检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

28 篇 会议
6 篇 期刊文献

馆藏范围

34 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

20 篇 工学
- 16 篇 计算机科学与技术...
- 14 篇 软件工程
- 5 篇 控制科学与工程
- 3 篇 信息与通信工程
- 2 篇 机械工程
- 2 篇 仪器科学与技术
- 1 篇 动力工程及工程热...
- 1 篇 电气工程
- 1 篇 电子科学与技术（可...
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 测绘科学与技术
- 1 篇 生物工程
9 篇 管理学
- 8 篇 管理科学与工程(可...
- 1 篇 工商管理
- 1 篇 图书情报与档案管...
7 篇 理学
- 3 篇 数学
- 3 篇 系统科学
- 1 篇 物理学
- 1 篇 生物学
1 篇 经济学
- 1 篇 应用经济学
1 篇 教育学
- 1 篇 教育学
1 篇 文学
- 1 篇 新闻传播学

主题

3 篇 neural networks
2 篇 computational mo...
2 篇 predictive model...
2 篇 computers
2 篇 training
2 篇 recurrent neural...
1 篇 random errors
1 篇 table lookup
1 篇 structured singu...
1 篇 computer science
1 篇 surveys
1 篇 tools
1 篇 consumer behavio...
1 篇 metals
1 篇 reliability
1 篇 learning systems
1 篇 pseudospectra
1 篇 data integrity
1 篇 grasping
1 篇 reinforcement le...

机构

2 篇 college of compu...
2 篇 school of comput...
2 篇 department of co...
2 篇 shool of compute...
2 篇 shool of informa...
2 篇 state key labora...
2 篇 electronic engin...
2 篇 shool of informa...
2 篇 college of elect...
2 篇 department of th...
2 篇 school of comput...
1 篇 key laboratory o...
1 篇 suoao technology...
1 篇 school of comput...
1 篇 the department o...
1 篇 school of comput...
1 篇 shool of opto-el...
1 篇 the shool of eng...
1 篇 shool of compute...
1 篇 shool of compute...

作者

2 篇 yu fei richard
2 篇 zeng peigen
2 篇 ma fei
2 篇 hou haowen
1 篇 niyato dusit
1 篇 shrikarti bn
1 篇 yuan wei
1 篇 cao zehong
1 篇 vu-le the-anh
1 篇 michiels w.
1 篇 bn shrikarti
1 篇 changbin yu
1 篇 wagenknecht t.
1 篇 zhai hao
1 篇 jie lian
1 篇 chang su
1 篇 li yichen
1 篇 sujithra kanmani...
1 篇 fengchao peng
1 篇 you xinge

语言

31 篇 英文
3 篇 其他
1 篇 中文

检索条件"机构=Shool of Computer Engineering and Science"

共 34 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models 31

VisualRWKV: Exploring Recurrent Neural Networks for Visual L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shool of Information Technology Carleton University Canada

ISBN: (纸本)9798891761964

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: https://***/howard-hou/VisualRWKV. © 2025 Association for Computational Linguistics.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Fruits Classification and Analysis in Hyperspectral Imaging Using Deep Convolutional Neural Networks 6th

Fruits Classification and Analysis in Hyperspectral Imaging ...

引用

6th International Conference on Advanced Informatics for Computing Research, ICAICR 2023

作者： Verma, Divyanshu Vijayarajan, V. Rajkumar, S. Ramesh Pathy, M. Shool of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India School of Bio Sciences and Technology Vellore Institute of Technology Tamil Nadu Vellore632014 India

ISBN: (纸本)9783031840616

Hyperspectral imaging (HSI) emerges as a highly efficient means of information retention, particularly when leveraging the power of deep learning. The intricate task of non-destructively identifying rotten fruits is addressed through HSI, offering a non-invasive method for data collection that significantly streamlines the sorting process using advanced algorithms. Deep learning, employing neural network methodologies, facilitates the exploration of the intricate connection between spatial and spectral contexts within the data. The HSI system captures the wavelength information of refracted, reflected, and absorbed light across multiple bands. To address noise introduced by the machinery, a Standard Normal Variate (SNV) filter is applied, resulting in a refined dataset represented as a hyperspectral cube (3D). The workflow involves the utilization of an image pre-training convolutional neural network (CNN) on the collected dataset, subsequently fine-tuned to serve as a robust classifier. In the proposed model, a substantial majority of the dataset (70%) is dedicated to training the neural network, with the remaining portion (30%) reserved for the validation process. The findings demonstrate that this analysis approach, leveraging the CNN algorithm, yields remarkably accurate results (>90%) and proves to be highly effective in discerning fruit quality. The presented methodology showcases a promising synergy between hyperspectral imaging and deep learning, offering a reliable solution for non-destructive fruit quality assessment. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Fake Detection using Transfer Learning: A Comparative study of Multiple Neural Networks

Deep Fake Detection using Transfer Learning: A Comparative s...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Abhineswari, M. Charan, Kurupati Sai Bn, Shrikarti Kanmani R, Sujithra Shool of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331540685

With the proliferation of sophisticated AI techniques, the creation and dissemination of deep fake images and videos have emerged as a pressing concern in today's digital landscape. Deep fake technology employs advanced machine learning algorithms to manipulate or synthesize realistic-looking media, often with malicious intent. This study evaluates the effectiveness of various pre-trained deep learning models using transfer learning for detecting deep fake images on the Face Forensics++ dataset. The models considered include MobileN etV2, ResN et50, Inception V3, EfficientN et, Xception, NASNetMobile, and a Custom CNN. Accuracies obtained from these models are compared to assess their performance in distinguishing between real and fake images. With the highest performance in MobileNetV2 with 89% followed by ResNet50 with 83 % and other models. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Embodied Contrastive Learning with Geometric Consistency and Behavioral Awareness for Object Navigation 24

Embodied Contrastive Learning with Geometric Consistency and...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Chen, Bolei Kang, Jiaxu Zhong, Ping Liang, Yixiong Sheng, Yu Wang, Jianxin Shool of Computer Science and Engineering Central South University Changsha China

ISBN: (纸本)9798400706868

Object Navigation (ObjcetNav), which enables an agent to seek any instance of an object category specified by a semantic label, has shown great advances. However, current agents are built upon occlusion-prone visual observations or compressed 2D semantic maps, which hinder their embodied perception of 3D scene geometry and easily lead to ambiguous object localization and blind exploration. To address these limitations, we present an Embodied Contrastive Learning (ECL) method with Geometric Consistency (GC) and Behavioral Awareness (BA), which motivates agents to actively encode 3D scene layouts and semantic cues. Driven by our embodied exploration strategy, BA is modeled by predicting navigational actions based on multi-frame visual images, as behaviors that cause differences between adjacent visual sensations are crucial for learning correlations among continuous visions. The GC is modeled as the alignment of behavior-aware visual stimulus with 3D semantic shapes by employing unsupervised contrastive learning. The aligned behavior-aware visual features and geometric invariance priors are injected into a modular ObjectNav framework to enhance object recognition and exploration capabilities. As expected, our ECL method performs well on object detection and instance segmentation tasks. Our ObjectNav strategy outperforms state-of-the-art methods on MP3D and Gibson datasets, showing the potential of our ECL in embodied navigation. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Personalized Privacy-Preserving Information Fusion in Mobile Crowdsensing 20

Personalized Privacy-Preserving Information Fusion in Mobile...

引用

20th IEEE International Symposium on Parallel and Distributed Processing with Applications, 12th IEEE International Conference on Big Data and Cloud Computing, 12th IEEE International Conference on Sustainable Computing and Communications and 15th IEEE International Conference on Social Computing and Networking, ISPA/BDCloud/SocialCom/SustainCom 2022

作者： Feng, Zheqi Peng, Tao Wang, Guojun Guan, Kejian Guangzhou University Shool of Computer Science and Cyber Engineering Guangzhou510006 China

ISBN: (纸本)9781665464970

In mobile crowdsensing (MCS), information fusion is necessary to obtain data aggregation results. In information fusion, most of the existing personalized mechanisms only consider meeting the personalized requirements of data collectors and rarely consider the potential personalized requirements of data users. Furthermore, how to provide personalized data aggregation results for data users with different data quality requirements has not been addressed. This paper proposes a personalized privacy-preserving information fusion (P3IF) mechanism based on the personalized sampling mechanism in the MCS. P3IF provides personalized data aggregation results for data users with different data quality requirements while ensuring personalized privacy protection for data collectors. Specifically, we design a personalized privacy-preserving information fusion scheme based on the personalized differential privacy mechanism. Considering on the privacy requirements of the data collectors, we conduct personalized privacy sampling on the raw data from the data collectors and obtain a subset of sensing data. According to the data quality requirements of data users and the quality of each data, the obtained subset is sampled for personalized data quality requirements, and the final data set is obtained. Simulation experiments verify the feasibility and effectiveness of P3IF. © 2022 IEEE.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

Efficient-Learning Grasping and Pushing in Dense Stacking via Mask Function and Pixel Overlap Rate 7

Efficient-Learning Grasping and Pushing in Dense Stacking vi...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Lian, Jie Jiang, Juncheng Qiu, Chaochao Pan, Qinghui Dong, Yongxiang Wang, Zhao Wang, Dong Dalian University of Technology School of Control Science and Engineering Dalian China University of Science and Technology Liaoning Shool of Computer Science and Software Engineering China

ISBN: (纸本)9798350363173

In the field of robotic grasping, grasping tightly stacked objects is a formidable challenge. The presence of non-target objects significantly increases the risk of grasping failure. To solve this problem, the aim is to take action while grasping, reduce clutter, and effectively complete grasping tasks. Based on deep reinforcement learning, the Efficient Learning Grasping(ELG) framework is proposed that integrates pushing actions alongside grasping to efficiently pick up objects from cluttered environments with reduced training time. However, in the process of grasping, the agent is rewarded only when the grasp is successful, so the data collection is extremely inefficient and spends a lot of time on the training of grasping strategy. In our work, two strategies are proposed to improve the training efficiency. First, two mask functions are introduced as prior knowledge to enable the agent to focus on more meaningful regions while ignoring some unnecessary regions, aiming at effective learning. Second, The Pixel Overlap Rate (POR) is introduced to quantify the environment clutter level, and set a new push action reward function based on the POR. The implementation of the above ideas in a simulation environment and transferred the learned models to the real world and verified them in practice. Compared with existing method, our method improves the training efficiency of the initial algorithm while having a higher success rate of grasping. Detailed grasping video at https://***/CqtSvaVl60M. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An IRVS based human-machine interaction system using head-and-eye coordination movement

An IRVS based human-machine interaction system using head-an...

引用

2009 International Workshop on Intelligent Systems and Applications, ISA 2009

作者： Sheng, He Yu, Lei Yong-xin, Ma Yun, Meng Lei, Huang School of Instrument Science and Opto-electronic Engineering Beihang University Beijing China School of Mechanical and Electronic Control Engineering Beihang University Beijing Jiaotong University Beijing China Shool of Computer Engineering and Science Beijing China Shool of Mechanical engineering and Automation Beihang University Beijing China

ISBN: (纸本)9781424438945

In this paper we introduce an eye-gaze tracking system using the changes of the user's head position. The system presents a new optical structure. In this structure we propose an algorithm based on the projection of the line of sight. With this algorithm, we can say goodbye to complicated arithmetic operations, and improve the system's response time, which indeed, ensures synchronization. We modify the algorithm so the system can match eye features of Asian users. Test of the system shows it has high accuracy and a good real-time response, which makes the users feel more comfortable when they are using this system. © 2009 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Decoupling of Direction and Length for Cumulative Step Size Adaptation 17

Decoupling of Direction and Length for Cumulative Step Size ...

引用

17th International Conference on Computational Intelligence and Security, CIS 2021

作者： Zhang, Shuo Li, Zhenhua Yang, Detian Wang, Shuo Cai, Xinye School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Shool of Information Technology and Engineering Tianjin University of Technology and Education Tianjin China

ISBN: (纸本)9781665494892

Covariance matrix adaptation evolution strategy (CMA-ES) is a successful evolutionary algorithm for continuous optimization. The cumulative step size adaptation (CSA) is the default method for adapting the step size in CMA-ES and achieves remarkable performance in practice. It follows the idea of exploiting the correlations between search directions in consecutive generations. In this paper, we investigate the effects of the update directions and the length in CSA. We find that sampling from uniform sphere distribution can yield comparative performance to the default setting, and normalizing the update direction in CSA does not hurt the performance. Further, the CSA with actual search direction cannot perform well, and the correlation between the default direction of CSA and the actual search direction is rather small. It indicates that CSA does not accumulate the actual search directions. We argue that the step size and the covariance matrix should be updated by decoupled search information, and accumulating the actual search direction results in inferior performance due to the same update direction in two evolution paths for the step size and covariance matrix updates. © 2021 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Thinking on Design and Realization of Source Code Online Evaluation System

Thinking on Design and Realization of Source Code Online Eva...

引用

2013 2nd International Conference on Social science and Education(ICSSE 2013)

作者： Yuansong Li Software Engineering Department Shool of Computer Science Sichuan University of Science and Engineering

The traditional evaluation procedure is mainly manual evaluation in practical teaching field. Such work is very complicated. With the constant development and improvement of computer technology, there are high requirements for the programming level of workers and such traditional evaluation method has a series of problems. To better impel students to learn programming and effectively ease the burden of teachers, this paper designs a source code online evaluation system which can effectively improve the evaluation level.

关键词： Source code, Evaluation, System, Design

来源：评论

学校读者我要写书评

暂无评论

Analysis of image stitching error based on scale invariant feature transform and random sample consensus 12

Analysis of image stitching error based on scale invariant f...

引用

12th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2015

作者： Shuang, Dou Cai, Hua Yang, Yong Tailin, Han Xue, Menghan School of Computer Engineering Changchun University of Science and Technology Changchun China College of Electronic and Information Engineer Changchun University of Science and Technology Changchun China Electronic Engineering Shool Beijing University of Posts and Telecommunications Changchun China

ISBN: (纸本)9781467376822

This article introduced the process of image stitching based on SIFT and RANSAC. It was pointed out that the reliability calculation of the RANSAC algorithm is based on an idealized assumption which does not hold. The false assumption will lead to the instability of image stitching results, especially in multi-map or panorama situations. To solve the problem, this paper presents a strategy to limit the range of randomly points selecting. Experiments show that the strategy can effectively reduce the effect caused by random errors, and obtain more stable image stitching result. © 2015 IEEE.

关键词： Random errors

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共4页 << < 1 2 3 4 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：