visual tracking is an important research topic in the field of computer vision. The current Siamese tracker based on the region proposal network (SiamRPN) has achieved promising tracking results in terms of efficiency and performance. However, through our empirical study, we have observed that deep features learned by SiamRPN are of substandard quality, as the salient regions within the deep features fail to correspond accurately with meaningful …
TFC: Transformer Fused Convolution for Adversarial Domain Adaptation
In unsupervised domain adaptation (UDA), a classifier is applied to the target domain without or with limited labels, when the target domain has no or few labels. Recently, inspired by their capabilities of long-distance feature dependencies, vision transformer (ViT)-based methods have been used in UDA, however, they ignore the fact that ViT lacks strength in extracting local feature details. To handle the above problems, the purpose of this arti…
Assessing provincial environment governance efficiency in China: A multi-agents participation perspective
Adaptive Density Estimation for Personalized Recommendations Across Varied User Activity Levels
Top-N recommendation systems are recognized as highly effective for delivering personalized services that cater to the varied interests of users. Nonetheless, current state-of-the-art (SOTA) analyses reveal a marked variability in their performance across users with differing levels of activity, which substantially undermines the quality of personalized recommendation services. Prevailing research tends to overlook this discrepancy, often presumi…
Cig2s: A Cross-View Image Geo-Localization Model Based on G2S Transform Suitable for Center-Misaligned Scenarios
In multimedia social networks, the user's geo-location can be inferred by matching his shared images with the referenced satellite images, viz. cross-view image geo-localization. Although the existing most cross-view image geo-localization methods perform well in the center-misaligned scenario, in practical application, the shooting location of the query ground image is most likely not aligned with the center point of satellite images. Then, thei…
A Review of Few-Shot and Zero-Shot Learning for Node Classification in Social Networks
Node classification tasks aim to assign labels or categories to entire graphs based on their structural properties or node attributes. It can be adopted for various types of graph systems, including but not limited to network traffic, biological networks, knowledge graphs, etc., especially to social networks. This problem is well-studied, and solutions have demonstrated significant success in numerous real-world applications. However, in the situ…
CGraphNet: Contrastive Graph Context Prediction for Sparse Unlabeled Short Text Representation Learning on Social Media
Unlabeled text representation learning (UTRL), encompassing static word embeddings such as Word2Vec and contextualized word embeddings such as bidirectional encoder representations from transformer (BERT), aims to capture semantic word relationships in a low-dimensional space without the need for manual labeling. These word embeddings are invaluable for downstream tasks such as document classification and clustering. However, the surge of short t…
The Invisible Catalyst: How Belonging Collapse and Bystander Complicity Mediate Toxic Disinhibition’s Path to Cyberbullying
This study investigates how toxic online disinhibition influences cyberbullying through the mediating roles of belonging collapse and bystander complicity. Using a cross-sectional survey of 379 Chinese university students, we tested a sequential mediation model with structural equation modeling. Results indicate that higher levels of toxic disinhibition predict lower perceived belonging and greater passive bystander behavior, both of which are as…
Huaxian formula prevents the progression of radiation-induced pulmonary fibrosis by inhibiting the pro-fibrotic effects of macrophages
HXF's preventive effects on RIPF involve multiple targets and mechanisms, including the modulation of Arg1, Mmp10, and Fgf23 expression. By inhibiting the pro-fibrotic capacity of macrophages, HXF suppresses fibroblast activation and collagen production, thereby alleviating lung fibrosis. These findings underscore the potential of HXF as a preventive strategy in managing RIPF
Inhibiting Informal Social Control: How Callous–Unemotional Traits and Body Shame Impede Bystander Intervention in Cyber Delinquency
Bystander intervention acts as a critical mechanism of informal social control against cyber delinquency. Grounded in Social Information Processing theory, this study examines the barriers impeding students from acting as capable guardians. Analysis of 423 university students supported a serial mediation model: Callous–unemotional (CU) traits inhibit intervention by eroding perceived social support, subsequently desensitizing individuals to harm …
Computer Science (11 works) · Artificial Intelligence (9 works) · Machine learning (5 works) · Engineering (3 works) · Mathematics (3 works) · Algorithm (2 works) · Bullying, Victimization, and Aggression (2 works) · Bystander effect (2 works) · Computer vision (2 works) · Domain Adaptation and Few-Shot Learning (2 works)