检索结果-内蒙古大学图书馆

2021 International Conference on Networking and Network Applications, NaNA 2021

作者： Xia, Hong Li, Jianguo Chen, Yanping Lv, Ning Wang, ZhongMin Dong, Qingyi Xi'an University of Posts and Telecommunications School of Computer Science and Technology Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665441582

In order to solve the impact of the temporal and spatial characteristics of traffic on network routing optimization, this paper proposes convolution long-short memory neural network deep reinforcement learning (CLSDRL) model for routing optimization. The CLSDRL model consists of deep deterministic policy gradients (DDPG) deep couple with convolution neural network (CNN) and long-short memory neural network (LSTM). After extracting the spatial and temporal characteristics of network traffic with CNN and LSTM, routing decisions are made with DDPG algorithm. Experiments are conducted under different load intensities, and the network performance is evaluated by the average network delay and packet loss rate, experimental results show that this method can improve significantly network performance. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

StarRec: A Hypergraph-based Framework with Star-Expansion for Multi-Behavior Recommendation

StarRec: A Hypergraph-based Framework with Star-Expansion fo...

引用

2025 SIAM International Conference on data Mining, SDM 2025

作者： Zhang, Wenhan Song, Zijian Wu, Yihuan Deng, Lifang Zhang, Jiandong Bian, Kaigui Cui, Bin School of Computer Science AI Innovation Center National Engineering Laboratory for Big Data Analysis and Applications Peking University China State Key Laboratory of Multimedia Information Processing Peking University China School of Electronics Engineering and Computer Science Peking University China Lazada Group China

In modern recommendation systems, leveraging multiple types of user-item interaction behaviors (e.g., click, add-to-cart, and purchase) presents both advantages and challenges. Recent studies organize multi-behavior data into heterogeneous bipartite graphs and used graph neural networks to learn latent representations. However, these methods struggle to model higher-order interactions and capture complex dependencies across various behaviors. In this paper, we propose a novel graph construction method that converts multi-behavior interactions into dual star-expansion hypergraphs by introducing a new type of node called hypernode. Subsequently, we develop StarRec, a hypergraph-based framework for multi-behavior recommendation. StarRec utilizes a spatial-based two-stage intra-behavior message passing strategy and a cross-behavior propagation layer to accurately and efficiently propagate information, modeling both high-order and cross-behavior relationships through the hypergraphs. This approach yields comprehensive representations that enhance recommendation performance. Experimental results on two real-world datasets demonstrate the superiority of StarRec. Our extensive experiments show that StarRec significantly outperforms state-of-the-art methods while maintaining competitive model scalability. Copyright © 2025 by SIAM.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Research progress on an intelligent production and distribution of the remote sensing products

Research progress on an intelligent production and distribut...

引用

International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2020

作者： Kong, Dezhen Zhao, Jinhuan Tian, Meng Liu, Yang Henan Province Space Information Processing Engineering Laboratory KaifengHenan475004 China Henan Key Laboratory of Big Data Analysis and Processing KaifengHenan475004 China School of Computer and Information Engineering Henan University KaifengHenan475004 China

ISBN: (纸本)9783030539795

Since the amount of remote sensing data that can be obtained every day has reached ten terabytes, the storage and sharing of massive remote sensing data and the construction of product production application architecture have become imminent research topics. The purpose of this study is to build an efficient system that can meet the needs of massive remote sensing data storage, calculation, and distribution. The article elaborates on the latest research progress of cloud service remote sensing data distribution and intelligent production from the four aspects of remote sensing cloud service development, data distribution technology, cloud service technology, and operation mechanism of remote sensing cloud computing processing model, and proposes cloud service remote sensing key issues facing data distribution, and summarize and prospect related research, with a view to promoting the further development of research on cloud service remote sensing data distribution and intelligent production. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Selection Hyper-heuristic based on Q-learning for School Bus Routing Problem

引用

IAENG International Journal of Applied Mathematics 2022年第4期52卷 1页

作者： Hou, Yan-e Gu, Wenbo Wang, Chunxiao Yang, Kang Wang, Yujing Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China

School bus routing problem (SBRP) has been studied for decades. Many successful approaches based on heuristics or metaheuristics have been developed for various SBRP problems. However, developing an effective algorithm for SBRP is still a very challenging task. This paper developed a Q-learning-based selection hyper-heuristic to solve basic and open single-school SBRP problems, which both aim to minimize the total travel distance. The proposed algorithm took a Qlearning algorithm as the high-level strategy to select a lowlevel heuristic from a set of low-level heuristics, which are dependent on the problem domain. The selected low-level heuristic was regarded as an action and then executed to improve the current solution. In each stage of the optimization process, the best action with the best cumulative rewards will be chosen to get better results. The presented algorithm was implemented and some experiments were carried out on some Capacitated vehicle routing problem (CVRP) instances and SBRP benchmark instances. Experiment results on two types of instances demonstrate that our proposed hyper-heuristic algorithm is more competition than existing approaches. © 2022, IAENG International Journal of Applied Mathematics. All Rights Reserved.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Selection Hyper-heuristic Algorithm for the Capacitated Vehicle Routing Problem

引用

IAENG International Journal of Applied Mathematics 2022年第4期52卷 1页

作者： Hou, Yan-e He, Wenwen Wang, Congran Ren, Xinhui Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China

As a classical combinatorial optimization problem, capacitated vehicle routing problem (CVRP) has been continuously studied. However, developing effective approaches for CVRP remains very challengeable. This article presented a two-stage selection hyper-heuristic algorithm for CVRP. The proposed algorithm used the multi-armed bandit algorithm as the high-level selection strategy, which selected a low-level heuristic at each step in the iterative local search framework according to the rewards that it had obtained. For the new neighborhood solution that was found by the selected lowlevel heuristic, a hybrid acceptance strategy was employed to decide whether to accept it. In addition, we also designed a low-level heuristic based on the ruin-and-recreate principle to expand the search space of neighborhood solutions except for the regular neighborhood operators widely used in CVRP. Moreover, the routes of better solutions were also put into a pool of routes. Then a set partitioning procedure model was built based on these routes and then solved by CPLEX to obtain better solution. Computational results on 82 instances demonstrate that the presented algorithm is a satisfactory and competitive approach for CVRP. © 2022, IAENG International Journal of Applied Mathematics. All Rights Reserved.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

A Survey of Text Detection Algorithms in images Based on Deep Learning 4

A Survey of Text Detection Algorithms in Images Based on Dee...

引用

4th International Conference on Natural Language processing, ICNLP 2022

作者： Li, Linna Hu, Cuicui Liu, Ying Xi'an University of Posts and Telecommunications Network Public Opinion Monitoring and Analysis Center Shaanxi Xi'an710121 China Xi'an University of Posts and Telecommunications College Key Laboratory of Electronic Information Application Technology for Scene Investigation Ministry of Public Security Center for Image and Information Processing Shaanxi Xi'an710121 China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

Nowadays, text detection has infiltrated various industries like banking, education, criminal investigation, network public opinion, and more. However, the traditional way of text detection is largely dependent on the characteristics of manual design, which is time-consuming, laborious and inaccuracy. With the emergence of deep learning technology, text detection has already been transformed from text detection in static documents to more practical text detection in natural scenes. To address such challenges as complex background, improper acquisition, and multilingual text in natural scene images, there have been various improved neural network structures constructed. Especially, the performance of text detection in various scenes has been significantly improved. In learning in different scenes are summarized in detail. According to the different text objects in detection, the existing methods are classified into two categories as top-down and bottom-up, and the logic structure, advantages and disadvantages of various algorithms are summarized. In addition, the commonly used data sets and performance evaluation indexes are analyzed and explained, the practical application of text detection in different fields is introduced, and the future trend of research and development are indicated. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-level Cross-modal Feature Alignment via Contrastive Learning towards Zero-shot Classification of Remote Sensing image Scenes

arXiv

引用

arXiv 2023年

作者： Liu, Chun Ma, Suqiang Li, Zheng Yang, Wei Han, Zhigang School of Computer and Information Engineering Henan Key Laboratory of Big Data Analysis and Processing Henan Engineering Laboratory of Spatial Information Processing Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China College of Geography and Environmental Science Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China

Zero-shot classification of image scenes which can recognize the image scenes that are not seen in the training stage holds great promise of lowering the dependence on large numbers of labeled samples. To address the zero-shot image scene classification, the cross-modal feature alignment methods have been proposed in recent years. These methods mainly focus on matching the visual features of each image scene with their corresponding semantic descriptors in the latent space. Less attention has been paid to the contrastive relationships between different image scenes and different semantic descriptors. In light of the challenge of large intra-class difference and inter-class similarity among image scenes and the potential noisy samples, these methods are susceptible to the influence of the instances which are far from these of the same classes and close to these of other classes. In this work, we propose a multi-level cross-modal feature alignment method via contrastive learning for zero-shot classification of remote sensing image scenes. While promoting the single-instance level positive alignment between each image scene with their corresponding semantic descriptors, the proposed method takes the cross-instance contrastive relationships into consideration, and learns to keep the visual and semantic features of different classes in the latent space apart from each other. Extensive experiments have been done to evaluate the performance of the proposed method. The results show that our proposed method outperforms state of the art methods for zero-shot remote sensing image scene classification. All the code and data are available at github https://***/masuqiang/MCFA-Pytorch. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

CR-Famba: A Frequency-Domain Assisted Mamba for Thin Cloud Removal in Optical Remote Sensing imagery

引用

IEEE Transactions on Multimedia 2025年

作者： Liu, Jiao Pan, Bin Shi, Zhenwei Nankai University TKLNDST College of Computer Science Tianjin300350 China Nankai University School of Statistics and Data Science KLMDASR LEBPS LPMC Tianjin300071 China Beihang University Image Processing Center School of Astronautics the State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China

Optical remote sensing images are inevitably affected by cloud cover. To remove clouds from optical remote sensing images, a series of deep learning-based thin cloud removal methods have been developed. However, these methods have not explored the long-range modeling ability of state space models in optical remote sensing image thin cloud removal. In this paper, we propose a frequency-domain assisted Mamba for thin cloud removal, which is called CR-Famba. In CR-Famba, to better extract global and local features of images, we design a frequency-domain assisted state space layer (FDA-SSL). The FDA-SSL consists of two core components: residual state space block (RSSB) and frequency domain detail enhancement block (FDDEB). The RSSB utilizes the visual state space module (VSSM) to extract long-range dependencies of images from a spatial perspective while adding convolutional layers to overcome local pixel forgetting. Due to the rich detailed information of remote sensing images, we present FDDEB equipped with discrete wavelet transform (DWT) to supplement the extracted local information from the frequency domain perspective. We conduct experiments on different types of cloud-containing datasets, and the results show that our method can recover images with clearer texture details compared to other methods. https://***/Lab-PANbin/ © 2025 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization

Efficient Document Retrieval by End-to-End Refining and Quan...

引用

2022 Conference on Empirical Methods in Natural Language processing, EMNLP 2022

作者： Qiu, Zexuan Su, Qinliang Yu, Jianxing Si, Shijing School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-Sen University Guangzhou China School of Economics and Finance Shanghai International Studies University China

Efficient document retrieval heavily relies on the technique of semantic hashing, which learns a binary code for every document and employs Hamming distance to evaluate document distances. However, existing semantic hashing methods are mostly established on outdated TFIDF features, which obviously do not contain lots of important semantic information about documents. Furthermore, the Hamming distance can only be equal to one of several integer values, significantly limiting its representational ability for document distances. To address these issues, in this paper, we propose to leverage BERT embeddings to perform efficient retrieval based on the product quantization technique, which will assign for every document a real-valued codeword from the codebook, instead of a binary code as in semantic hashing. Specifically, we first transform the original BERT embeddings via a learnable mapping and feed the transformed embedding into a probabilistic product quantization module to output the assigned codeword. The refining and quantizing modules can be optimized in an end-to-end manner by minimizing the probabilistic contrastive loss. A mutual information maximization based method is further proposed to improve the representativeness of codewords, so that documents can be quantized more accurately. Extensive experiments conducted on three benchmarks demonstrate that our proposed method significantly outperforms current state-of-the-art baselines. © 2022 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge

Answering Subjective Induction Questions on Products by Summ...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yufeng Zhang Meng-Xiang Wang Jianxing Yu School of Artificial Intelligence Sun Yat-sen University Zhuhai Guangdong Key Laboratory of Big Data Analysis and Processing China China National Institute of Standardization China Pazhou Lab Guangzhou China

This paper proposes a new task in the field of Answering Subjective Induction Question on Products (SUBJPQA). The answer to this kind of question is non-unique, but can be interpreted from many perspectives. For example, the answer to ‘whether the phone is heavy’ has a variety of different viewpoints. A satisfied answer should be able to summarize these subjective opinions from multiple sources and provide objective knowledge, such as the weight of a phone. That is quite different from the traditional QA task, in which the answer to a factoid question is unique and can be found from a single data source. To address this new task, we propose a three-steps method. We first retrieve all answer-related clues from multiple knowledge sources on facts and opinions. The implicit commonsense facts are also collected to supplement the necessary but missing contexts. We then capture their relevance with the questions by interactive attention. Next, we design a reinforcement-based summarizer to aggregate all these knowledgeable clues. Based on a template-controlled decoder, we can output a comprehensive and multi-perspective answer. Due to the lack of a relevant evaluated benchmark set for the new task, we construct a large-scale dataset, named SupQA, consisting of 48,352 samples across 15 product domains. Evaluation results show the effectiveness of our approach.

关键词：

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

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

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：