检索结果-内蒙古大学图书馆

作者： Wang, Linbo Tan, Li Fang, Xianyong Guo, Yanwen Wan, Shaohua MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei China National Key Lab for Novel Software Technology Nanjing University Nanjing China School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan China

The transformational and spatial proximities are important cues for identifying inliers from an appearance based match set because correct matches generally stay close in input images and share similar local transformations. However, most existing approaches only check one type of them or both types consecutively with manually set thresholds, and thus their matching accuracy and flexibility in handling large-scale images are limited. In this paper, we present an efficient clustering based approach to identify match inliers with both proximities simultaneously. It first projects the putative matches into a joint transformational-spatial space, where mismatches tend to scatter all around while correct matches gather together. A mode-seeking process based on joint kernel density estimation is then proposed to obtain significant clusters in the joint space, where each cluster contains matches mapping the same object across images with high accuracy. Moreover, kernel bandwidths for measuring match proximities are adaptively set during density estimation, which enhances its applicability for matching different images. Experiments on three standard datasets show that the proposed approach delivers superior performance on a variety of feature matching tasks, including multi-object matching, duplicate object matching and object retrieval. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Clustering Density estimation Feature matching Mode-seeking

来源：评论

学校读者我要写书评

暂无评论

Joint QoS Prediction for Web Services based on Deep Fusion of Features

引用

IEEE Transactions on Network and Service Management 2023年 1-1页

作者： Ding, Linghang Liu, Jianxun Kang, Guosheng Xiao, Yong Cao, Buqing Hunan Provincial Key Lab. for Services Computing and Novel Software Technology and School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

In order to solve the problem of insufficient accuracy of Web service QoS prediction, a joint QoS prediction method for Web services based on the deep fusion of features was proposed by considering the hidden environmental preference information in QoS and the common characteristics of multi-class QoS. QoS data was modeled as user-service bipartite graph at first, then, multi-component graph convolution neural network was used for feature extraction and mapping, and weighted fusion method was used for the same dimensional mapping of multi-class of QoS features. Subsequently, the attention factor decomposition machine was used to extract the first-order features, second-order interactive features and high-order interactive features of the mapped feature vector. Finally, the results of each part were combined to achieve the joint QoS prediction. The experimental results show that the proposed method is superior to the existing QoS prediction methods in terms of root mean square error (RMSE) and average absolute error (MAE). IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training 24

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Lang...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availab.lity of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly availab.e image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are availab.e at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation 41

Hyperbolic Geometric Latent Diffusion Model for Graph Genera...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright 2024 by the author(s)

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Optimal Joint Trajectory and Caching with Graph-based Federated Knowledge Distillation in UAV-assisted Networks

Optimal Joint Trajectory and Caching with Graph-based Federa...

引用

Networks, Communications and intelligent computing (NCIC), International Conference on

作者： Gerald Tietaa Maale Noble Arden Elorm Kuadey Guolin Sun Guisong Liu National Key Lab. for Intelligent Collaborative Computing Intelligent Term. Key Lab. of Sichuan Prov. Yibin China School of Computer Science and Engineering UESTC Chengdu China School of Computing and Artificial Intelligence Southwestern University of Finance and Economics Chengdu China

ISBN: (数字)9798350371949

ISBN: (纸本)9798350371956

The use of unmanned aerial vehicles (UAVs) as mobile cache nodes can enhance data traffic throughput and reduce user latency in urban areas. However, jointly optimizing UAV trajectories for efficient content delivery and onboard caching strategies presents significant challenges stemming from the tight coupling between these two problems, as well as issues related to the non-independent and non-identically distributed (non-IID) nature of real-world content popularity and wireless channel dynamics. To address these challenges, we propose KDLMGCN, a deep learning framework that employs graph convolutional networks with LSTM to capture intricate relationships between UAV locations and ground user content demand patterns. Through empirical evaluation, we demonstrate that KDLMGCN surpasses benchmark methods in terms of convergence, cache hit rates, and average transmission, with real-world trajectory dataset and Zipf-based content popularity data.

关键词： Knowledge engineering Wireless communication Training Computational modeling Urban areas Autonomous aerial vehicles Trajectory

来源：评论

学校读者我要写书评

暂无评论

Concrete Structural Crack Damage Classification Using Nonlinear Dimension Reduction and Broad Learning System

Concrete Structural Crack Damage Classification Using Nonlin...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Bingshu Lin, Jia Zhuang, Xiaodong Zhang, Guanghui Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi'an China Shenzhen University Guangdong Key Lab. of Intelligent Info. Processing and Shenzhen Key Laboratory of Media Security Shenzhen China School of Computer Science and Technology Shandong University Qingdao China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9781665410205

Concrete structural crack damage classification is of importance for road safety. This paper proposes a new method based on broad neural network for crack damage classification in concrete structures. It includes three stages. Firstly, a pre-trained deep neural network is used to extract the features from crack images. Secondly, principal component analysis is used to project the retrieved features from high dimensions to low dimensions. Thirdly, broad learning system is employed to predict the classification using the low-dimensional features. Experimental results demonstrate that this method reduces the model's training time and improves classification accuracy. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Not all diffusion model activations have been evaluated as discriminative features 24

Not all diffusion model activations have been evaluated as d...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is availab.e at https://***/Darkbblue/generic-diffusion-feature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interactive Web API Recommendation via Exploring Mashup-API Interactions and Functional Description

Interactive Web API Recommendation via Exploring Mashup-API ...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Wanjun Chen Qiqi Chen Jiexun Shen Guosheng Kang Jianxun Liu Buqing Cao Lihong Zhang School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology HNUST Xiangtan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the advance of service computing technology, the number of Web APIs has risen dramatically over the Internet. Users tend to use Web APIs to achieve their business needs. However, it is difficult for users to find and select the desirable ones due to the plethora of Web APIs. To address this problem, some collab.rative filtering-based Web API recommendation methods have been proposed even though their performance is still far from satisfaction, since they only rely on Mashup-API interactions and feature interactions are not considered in the recommendation model. To further improve the recommendation performance, this paper proposes an interactive Web API recommendation method via exploring both Mashup-API interactions and functional description documents of Mashups and Web APIs. Specifically, LightGCN is employed to derive the node representations for the Mashup-API interaction graph, and BERT model is used for the text representations of functional description documents. Furthermore, the two presentations of both the Mashup and Web API are concatenated as the input of ANFM (Attentional Neural Factorization Machine) model, in which low and high-order feature interactions are fully modeled and the weights of feature interactions are trained by attention mechanism. Solid experiments are conducted over a real-world dataset and the experimental results indicate that the proposed method outperforms the baseline methods.

关键词： Attention mechanisms Federated learning Mashups Computational modeling Semantics Neural networks Service computing

来源：评论

学校读者我要写书评

暂无评论

Multi-view Hypergraph-based Self-supervised Learning Model for Web API Recommendation

Multi-view Hypergraph-based Self-supervised Learning Model f...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Jiexun Shen Dongfan Li Wanjun Chen Yong Xiao Guosheng Kang Jianxun Liu Zhenlian Peng School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology HNUST Xiangtan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

With the rapid development of service computing technology, how to recommend the desirable Web APIs to developers from the large number of APIs is a challenge. The traditional methods based on collab.rative filtering are limited by data sparsity. With the support of multi-dimensional relational feature modeling, graph neural network-based methods are proposed to mitigate data sparsity, but their convolution nature may amplify the noise effect. Therefore, how to simultaneously reduce the impact of sparsity and noisy data has been an open question in the field of API recommendation. To address the problem, this paper proposes a self-supervised learning method based on multi-view hypergraph for Web API recommendation. First, the Mashup-API interaction graph is transformed into a hypergraph, and the hyperedges are used as intermediate hubs to transfer messages between nodes, maintaining the global collab.ration effect between Mashup and API nodes. Then, a multi-view strategy is adopted to generate embeddings of Mashups and APIs through information fusion, by which recommendation probability is derived by dot product between the embeddings of Mashups and Web APIs. To train the model parameters effectively, a self-supervised learning method is used to reduce the effect of noisy data to improve the embeddings. Extensive experiments are conducted on a real-world dataset, and the experimental results show that the proposed model outperforms the baselines.

关键词： Knowledge engineering Mashups Noise Neural networks Collab.ration Service computing Self-supervised learning Feature extraction Data models Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Crawling and Exploring RESTful Web APIs from RapidAPI 17th

Crawling and Exploring RESTful Web APIs from RapidAPI

引用

CCF 17th International Conference on Service Science, CCF ICSS 2024

作者： Li, Wen Ren, Hongshuai Nie, Yamei Liu, Zihao Kang, Guosheng Liu, Jianxun Peng, Zhenlian School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology HNUST Xiangtan China

ISBN: (纸本)9789819757596

RapidAPI serves as a marketplace and management platform that integrates a wide range of Web APIs, offering developers access to a rich pool of API resources. More and more researchers are delving into ways to maximize the value created by leveraging these resources. Thus, acquiring the Web API data and knowing the details is of significance for researchers and ordinary users. In this paper, we propose the methodology of crawling Web APIs from RapidAPI (https://***/hub) and provide rich visualizations and statistical analysis for the crawled dataset. The crawling code and the crawled dataset are open for public access (https://***/intelligentServicelab.RESTful-API-Crawler) so that researchers and users can acquire them with no effort. Moreover, the use cases of RESTful Web APIs are provided as a usage reference for users and developers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Web crawler

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：