Query：
学者姓名：张勇
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-Author
Language
Clean All
Abstract ：
Most existing weakly supervised crowd counting methods utilize Convolutional Neural Networks (CNN) or Transformer to estimate the total number of individuals in an image. However, both CNN-based (grid-to-count paradigm) and Transformer-based (sequence-to-count paradigm) methods take images as inputs in a regular form. This approach treats all pixels equally but cannot address the uneven distribution problem within human crowds. This challenge would lead to a decline in the counting performance of the model. Compared with grid and sequence, the graph structure could better explore the relationship among features. In this article, we propose a new graph-based crowd counting method named CrowdGraph, which reinterprets the weakly supervised crowd counting problem from a graph-to-count perspective. In the proposed CrowdGraph, each image is constructed as a graph, and a graph-based network is designed to extract features at the graph level. CrowdGraph comprises three main components: a dynamic graph convolutional backbone, a multi-scale dilated graph convolution module, and a regression head. To the best of our knowledge, CrowdGraph is the first method that is completely formulated based on the Graph Neural Network (GNN) for the crowd counting task. Extensive experiments demonstrate that the proposed CrowdGraph outperforms pure CNN-based and pure Transformer-based weakly supervised methods comprehensively and achieves highly competitive counting performance.
Keyword ：
Crowd counting Crowd counting weakly supervised learning weakly supervised learning uneven distribution of crowds uneven distribution of crowds graph neural network graph neural network
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Chengyang , Zhang, Yong , Li, Bo et al. CrowdGraph: Weakly supervised Crowd Counting via Pure Graph Neural Network [J]. | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (5) . |
| MLA | Zhang, Chengyang et al. "CrowdGraph: Weakly supervised Crowd Counting via Pure Graph Neural Network" . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20 . 5 (2024) . |
| APA | Zhang, Chengyang , Zhang, Yong , Li, Bo , Piao, Xinglin , Yin, Baocai . CrowdGraph: Weakly supervised Crowd Counting via Pure Graph Neural Network . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (5) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Multivariate time series forecasting plays an important role in many domain applications, such as air pollution forecasting and traffic forecasting. Modeling the complex dependencies among time series is a key challenging task in multivariate time series forecasting. Many previous works have used graph structures to learn inter-series correlations, which have achieved remarkable performance. However, graph networks can only capture spatio-temporal dependencies between pairs of nodes, which cannot handle high-order correlations among time series. We propose a Dynamic Hypergraph Structure Learning model (DHSL) to solve the above problems. We generate dynamic hypergraph structures from time series data using the K-Nearest Neighbors method. Then a dynamic hypergraph structure learning module is used to optimize the hypergraph structure to obtain more accurate high-order correlations among nodes. Finally, the hypergraph structures dynamically learned are used in the spatio-temporal hypergraph neural network. We conduct experiments on six real-world datasets. The prediction performance of our model surpasses existing graph network-based prediction models. The experimental results demonstrate the effectiveness and competitiveness of the DHSL model for multivariate time series forecasting.
Keyword ：
Recurrent neural networks Recurrent neural networks Time series analysis Time series analysis hypergraph structure learning hypergraph structure learning Forecasting Forecasting Predictive models Predictive models multivariate time series forecasting multivariate time series forecasting Data models Data models Adaptation models Adaptation models Graph neural network Graph neural network Correlation Correlation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Shun , Zhang, Yong , Lin, Xuanqi et al. Dynamic Hypergraph Structure Learning for Multivariate Time Series Forecasting [J]. | IEEE TRANSACTIONS ON BIG DATA , 2024 , 10 (4) : 556-567 . |
| MLA | Wang, Shun et al. "Dynamic Hypergraph Structure Learning for Multivariate Time Series Forecasting" . | IEEE TRANSACTIONS ON BIG DATA 10 . 4 (2024) : 556-567 . |
| APA | Wang, Shun , Zhang, Yong , Lin, Xuanqi , Hu, Yongli , Huang, Qingming , Yin, Baocai . Dynamic Hypergraph Structure Learning for Multivariate Time Series Forecasting . | IEEE TRANSACTIONS ON BIG DATA , 2024 , 10 (4) , 556-567 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Traffic Anomaly Detection (TAD) is an important and difficult task in Intelligent Transportation Systems (ITS) . Traffic anomaly events are sparse in both spatial and temporal spaces, posing a challenge to the performance of model. Moreover, a single traffic anomaly event can impact multiple road sections in the neighborhood, further undermining the accuracy of TAD. In this paper, we propose a new TAD method based on spatio-temporal hypergraph convolutional neural network. Specifically, we adopt a spatial-temporal augmentation approach for traffic data. This will enhance the performance of detecting sparse anomalies. Meanwhile, we introduce a hypergraph learning method to model the road network. This could capture the spreading features of anomalies for better detection results. Additionally, we design a dynamic hypergraph construction method to extract the evolving relationships of road segments. The proposed model evaluation on the Beijing (SE-BJ) dataset for TAD reveals superior performance compared to state-of-the-art ones.
Keyword ：
Traffic anomaly detection Traffic anomaly detection Dynamic hypergraph construction Dynamic hypergraph construction Hypergraph convolution Hypergraph convolution Data sparsity Data sparsity Data augmentation Data augmentation Hypergraph learning Hypergraph learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Feng, Jiangtao , Zhang, Yong , Piao, Xinglin et al. Traffic Anomaly Detection based on Spatio-Temporal Hypergraph Convolution Neural Networks [J]. | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS , 2024 , 646 . |
| MLA | Feng, Jiangtao et al. "Traffic Anomaly Detection based on Spatio-Temporal Hypergraph Convolution Neural Networks" . | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 646 (2024) . |
| APA | Feng, Jiangtao , Zhang, Yong , Piao, Xinglin , Hu, Yongli , Yin, Baocai . Traffic Anomaly Detection based on Spatio-Temporal Hypergraph Convolution Neural Networks . | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS , 2024 , 646 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
In Graph Neural Networks (GNNs), a common feature across many datasets is the Power-law Distribution of node degrees, where most nodes exhibit few connections, contrasting with a small fraction that possesses a high number of links. This difference often introduces training instability and compromises performance on tasks like node classification, particularly for low-degree nodes. To tackle these challenges, we introduce RUNCL: : R elationship U pdating N etwork with C ontrastive L earning, a novel model designed to ensure that the model learns more accurate node features, especially the features of low-degree nodes. Specifically, RUNCL comprises a graph generation module that generates different neighborhood information graphs based on the node feature graphs. The optimal graph selection module selects the neighborhood information graph that best reflects the relationship between nodes and a contrastive learning module to learn more accurate node embeddings by contrasting positive and negative samples. We evaluate the performance of RUNCL on six datasets, and the experimental results demonstrate its effectiveness. The model exhibited an improvement of 2.5% in the testset. Moreover, the model's performance boosted to 6% when the testset only included low-degree nodes. The implementation and data are made available at https://github.com/pengyu-zhang/RUNCLRelationship-Updating-Network-with-Contrastive-Learning.
Keyword ：
Classification graph neural networks Classification graph neural networks Semi-supervised Semi-supervised Graph convolutional networks Graph convolutional networks Graph analysis Graph analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Pengyu , Zhang, Yong , Piao, Xinglin et al. Relationship updating network with contrastive learning [J]. | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS , 2024 , 646 . |
| MLA | Zhang, Pengyu et al. "Relationship updating network with contrastive learning" . | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 646 (2024) . |
| APA | Zhang, Pengyu , Zhang, Yong , Piao, Xinglin , Sun, Yongliang , Yin, Baocai . Relationship updating network with contrastive learning . | PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS , 2024 , 646 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Describing an object from multiple perspectives often leads to incomplete data representation. Consequently, learning consistent representations for missing data from multiple views has emerged as a key focus in the realm of Incomplete Multi-view Representation Learning (IMRL). In recent years, various strategies, such as subspace learning, matrix decomposition, and deep learning, have been harnessed to develop numerous IMRL methods. In this article, our primary research revolves around IMRL, with a particular emphasis on addressing two main challenges. Firstly, we delve into the effective integration of intra-view similarity and contextual structure into a unified framework. Secondly, we explore the effective facilitation of information exchange and fusion across multiple views. To tackle these issues, we propose a deep learning approach known as Structural Contrastive Auto-Encoder (SCAE) to solve the challenges of IMRL. SCAE comprises two major components: intra-view structural representation learning and inter-view contrastive representation learning. The former involves capturing intra-view similarity by minimizing the Dirichlet energy of the feature matrix, while also applying spatial dispersion regularization to capture intra-view contextual structure. The latter encourages maximizing the mutual information of inter-view representations, facilitating information exchange and fusion across views. Experimental results demonstrate the efficacy of our approach in significantly enhancing model accuracy and robustly addressing IMRL problems. The code is available at https://github.com/limengran98/SCAE.
Keyword ：
MC-VAE MC-VAE Dirichlet energy Dirichlet energy mutual information maximization mutual information maximization Incomplete multi-view representation learning Incomplete multi-view representation learning contrastive learning contrastive learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Mengran , Zhang, Ronghui , Zhang, Yong et al. SCAE: Structural Contrastive Auto-Encoder for Incomplete Multi-View Representation Learning [J]. | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (9) . |
| MLA | Li, Mengran et al. "SCAE: Structural Contrastive Auto-Encoder for Incomplete Multi-View Representation Learning" . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20 . 9 (2024) . |
| APA | Li, Mengran , Zhang, Ronghui , Zhang, Yong , Piao, Xinglin , Zhao, Shiyu , Yin, Baocai . SCAE: Structural Contrastive Auto-Encoder for Incomplete Multi-View Representation Learning . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (9) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Video object segmentation (VOS) exhibits heavy occlusions, large deformation, and severe motion blur. While many remarkable convolutional neural networks are devoted to the VOS task, they often mis-identify background noise as the target or output coarse object boundaries, due to the failure of mining detail information and high-order correlations of pixels within the whole video. In this work, we propose an edge attention gated graph convolutional network (GCN) for VOS. The seed point initialization and graph construction stages construct a spatio-temporal graph of the video by exploring the spatial intra-frame correlation and the temporal inter-frame correlation of superpixels. The node classification stage identifies foreground superpixels by using an edge attention gated GCN which mines higher-order correlations between superpixels and propagates features among different nodes. The segmentation optimization stage optimizes the classification of foreground superpixels and reduces segmentation errors by using a global appearance model which captures the long-term stable feature of objects. In summary, the key contribution of our framework is twofold: (a) the spatio-temporal graph representation can propagate the seed points of the first frame to subsequent frames and facilitate our framework for the semi-supervised VOS task; and (b) the edge attention gated GCN can learn the importance of each node with respect to both the neighboring nodes and the whole task with a small number of layers. Experiments on Davis 2016 and Davis 2017 datasets show that our framework achieves the excellent performance with only small training samples (45 video sequences).
Keyword ：
semi-supervised video object segmentation semi-supervised video object segmentation graph convolutional network graph convolutional network superpixel superpixel spatio-temporal graph model spatio-temporal graph model
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Yuqing , Zhang, Yong , Wang, Shaofan et al. Semi-supervised Video Object Segmentation Via an Edge Attention Gated Graph Convolutional Network [J]. | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (1) . |
| MLA | Zhang, Yuqing et al. "Semi-supervised Video Object Segmentation Via an Edge Attention Gated Graph Convolutional Network" . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20 . 1 (2024) . |
| APA | Zhang, Yuqing , Zhang, Yong , Wang, Shaofan , Liang, Yun , Yin, Baocai . Semi-supervised Video Object Segmentation Via an Edge Attention Gated Graph Convolutional Network . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2024 , 20 (1) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Cell localization in medical image analysis is a challenging task due to the significant variation in cell shape, size and color. Existing localization methods continue to tackle these challenges separately, frequently facing complications where these difficulties intersect and adversely impact model performance. In this paper, these challenges are first reframed as issues of feature misalignment between cell images and location maps, which are then collectively addressed. Specifically, we propose a feature alignment model based on a multiscale hypergraph attention network. The model considers local regions in the feature map as nodes and utilizes a learnable similarity metric to construct hypergraphs at various scales. We then utilize a hypergraph convolutional network to aggregate the features associated with the nodes and achieve feature alignment between the cell images and location maps. Furthermore, we introduce a stepwise adaptive fusion module to fuse features at different levels effectively and adaptively. The comprehensive experimental results demonstrate the effectiveness of our proposed multi -scale hypergraph attention module in addressing the issue of feature misalignment, and our model achieves state-of-the-art performance across various cell localization datasets.
Keyword ：
Hypergraph neural network Hypergraph neural network Cell localization Cell localization Stepwise adaptive fusion Stepwise adaptive fusion Multi-scale hypergraph attention Multi-scale hypergraph attention Feature alignment Feature alignment
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Bo , Zhang, Yong , Zhang, Chengyang et al. Multi-scale hypergraph-based feature alignment network for cell localization [J]. | PATTERN RECOGNITION , 2024 , 149 . |
| MLA | Li, Bo et al. "Multi-scale hypergraph-based feature alignment network for cell localization" . | PATTERN RECOGNITION 149 (2024) . |
| APA | Li, Bo , Zhang, Yong , Zhang, Chengyang , Piao, Xinglin , Hu, Yongli , Yin, Baocai . Multi-scale hypergraph-based feature alignment network for cell localization . | PATTERN RECOGNITION , 2024 , 149 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Millimeter-wave (mmWave) communications with abundant spectrum resources have become an enabling technology for high throughput, ultra-reliable, and low latency communications (URLLC). Since the mmWave signal is sensitive to blockage, accurate base station (BS) selection is the premise of achieving the URLLC. In this paper, we propose a multi-view images assisted proactive BS selection scheme that can predict the optimal BS for the user in the next frame. The proposed scheme utilizes vision sensing and thus does not require the entire pilot resources, such that the latency caused by seeding and receiving pilots reduces. In addition, we design a multi-task learning strategy and a prior knowledge based fine tuning method to ensure the accuracy and reliability of BS selection. Simulation results in an outdoor environment demonstrate the superior performance of the proposed scheme in terms of both the accuracy and the robustness.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Bo , Gao, Feifei , Zhang, Yong et al. Proactive Base Station Selection Empowered by Multi-View Images [J]. | 2024 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC 2024 , 2024 . |
| MLA | Lin, Bo et al. "Proactive Base Station Selection Empowered by Multi-View Images" . | 2024 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC 2024 (2024) . |
| APA | Lin, Bo , Gao, Feifei , Zhang, Yong , Pan, Chengkang , Liu, Guangyi . Proactive Base Station Selection Empowered by Multi-View Images . | 2024 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC 2024 , 2024 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Attribute graphs are a crucial data structure for graph communities. However, the presence of redundancy and noise in the attribute graph can impair the aggregation effect of integrating two different heterogeneous distributions of attribute and structural features, resulting in inconsistent and distorted data that ultimately compromises the accuracy and reliability of attribute graph learning. For instance, redundant or irrelevant attributes can result in overfitting, while noisy attributes can lead to underfitting. Similarly, redundant or noisy structural features can affect the accuracy of graph representations, making it challenging to distinguish between different nodes or communities. To address these issues, we propose the embedded fusion graph auto-encoder framework for self-supervised learning (SSL), which leverages multitask learning to fuse node features across different tasks to reduce redundancy. The embedding fusion graph auto-encoder (EFGAE) framework comprises two phases: pretraining (PT) and downstream task learning (DTL). During the PT phase, EFGAE uses a graph auto-encoder (GAE) based on adversarial contrastive learning to learn structural and attribute embeddings separately and then fuses these embeddings to obtain a representation of the entire graph. During the DTL phase, we introduce an adaptive graph convolutional network (AGCN), which is applied to graph neural network (GNN) classifiers to enhance recognition for downstream tasks. The experimental results demonstrate that our approach outperforms state-of-the-art (SOTA) techniques in terms of accuracy, generalization ability, and robustness.
Keyword ：
Convolution Convolution self-supervised learning (SSL) self-supervised learning (SSL) Task analysis Task analysis redundancy reduction redundancy reduction Self-supervised learning Self-supervised learning Representation learning Representation learning Graph neural networks Graph neural networks attribute graphs attribute graphs contrastive learning contrastive learning Termination of employment Termination of employment Adaptive graph convolution Adaptive graph convolution Redundancy Redundancy graph auto-encoder (GAE) graph auto-encoder (GAE)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Mengran , Zhang, Yong , Wang, Shaofan et al. Redundancy Is Not What You Need: An Embedding Fusion Graph Auto-Encoder for Self-Supervised Graph Representation Learning [J]. | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2024 . |
| MLA | Li, Mengran et al. "Redundancy Is Not What You Need: An Embedding Fusion Graph Auto-Encoder for Self-Supervised Graph Representation Learning" . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2024) . |
| APA | Li, Mengran , Zhang, Yong , Wang, Shaofan , Hu, Yongli , Yin, Baocai . Redundancy Is Not What You Need: An Embedding Fusion Graph Auto-Encoder for Self-Supervised Graph Representation Learning . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2024 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Traffic accident prediction is an important research problem, which can help to identify dangerous situations on the road in advance and take appropriate measures. Nonetheless, real -world traffic accident data suffers from a significant data unbalance problem, as accident occurrences vary unevenly in both spatial and data domains. This unbalance can easily lead to the prediction methods biased towards the side with more data. Recently, researchers have proposed a series of effective prediction methods based on deep learning and graph theory. Existing graph -based methods always adopt the predefined distance graph. However, these methods cannot fully capture the spatial correlations among regions that are far away from each other but share similar accident patterns. To address these challenges, we propose a traffic accident prediction method that combines Adaptive Graphs with Self -Supervised Learning (AGSSL). In the proposed method, we can adaptively construct graph structures to learn global spatial correlations among urban regions. Meanwhile, two self -supervised learning modules called Graph Infomax and Focal Contrastive Regularization are used to learn a robust representation of traffic accidents data under an unbalanced distribution. Experiment results show that AGSSL outperforms SOTA methods in traffic accident prediction.
Keyword ：
Self-supervised learning Self-supervised learning Traffic accident prediction Traffic accident prediction Unbalanced data classification Unbalanced data classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Shun , Zhang, Yong , Piao, Xinglin et al. Data-unbalanced traffic accident prediction via adaptive graph and self-supervised learning [J]. | APPLIED SOFT COMPUTING , 2024 , 157 . |
| MLA | Wang, Shun et al. "Data-unbalanced traffic accident prediction via adaptive graph and self-supervised learning" . | APPLIED SOFT COMPUTING 157 (2024) . |
| APA | Wang, Shun , Zhang, Yong , Piao, Xinglin , Lin, Xuanqi , Hu, Yongli , Yin, Baocai . Data-unbalanced traffic accident prediction via adaptive graph and self-supervised learning . | APPLIED SOFT COMPUTING , 2024 , 157 . |
| Export to | NoteExpress RIS BibTex |
Export
| Results： |
Selected to |
| Format： |
