检索结果-内蒙古大学图书馆

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Wangzhang, Suhui Yang, Ruizhang Gu, Rong Li, Bo Liu, Dingjin Wang, Zhaokang Nanjing University State Key Laboratory for Novel Software Technology China Sinopec Geophysical Research Institute China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China

ISBN: (纸本)9798350329223

The reverse-time migration (RTM) imaging algorithm, which is used for complex underground structure analysis, is known as one of the current mainstream method of high-precision seismic imaging. Nowadays, as the fast development of seismic data acquisition technology, there exists large amount of seismic data. Thus, the requirement for the efficient computation of the reverse-time migration (RTM) imaging algorithms over large-scale data have been increased greatly. To address this problem, in this paper, we propose a distributed reverse-time migration imaging algorithm based on the widely-used Spark platform first. Based on that, we design and implement a RTM computation solution based on Spark and GPU with several optimizations, including pre-shuffle&caching and load balancing. We also analyze the fault tolerance capability of the proposed distributed algorithm. We evaluate the proposed methods on the typical three-dimensional wavefild benchmark dataset. Experimental results show that the performance of the Spark based reverse-time migration imaging algorithm can scale up near linearly with computing nodes. In addition, the GPU+Spark based version has significant performance improvement on execution efficiency over the Spark-based algorithm. Moreover, the proposed optimization strategies also take effect. In addition, the method proposed in this paper has been applied in the real-world environment of one of the top oil exploration companies world wide, and has achieved significant improvement under the premise of the algorithm correctness guarantee. © 2023 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Learned Video Compression With Refined Adaptive Flow Pyramid And Coordinate-Aware Attention

Learned Video Compression With Refined Adaptive Flow Pyramid...

引用

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

作者： Huang, Qian Liu, Wenting Li, Xin Wang, Yiming College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China

ISBN: (纸本)9798350368741

In video compression, motion estimation and motion compensation are critical for achieving efficient encoding. Although the commonly used SpyNet and bilinear interpolation have contributed in improving the compression efficiency, they still have limitations. SpyNet often loses details and fails to fully utilize the feature extraction capabilities of deep networks. Furthermore, bilinear interpolation inherently attenuates high-frequency information, leading to frame blurring and distortion. In this paper, we propose a novel video compression algorithm. To overcome the limitations of SpyNet, we propose a refined adaptive flow pyramid network. This network uses a multi-scale feature pyramid to capture more details. Moreover, we use an iterative cost volume refinement engine that improves the feature representation of the network and iteratively improve the accuracy of motion estimation. In addition, to overcome the limitation of bilinear interpolation, we propose a coordinate-aware attention module, which captures more high-frequency information to improve the accuracy of motion compensation. Experimental results show that our method outperforms VTM-13.2 (LDP) in terms of PSNR. © 2025 IEEE.

关键词： coordinate network cross attention flow pyramid learned video compression

来源：评论

学校读者我要写书评

暂无评论

A survey on model-based reinforcement learning

引用

Science China(Information Sciences) 2024年第2期67卷 59-84页

作者： Fan-Ming LUO Tian XU Hang LAI Xiong-Hui CHEN Weinan ZHANG Yang YU National Key Laboratory for Novel Software Technology Nanjing University Polixir. ai Department of Computer Science and Engineering Shanghai Jiao Tong University

Reinforcement learning(RL) interacts with the environment to solve sequential decision-making problems via a trial-and-error approach. Errors are always undesirable in real-world applications, even though RL excels at playing complex video games that permit several trial-and-error attempts. To improve sample efficiency and thus reduce errors, model-based reinforcement learning(MBRL) is believed to be a promising direction, as it constructs environment models in which trial-and-errors can occur without incurring actual costs. In this survey, we investigate MBRL with a particular focus on the recent advancements in deep RL. There is a generalization error between the learned model of a non-tabular environment and the actual environment. Consequently, it is crucial to analyze the disparity between policy training in the environment model and that in the actual environment, guiding algorithm design for improved model learning, model utilization, and policy training. In addition, we discuss the recent developments of model-based techniques in other forms of RL, such as offline RL, goal-conditioned RL, multi-agent RL, and meta-RL. Furthermore,we discuss the applicability and benefits of MBRL for real-world tasks. Finally, this survey concludes with a discussion of the promising future development prospects for MBRL. We believe that MBRL has great unrealized potential and benefits in real-world applications, and we hope this survey will encourage additional research on MBRL.

关键词： reinforcement learning model-based reinforcement learning planning model learning model learning with reduced error model usage

来源：评论

学校读者我要写书评

暂无评论

Revisiting Unsupervised Domain Adaptation Models: A Smoothness Perspective 16th

Revisiting Unsupervised Domain Adaptation Models: A Smoothne...

引用

16th Asian Conference on computer Vision, ACCV 2022

作者： Wang, Xiaodong Zhuo, Junbao Zhang, Mengru Wang, Shuhui Fang, Yuejian School of Software and Microelectronics Peking University Beijing China Key Laboratory of Intelligent Information Processing Indian Institute of Computer Technology CAS Beijing China MEGVII Technology Beijing China

ISBN: (纸本)9783031263507

Unsupervised Domain Adaptation (UDA) aims to leverage the labeled source data and unlabeled target data to generalize better in the target domain. UDA methods utilize better domain alignment or carefully-designed regularizations to increase the discriminability of target features. However, most methods focus on directly increasing the distance between cluster centers of target features, i.e., enlarging inter-class variance, which intuitively increases the discriminability of target features and is easy to implement. However, due to intra-class variance optimization being under-explored, there are still some samples of the same class are prone to be classified into several classes. To handle this problem, we aim to equip UDA methods with the high smoothness constraint. We first define the model’s smoothness as the predictions similarity within each class, and propose a simple yet effective technique LeCo (impLicit smoothness Constraint) to promote the smoothness. We construct the weak and strong "views" of each target sample and enforce the model predictions of these two views to be consistent. Besides, a new uncertainty measure named Instance Class Confusion conditions the consistency is proposed to guarantee the transferability. LeCo implicitly reduces the model sensitivity to perturbations for target samples and guarantees smaller intra-class variance. Extensive experiments show that the proposed technique improves various baseline approaches by a large margin, and helps yield comparable results to the state-of-the-arts on four public datasets. Our codes are publicly available at https://***/Wang-Xiaodong1899/LeCo_UDA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A Programming Language Learning Service by Linking Stack Overflow with Textbooks

A Programming Language Learning Service by Linking Stack Ove...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Wu, Jiawei Sun, Yanchun Zhang, Jiaqi Zhou, Yuqi Huang, Gang Ministry of Education Key Laboratory of High Confidence Software Technologies China Peking University School of Computer Science Beijing China Peking University School of Software and Microelectronics Beijing China National Key Laboratory of Data Space Technology and System China

ISBN: (纸本)9798350304855

Before software developers actually start coding, an essential requirement is to be proficient in a programming language. However, as an important learning resource, programming language textbooks usually contain much about syntax and semantics of a programming language, but little about pragmatics, which is highly relevant with practical skills in solving real-world problems using programming languages. This makes it difficult for learners to transfer knowledge from textbooks to *** solve this problem, this paper proposes a programming language learning service, utilizing abundant development knowledge in Stack Overflow (SO) Q&A posts as the pragmatics knowledge of programming languages to make up for the shortage of pragmatics knowledge in textbooks. To link SO Q&A posts with textbooks, this paper first proposes a deep learning classification model to recognize SO posts containing development knowledge. Second, to align filtered SO posts with programming language learning processes, this paper proposes a weakly supervised link approach to matching SO posts with chapters and sections of textbooks. The feature of weak supervision ensures that the approach can be easily extended to other textbooks. Based on these modules above, this paper implements the programming language learning service in the form of a Chrome plugin. We conduct experiments and user study. Their results demonstrate the effectiveness, scalability and stability of the service. © 2023 IEEE.

关键词： Textbooks

来源：评论

学校读者我要写书评

暂无评论

DNS Covert Channel Attack Detection Based on Spatio-Temporal Feature Fusion 22

DNS Covert Channel Attack Detection Based on Spatio-Temporal...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： You, Wei Zhao, Chunlei Shan, Chao Dong, Guozhong Yu, Jie Guan, Yong Tianjin University of Technology Tianjin Key Laboratory of Intelligent Computing and Software New Technology Tianjin China Coordination Center of China Hubei Branch of National Computer Network Emergency Response Technical Team HuBei China Pengcheng Laboratory Department of New Networks Shenzhen China

ISBN: (纸本)9798331509712

An increasing number of Advanced Persistent Threat (APT) organizations are utilizing DNS (Domain Name System) covert channels to evade network intrusion detection systems and establish private authoritative servers for remote attacks. However, current detection models for DNS covert channels often have poor performance and limited generalization ability. To address these challenges, we propose a DNS covert channel attack detection method based on spatiotemporal feature fusion. This method combines the Interaction timing sequence features of DNS traffic with the spatial statistical features of domain names, and constructs a detection model called ConvSLSTM, which integrates a Convolutional Neural Network (CNN) with a stacked Long Short Term Memory (LSTM) network. CNN extracts local spatial features from traffic, while stacked LSTM captures Interaction timing sequence features, significantly improving detection accuracy. This article uses three typical public datasets for experiments, which contain a total of 440000 DNS covert channel attack data. Comparative experiments show that our method is significantly superior to existing methods and exhibits stronger generalization ability in detecting DNS covert channel attacks constructed by unknown tools. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Deep Semantic and Attentive Network for Unsupervised Video Summarization

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2022年第2期18卷 1-21页

作者： Zhong, Sheng-Hua Lin, Jingxu Lu, Jianglin Fares, Ahmed Ren, Tongwei College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical Engineering Computer Systems Engineering Program Faculty of Engineering at Shoubra Benha University Cairo Egypt State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

With the rapid growth of video data, video summarization is a promising approach to shorten a lengthy video into a compact version. Although supervised summarization approaches have achieved state-of-the-art performance, they require frame-level annotated labels. Such an annotation process is time-consuming and tedious. In this article, we propose a novel deep summarization framework named Deep Semantic and Attentive Network for Video Summarization (DSAVS) that can select the most semantically representative summary by minimizing the distance between video representation and text representation without any frame-level labels. Another challenge associated with video summarization tasks mainly originates from the difficulty of considering temporal information over a long time. Long Short-Term Memory (LSTM) performs well for temporal dependencies modeling but does not work well with long video clips. Therefore, we introduce a self-attention mechanism into our summarization framework to capture the long-range temporal dependencies among the frames. Extensive experiments on two popular benchmark datasets, i.e., SumMe and TVSum, show that our proposed framework outperforms other state-of-the-art unsupervised approaches and even most supervised methods. © 2022 Association for Computing Machinery.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Versatile Low-Light Enhancement Module for Improved Workpiece Detection 13

A Versatile Low-Light Enhancement Module for Improved Workpi...

引用

13th International Conference of Information and Communication technology, ICTech 2024

作者： Yin, ZhenYu Lin, DaHeng Wang, XiaoHui Xin, Qi Zhang, XueMei Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang110168 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China Liaoning Key Laboratory of Domestic Industrial Control Platform Technology on Basic Hardware & Software China School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110168 China

ISBN: (纸本)9798350376258

This study presents a versatile Low-Light Enhancement Module (LLEM) to enhance object detection models, particularly for workpieces in challenging lighting conditions. The LLEM seamlessly integrates into existing models, addressing low-light challenges through a denoising branch, a global branch, and a Structural Perception loss for image quality improvement. The denoising branch utilizes Residual Denoising Modules to effectively reduce noise and preserve low-level features. Meanwhile, the global branch focuses on color recovery and gamma correction. Experimental results show YOLOv3+LLEM significantly improves detection performance, achieving a mAP increase from 88.0% to 91.9%. This enhancement, especially with the introduction of Structural Perception loss, maintains computational efficiency, validating its practicality for industrial workpiece detection in low-light conditions. ©2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Chen, Chenglizhao Liu, Xinyu Song, Mengke Li, Luming Yuan, Shaojiang Yu, Xu Pang, Shanchen Qingdao Institute of Software College of Computer Science and Technology China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software China State Key Laboratory of Chemical Safety China

Video anomaly detection methods are mainly classified into two categories based on their primary feature types: appearance-based and action-based. Appearance-based methods rely on low-level visual features like color, texture, and shape, learning patterns specific to training scenes. While effective in familiar settings, they struggle with unknown or altered scenes due to poor generalization and limited understanding of action-scene relationships. In contrast, action-based methods focus on detecting action anomalies but often overlook contextual scene associations, leading to misjudgments (e.g., running on a street being deemed normal without considering scene context). To overcome these limitations, we propose a novel decoupling-based anomaly detection architecture (DecoAD). Its core lies in the decoupling and interweaving of scenes and actions, enabling explicit modeling of their complex relationships. By reconstructing these interactions using knowledge graphs, DecoAD achieves a deeper understanding of behaviors and contexts. This design ensures strong performance in both known and unknown scenarios, significantly enhancing generalization. To evaluate its effectiveness in dynamic scenes and its ability to handle scene-related anomalies, we introduce UFSR, the first video anomaly detection dataset featuring dynamic scenes and scene-related anomalies. DecoAD supports fully-supervised, weakly-supervised, and unsupervised settings, improving AUC on UBnormal by 1.1%, 3.1%, and 2.1% in fully-supervised, weakly-supervised, and unsupervised settings, and on UFSR by 1.2% and 8.2% in weakly-supervised and unsupervised settings. The source code and datasets are available at: https://***/liuxy3366/DecoAD. © 1991-2012 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Application Testing Method based on Multi-attribute Fusion 9

Reinforcement Learning Application Testing Method based on M...

引用

9th International Conference on Dependable Systems and Their Applications, DSA 2022

作者： Cai, Lizhi Wang, Jin Chen, Mingang Wang, Jilong School of Information Science and Engineering East China University of Science and Technology Shanghai China Shanghai Development Center of Computer Software Technology Shanghai Key Laboratory of Computer Software Testing & Evaluating Shanghai China

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Reinforcement learning has been successfully applied to assess the reliability of applications, but the existing testing methods based on reinforcement learning have the problems of invalid interactive widgets and difficult training, resulting in low testing efficiency. In order to solve these problems, this paper proposes a lightweight application automation testing method of deep reinforcement learning based on multi-attribute fusion (MARTesting). First, the invalid widgets are removed by the difference operation of the attribute sets of the current and previous state, then the attributes of all widget elements on the page are abstracted into state as the input of the neural network, and a state is accurately determined by fusing the position and text information of page elements, finally combine the novelty of the state and the execution frequency of the action as a reward function. The experimental results on six open source applications show that the MARTesting method proposed in this paper has achieved significant improvements in code coverage and branch coverage compared with existing methods. © 2022 IEEE.

关键词： Reinforcement learning

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：