检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Huang, Zhewei Huang, Ailin Hu, Xiaotao Hu, Chen Xu, Jun Zhou, Shuchang Megvii Technology China Nankai University China Guangdong Provincial Key Laboratory of Big Data Computing CUHK Hong Kong

The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolution (VSR). However, facing the challenge of the additional temporal dimension and scale inconsistency, most existing STVSR methods are complex and inflexible in dynamically modeling different motion amplitudes. In this work, we find that choosing an appropriate processing scale achieves remarkable benefits in flow-based feature propagation. We propose a novel Scale-Adaptive Feature Aggregation (SAFA) network that adaptively selects sub-networks with different processing scales for individual samples. Experiments on four public STVSR benchmarks demonstrate that SAFA achieves state-of-the-art performance. Our SAFA network outperforms recent state-of-the-art methods such as TMNet [83] and VideoINR [10] by an average improvement of over 0.5dB on PSNR, while requiring less than half the number of parameters and only 1/3 computational costs. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Graph Computation Model with Communication Equilibrium 15th

A Two-Stage Graph Computation Model with Communication Equil...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Dong, Yanmei Chen, Rongwang Guo, Kun College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China College of Mathematics and Computer Science Wuyi University Wuyishan Fujian354300 China Digital Fujian Tourism Big Data Institute Wuyishan Fujian354300 China

ISBN: (纸本)9789811625398

Distributed graph computing aims at performing in-depth analysis on large networks in a parallel manner. Iterative communication computation is an important model to perform graph analysis. Moreover, high-efficiency iterative communication computation is necessary for assuring the quality of graph partitioning. Many strategies to improve graph computing are usually based on the hypothesis of single communication iteration which focuses on the optimization of load balance in a single graph partitioning and the improvement of parallel granularity or communication manners. However, a graph in the real-world usually requires complex communication iterations to achieve good analysis results, which often have the problems of data and communication tilting and low analysis efficiency. In this paper, we propose a two-stage graph computing model with communication equilibrium (TSMCE). The model employs a communication-equilibrated graph partitioning strategy (CEGP) for load balancing and a two-stage graph computing mode (TS) to reduce the crossing-partition communication. With the change of graph density, various factors such as load balancing, communication balancing, cross-partition transmission traffic, communication delay, and convergence speed can always maintain an efficient balance. The experiments conducted on the real-world datasets show that the communication-equilibrated graph partitioning strategy can divide a graph with high quality compared with Hash and Metis. Besides, the overall performance of our two-stage graph computing model with communication equilibrium is higher than that of the BSP model. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

MedX-Net: Hierarchical Transformer with Large Kernel Convolutions for 3D Medical Image Segmentation

MedX-Net: Hierarchical Transformer with Large Kernel Convolu...

引用

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

作者： Lu, Lin Zou, Qingzhi Key Laboratory of Computing Power Network and Information Se-curity Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Due to the exceptional performance of Transform-ers in 2D medical image segmentation, recent work has also introduced them into 3D medical segmentation tasks. For instance, Swin UNETR and other hierarchical Transformers have reintroduced prior knowledge from several convolutional networks, further enhancing the volume segmentation capabilities of models. The efficacy of these hybrid methodologies is primarily attributed to the substantial quantity of parameters and the nonlocal self-attention mechanism with a large receptive field. We argue that the behavior of these methods' large receptive fields can be simulated by employing fewer parameters through the utilization of depth-wise convolutions with large kernel. Within this manuscript, we introduce a lightweight volume segmentation model called MedX-Net, which uses convolutional network modules to simulate hierarchical Transformers for robust volume segmentation. Firstly, inspired by the hierarchical Transformer module of Swin UNETR, we investigate large-kernel depth-wise convolutions with different sizes to achieve a reduced model parameter count while maintaining a large global receptive field. Secondly, we replace the multilayer perceptron (MLP) in the hierarchical Transformer module with Inverted Bottleneck with Depthwise Convolution Enhancement(DWCE) to improve model performance with fewer activation and normalization layers, further reducing the parameter count. We validate the effectiveness and efficiency of our model for volume segmentation on three public datasets: Synapse, BTCV and ACDC. On the Synapse dataset, compared to Swin UNETR, our model achieves an improvement from 83.48% to 87.21% in Dice score. Compared to the result of 86.57% achieved by nnFormer, our model achieves superior performance while reducing the model parameter count by 64%. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Application of Multi-objective Evolutionary Algorithm in E-Commerce Recommendation System

Application of Multi-objective Evolutionary Algorithm in E-C...

引用

Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), International Conference on

作者： Siyu Huang Junjie Liu Daxin Zhu Danlin Cai School of Mathmatics and Computer Science Quanzhou Normal University Quanzhou China Network Information Center Quanzhou Normal University Quanzhou China Fujian Provincial Key Laboratory of Data-Intensive Computing Quanzhou China

ISBN: (数字)9781728181431

ISBN: (纸本)9781728181448

Traditional recommendation methods often have incomplete understandings of recommendation evaluation indicators. They are limited to the accuracy of recommendation, but often ignore the diversity, novelty, coverage and other indicators. Therefore, the recommendation system should use more evaluation indicators to meet personalized demands of users so as to obtain satisfactory results. This is closely related to the problem of multi-objective optimization. This paper describes the mathematical expression of the multi-objective optimization problem and uses NSGA-II algorithm to test its accuracy and diversity indexes of Netflix dataset. The experimental results show that NSGA-II algorithm can meet multi-objective requirements of the recommendation system and the experimental results are satisfactory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Knowledge Graph Completion Based on Gated Attention Unit 29

Sequence-to-Sequence Knowledge Graph Completion Based on Gat...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Yi, Fengge Wei, Xiumei Liu, Xiaojing Jiang, Xuesong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

ISBN: (纸本)9798350330717

We present GauKGT5, a sequence-to-sequence model proposed for knowledge graph completion (KGC). Our research extends the KGT5 model, a recent sequence-to-sequence link prediction (LP) model. GauKGT5 takes advantage of textual characteristics inherent in the knowledge graph, exhibiting a small model size. However, KGT5's proficiency in link prediction necessitates the ensemble with a knowledge graph embedding model, which itself poses challenges due to its substantial size and expense. By integrating the Gated Attention Unit into the KGT5 model and directly applying it to the encoder-decoder structure, we achieve improved contextual dependency capturing within the sequence, resulting in enhanced prediction accuracy, accelerated training speed, and enhanced computational efficiency. At the same time, we introduce parallel computing as a means to enhance the efficiency of model training and inference within the XPU distributed computing environment. © 2023 IEEE.

关键词： gated attention unit knowledge graph completion sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Last-X-Generation Archiving Strategy for Multi-Objective Evolutionary Algorithms 13

Last-X-Generation Archiving Strategy for Multi-Objective Evo...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Shu, Tianye Nan, Yang Shang, Ke Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China Southern University of Science and Technology Shenzhen518055 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

ISBN: (纸本)9798350308365

For evolutionary multi-objective optimization algorithms (EMOAs), an external archive can be utilized for saving good solutions found throughout the evolutionary process. Recent studies showed that a solution set selected from an external archive is usually superior to the final population. That is, the incorporation of an external archive improves the performance of EMOAs. However, the computation time for maintaining an external archive is long, especially when the archive size is large. To solve this issue, a simple archiving strategy is to save all solutions generated in the last several generations. In this paper, we examine this archiving strategy for three representative EMOAs on artificial test problems (Minus-DTLZ and WFG) and real-world problems (RE). Our results show that archiving the last several generations clearly improves the performance of EMOAs without severely increasing the computation time. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs 39

CLDG: Contrastive Learning on Dynamic Graphs

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Xi'an Jiaotong University Department of Computer Science and Technology China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Xi'an Jiaotong University Department of Distance Education China Beihang University School of Software China Beihang University Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9798350322279

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

4K-Resolution Photo Exposure Correction at 125 FPS with ~8K Parameters

4K-Resolution Photo Exposure Correction at 125 FPS with ~8K ...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yijie Zhou Chao Li Jin Liang Tianyi Xu Xin Liu Jun Xu Nankai University Tianjin University Lappeenranta-Lahti University of Technology Guangdong Provincial Key Laboratory of Big Data Computing CUHK Shenzhen

The illumination of improperly exposed photographs has been widely corrected using deep convolutional neural networks or Transformers. Despite with promising performance, these methods usually suffer from large parameter amounts and heavy computational FLOPs on high-resolution photographs. In this paper, we propose extremely light-weight (with only ~8K parameters) Multi-Scale Linear Transformation (MSLT) networks under the multi-layer perception architecture, which can process 4K-resolution sRGB images at 125 Frame-Per-Second (FPS) by a Titan RTX GPU. Specifically, the proposed MSLT networks first decompose an input image into high and low frequency layers by Laplacian pyramid techniques, and then sequentially correct different layers by pixel-adaptive linear transformation, which is implemented by efficient bilateral grid learning or 1 × 1 convolutions. Experiments on two benchmark datasets demonstrate the efficiency of our MSLTs against the state-of-the-arts on photo exposure correction. Extensive ablation studies validate the effectiveness of our contributions. The code is available at https://***/Zhou-Yijie/MSLTNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computation Offloading Algorithm Based on Deep Reinforcement Learning and Multi-Task Dependency for Edge computing 25th

Computation Offloading Algorithm Based on Deep Reinforcemen...

引用

25th International Computer Symposium on New Trends in Computer Technologies and Applications, ICS 2022

作者： Lin, Tengxiang Lin, Cheng-Kuan Chen, Zhen Cheng, Hongju College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Department of Computer Science National Yang Ming Chiao Tung University Hsinchu300 Taiwan

ISBN: (纸本)9789811995811

Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, significantly reducing service latency. In this paper, we aim to divide the task into several sub-tasks through its inherent interrelation, guided by the idea of high concurrency for synchronization, and then offload sub-tasks to other edge servers so that they can be processed to minimize the cost. Furthermore, we propose a DRL-based Multi-Task Dependency Offloading Algorithm (MTDOA) to solve challenges caused by dependencies between sub-tasks and dynamic working scenes. Firstly, we model the Markov decision process as the task offloading decision. Then, we use the graph attention network to extract the dependency information of different tasks and combine Long Short-term Memory (LSTM) with Deep Q Network (DQN) to deal with time-dependent problems. Finally, simulation experiments demonstrate that the proposed algorithm boasts good convergence ability and is superior to several other baseline algorithms, proving this algorithm’s effectiveness and reliability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks 8th

Location Recommendations Based on Multi-view Learning and ...

引用

8th China National Conference on Big data and Social computing, BDSC 2023

作者： Chen, Junxin Lin, Kuijie Chen, Xiang Wang, Xijun Hsu, Terng-Yin School of Electronics and Information Technology Sun Yat-sen University Guangzhou511400 China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518000 China Department of Computer Science National Chiao Tung University Hsinchu30013 Taiwan

ISBN: (纸本)9789819939244

Personalized location recommendation plays a very important role in location-based social networks, from which both users and service providers can benefit from. In spite of the significant endeavors that have been made towards acquiring knowledge on location attributes and user inclinations, it is still faced with serious data sparsity problems. In this paper, we propose a personalized location recommendation model based on graph neural networks with multi-view learning to obtain effective representations of mobile users and locations from different heterogeneous graphs. We also design an attention-enhanced mechanism to explore the implicit interactions between mobile users and locations themselves. Conducting adequate comparative experiments on two real-world telecom datasets has demonstrated that our model achieves superior performance. Additionally, our model has been proven effective in addressing data sparsity issues. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Location

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：