检索结果-内蒙古大学图书馆

Unsupervised social network embedding via adaptive specific mappings

Frontiers of Computer Science 2024年第3期18卷 61-71页

作者： Youming GE Cong HUANG Yubao LIU Sen ZHANG Weiyang KONG School of Computer Science and Engineering Sun Yat-Sen UniversityGuangzhou 510275China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou 510006China

In this paper,we address the problem of unsuperised social network embedding,which aims to embed network nodes,including node attributes,into a latent low dimensional *** recent methods,the fusion mechanism of node attributes and network structure has been proposed for the problem and achieved impressive prediction ***,the non-linear property of node attributes and network structure is not efficiently fused in existing methods,which is potentially helpful in learning a better network *** this end,in this paper,we propose a novel model called ASM(Adaptive Specific Mapping)based on encoder-decoder *** encoder,we use the kernel mapping to capture the non-linear property of both node attributes and network *** particular,we adopt two feature mapping functions,namely an untrainable function for node attributes and a trainable function for network *** the mapping functions,we obtain the low dimensional feature vectors for node attributes and network structure,***,we design an attention layer to combine the learning of both feature vectors and adaptively learn the node *** encoder,we adopt the component of reconstruction for the training process of learning node attributes and network *** conducted a set of experiments on seven real-world social network *** experimental results verify the effectiveness and efficiency of our method in comparison with state-of-the-art baselines.

关键词： network embedding specific kernel mapping attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph Deviation Neural Networks for Anomaly Detection in Time Series

Spatial-Temporal Graph Deviation Neural Networks for Anomaly...

引用

2023 International Conference on Electronic, Electrical and Information Technology, EEIT 2023

作者： Guo, Ziyu Kong, Weiyang Liu, Yubao Sun Yat-Sen University Guang Zhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Anomaly detection in time series data (e.g., sensor data) is becoming a fundamental research problem that has various applications. Due to the complex inter-sensor relationships, it is challenging to detect anomalous events such as system faults and attacks hidden the high-dimensional time series. Recent advancements in deep learning approaches such as Graph Neural Networks (GNN) have greatly improved anomaly detection performance in time series data. However, existing methods usually use separate components to capture spatial and temporal dependence relationship and ignore the heterogeneities in spatial-temporal data which motivates us to capture them together. In this paper, we propose a novel approach STGDNN (short for Spatial-Temporal Graph Deviation Neural Networks) that learns the spatial-temporal dependence relationship together in structure learning of graph neural networks. In addition, we use the learned spatial-temporal graph structure and attention weights to explain the detected anomalies. The experiments on three real world datasets show our superiority in detection accuracy, anomaly diagnosis, and model interpretation compared with state-of-the-art methods. © Published under licence by IOP Publishing Ltd.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Hash Retrieval with Category Semantics 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Xu, Mengying Lai, Hanjiang Yin, Jian Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

ISBN: (数字)9783031533051

ISBN: (纸本)9783031533044

With the multi-medal resource springing up, the field of cross-modal research has witnessed rapid advancement. Among these, Cross-Modal Hash retrieval has attracted attention due to its time-saving capabilities during the retrieval process. However, most existing cross-modal hash retrieval methods focus on capturing the relationship between modalities and often train in a one-to-one correspondence manner. Consequently, they often neglect the comprehensive distribution of the entire dataset. In response, we propose a novel approach that introduces semantic relationships between categories to capture class relationships and enable the measurement of the full distribution. First, the original image and text are encoded to obtain respective representations. Then, these are fused to generate a joint representation, which is passed through a classification head to obtain category semantics. The semantic information is used to allocate hash centers from a Hadamard matrix. Meanwhile, the image and text representations are fed into a hash layer to produce hash codes. We train the network with a modal matching loss for alignment, as well as center and class loss to capture the full data distribution. Extensive evaluations on two benchmark databases demonstrate that our approach achieves competitive performance compared to state-of-the-art methods. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LLDB: Efficient Low-Light Image Enhancement with Difffusion Bridge

LLDB: Efficient Low-Light Image Enhancement with Difffusion ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Ma, Junlong Yue, Conghan Peng, Zhengwei Zhang, Dongyu Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

ISBN: (纸本)9798350368741

This paper investigates a low-light image enhancement method based on the diffusion bridge framework. Currently, low-light image enhancement tasks still face challenges in noise reduction and detail restoration, and existing diffusion model methods are time-consuming and have unstable diffusion processes. We conducted an in-depth study of diffusion bridge theory, integrating the advantages of the end-to-end paradigm of diffusion bridge theory and employing a nonlinear activation network to further enhance the performance of low-light image enhancement tasks. Additionally, we used a Gamma correction module for fine-tuning low-light images, significantly improving performance with almost no extra computational cost. Experiments show that Low-Light image enhancement with Difffusion Bridge (LLDB) far surpasses other methods on LOLv1 and LOLv2 datasets. Code is available at https://***/M-Chase/LLDB. © 2025 IEEE.

关键词： Diffusion Bridge Diffusion Model Low-Light image Enhancement

来源：评论

学校读者我要写书评

暂无评论

SymGaussian: Occluded Human Rendering with Multi-scale Symmetry Feature from Monocular Video

SymGaussian: Occluded Human Rendering with Multi-scale Symme...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Jiang, Zekai Duan, Tong Zhang, Dongyu Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

ISBN: (纸本)9798350368741

The growing demand for high-quality 3D human rendering in real-world applications highlights significant challenges. These challenges are particularly evident in dealing with occlusion in monocular video. Previous methods often rely on controlled datasets and overlook the inherent symmetry of the human body, leading to incomplete rendering in occluded areas. To address these limitations, we propose SymGaussian, a novel Gaussian Splatting-based approach for rendering occluded human from monocular video. We introduce Multi-scale Symmetry Feature to compensate for lost information in occluded areas, along with a Projective Texture Mapping method that efficiently encodes 2D appearance while preserving 3D perception. Experiments show that SymGaussian outperforms state-of-the-art methods in rendering quality, while achieving rapid training speed and real-time rendering capability exceeding 200 FPS. © 2025 IEEE.

关键词： 3D Gaussian Splatting Multi-scale Symmetry Feature Occluded Human Rendering Texture Mapping

来源：评论

学校读者我要写书评

暂无评论

Infusing knowledge into CLIP via low-rank matrix for video-text retrieval

Infusing knowledge into CLIP via low-rank matrix for video-t...

引用

2024 International Conference on Image, Signal processing, and Pattern Recognition, ISPP 2024

作者： Zhang, Daqing Yin, Jian School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

ISBN: (纸本)9781510680425

Video-text retrieval has been a crucial task with the exponential growth of video. Recent methods that leverage the pretrained CLIP model in the video-text retrieval task have demonstrated remarkable performance, surpassing many approaches trained on large-scale video-text datasets. However, these works ignore the performance-efficiency trade-off in the pursuit of better performance. Additionally, a completely new model is typically necessary for each task because many existing works fully fine-tune the pre-trained backbone. Therefore, to yield a compact and transferable model, we propose LoCLIP, a framework that transfers knowledge from CLIP in a parameter-efficient manner. Inspired by LoRA, we incorporate only a small set of trainable low-rank matrices per task, allowing adaptation to new tasks by simply replacing these matrices. In this way, we can acquire task-specific knowledge without compromising the prior knowledge stored in the pre-trained backbone. To demonstrate the effectiveness of our LoCLIP, we conduct extensive experiments and achieve comparable performance with state-of-the-art CLIP-based video-text retrieval methods while updating only a few parameters. © 2024 SPIE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Anima2: Cross-Species Animal Animation through Image-to-Video Synthesis with Subject Alignment

Anima2: Cross-Species Animal Animation through Image-to-Vide...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Xu, Yuanfeng Chen, Yuhao Huang, Zhongzhan He, Zijian Wang, Guangrun Lin, Liang Sun Yat-sen University China Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

ISBN: (纸本)9798350368741

Recent video editing advancements rely on accurate pose sequences to animate human actors. However, these efforts are not suitable for cross-species animation due to pose misalignment between species (for example, the poses of a cat differ greatly from that of a pig due to their distinct body structures). In this paper, we present Anima2, a zero-shot diffusion-based video generator to address this issue, aiming to accurately ANIMAte ANIMAls while preserving the background. The key technique involves two-fold subject alignment. First, we improve appearance feature extraction by integrating a Laplacian detail booster and a prompt-tuning identity extractor. They capture essential appearance information, including identity and fine details. Second, we align shape features and address conflicts from differing animals by introducing a scale-information remover and an adaptive rescaling module. They both enhance subject alignment for accurate cross-species animation. Additionally, we introduce two high-quality animal video datasets with diverse species to benchmark cross-species animation. Trained on these extensive datasets, our model directly generates videos with accurate movements, consistent appearances, and high-fidelity frames, eliminating the need for test-time training. Extensive experiments demonstrate our method's superiority in cross-species animation, showcasing robust adaptability and generality. © 2025 IEEE.

关键词： cross-species subject alignment video editing

来源：评论

学校读者我要写书评

暂无评论

Demand Learning and Cooperative Deployment of UAV Networks

引用

Chinese Journal of Electronics 2022年第3期31卷 408-415页

作者： ZHANG Xiao WANG Xuehe XU Xinping ZHAO Yingchao South-Central University for Nationalities Caritas Institute of Higher Education Sun Yat-sen University & Guangdong Key Laboratory of Big Data Analysis and Processing Nanyang Technological University

Unmanned aerial vehicle(UAV) as a powerful tool has found its applicability in assisting mobile users to deal with computation-intensive and delaysensitive applications(e.g., edge computing, high-speed Internet access, and local caching). However, deployment of UAV-aided mobile services(UMS) faces challenges due to the UAV limitation in wireless coverage and energy storage. Aware of such physical limitations, a future UMS system should be intelligent enough to self-plan trajectories and best offer computational capabilities to mobile users. There are important issues regarding the UAV-user interaction, UAV-UAV cooperation for sustainable service provision, and dynamic UMS pricing. These networking and resource management issues are largely overlooked in the literature and this article presents intelligent solutions for cooperative UMS deployment and operation. Mobile users' locations are generally private information and changing over time. How to learn on-demand users' truthful location reporting is important for determining optimal UAV deployment in serving all the users fairly. After addressing the truthful UAV-user interaction issue via game theory, we further study the UAV network sustainability for UMS provision by minimizing the energy consumption cost during deployment and seeking UAV-UAV cooperation. Finally, for profit-maximizing purpose, we analyze the cooperative UAVs' deployment, capacity allocation, and dynamic service pricing.

关键词： UAV network sustainability UMS provision local caching path planning delay-sensitive applications future UMS system UAV-UAV cooperation Internet access wireless coverage mobile robots energy storage optimal UAV deployment Internet control engineering computing autonomous aerial vehicles unmanned aerial vehicle dynamic service pricing learning (artificial intelligence) game theory mobile computing UAV-aided mobile services edge computing UMS deployment sustainable service provision resource allocation UAV-user interaction issue on-demand users resource management issues dynamic UMS pricing computation-intensive applications

来源：评论

学校读者我要写书评

暂无评论

TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing 38

TreeVI: Reparameterizable Tree-structured Variational Infere...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Xiao, Junxi Su, Qinliang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Mean-field variational inference (VI) is computationally scalable, but its highly-demanding independence requirement hinders it from being applied to wider scenarios. Although many VI methods that take correlation into account have been proposed, these methods generally are not scalable enough to capture the correlation among data instances, which often arises in applications involving graphs or explicit constraints among instances. In this paper, we developed the Tree-structured Variational Inference (TreeVI)2, which uses a tree to capture the correlation among latent variables in the posterior. We show that samples from the tree-structured posterior can be reparameterized efficiently and parallelly, making its training cost just 2 or 3 times that of VI under the mean-field assumption. To capture correlation with more complicated structure, the TreeVI is further extended to the multiple-tree case. Furthermore, we show that the underlying tree structure can be automatically learned from training data. With experiments on synthetic datasets, constrained clustering, user matching and link prediction, we demonstrate the efficacy of TreeVI in capturing instance-level correlation in posteriors and enhancing the performance of downstream applications. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Causal Graph for Learning Gender Debiased Word Embedding 9

A Causal Graph for Learning Gender Debiased Word Embedding

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Feng, Yanxia Rao, Yanghui Sun Yat-sen University School of Computer Science and Engineering Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (纸本)9798350330076

Word embedding learning is a powerful technique to represent words' rich semantics as low-dimensional vectors, but it may encode harmful social biases. Such biases can leave negative impacts on downstream applications that rely on word embeddings, e.g., text classification and sentiment analysis. In this work, we design a novel approach to debias word embeddings using a causal graph that separates gender and semantic information within words. Our method is theoretically interpretable and can effectively alleviate the issue of gender bias from words in real-world corpora without destructing their semantic meanings. We perform a comprehensive comparison for our proposed approach with existing state-of-the-art techniques using a range of evaluation metrics and tasks, and demonstrate that our method can not only mitigate bias mixed in word embeddings, but also improve their performance on downstream tasks. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：