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

25 篇 会议
9 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

19 篇 工学
- 15 篇 计算机科学与技术...
- 14 篇 软件工程
- 4 篇 控制科学与工程
- 3 篇 信息与通信工程
- 2 篇 材料科学与工程（可...
- 2 篇 电气工程
- 2 篇 生物工程
- 1 篇 冶金工程
- 1 篇 动力工程及工程热...
- 1 篇 电子科学与技术（可...
11 篇 理学
- 5 篇 物理学
- 3 篇 数学
- 3 篇 系统科学
- 2 篇 生物学
- 1 篇 天文学
- 1 篇 统计学（可授理学、...
7 篇 管理学
- 7 篇 管理科学与工程(可...
- 1 篇 工商管理
2 篇 教育学
- 2 篇 教育学
1 篇 经济学
- 1 篇 应用经济学
1 篇 法学
- 1 篇 社会学

主题

3 篇 neural networks
3 篇 computational mo...
2 篇 deep learning
2 篇 predictive model...
2 篇 data models
2 篇 training
2 篇 recurrent neural...
1 篇 random errors
1 篇 table lookup
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 grasping
1 篇 reinforcement le...
1 篇 mobile ad hoc ne...
1 篇 current measurem...

机构

2 篇 college of compu...
2 篇 college of compu...
2 篇 school of comput...
2 篇 shool of compute...
2 篇 shool of informa...
2 篇 haihe lab of ita...
2 篇 state key labora...
2 篇 electronic engin...
2 篇 shool of informa...
2 篇 college of elect...
2 篇 school of comput...
1 篇 key laboratory o...
1 篇 suoao technology...
1 篇 shool of compute...
1 篇 school of comput...
1 篇 the department o...
1 篇 cloud computing ...
1 篇 shool of compute...
1 篇 shool of opto-el...
1 篇 school of comput...

作者

2 篇 zhang shuo
2 篇 yu fei richard
2 篇 zeng peigen
2 篇 ma fei
2 篇 hou haowen
1 篇 jiang chuanqun
1 篇 niyato dusit
1 篇 shrikarti bn
1 篇 dong xiang
1 篇 yuan wei
1 篇 tashi nyima
1 篇 cao zehong
1 篇 vu-le the-anh
1 篇 yu zhiyong
1 篇 yang yifan
1 篇 henggui zhang
1 篇 bn shrikarti
1 篇 takamatsu tomono...
1 篇 zhai hao
1 篇 jie lian

语言

30 篇 英文
3 篇 其他
2 篇 中文

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

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

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

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

Capture, recognition, and visualization of human semantic interactions in meetings

Capture, recognition, and visualization of human semantic in...

引用

8th IEEE International Conference on Pervasive Computing and Communications, PerCom 2010

作者： Yu, Zhiwen Yu, Zhiyong Aoyama, Hideki Ozeki, Motoyuki Nakamura, Yuichi Shool of Computer Science Northwestern Polytechnical University China Academic Center for Computing and Media Studies Kyoto University Japan Graduate School of Science and Technology Kyoto Institute of Technology Japan

ISBN: (纸本)9781424453290

Human interaction is one of the most important characteristics of group social dynamics in meetings. In this paper, we propose an approach for capture, recognition, and visualization of human interactions. Unlike physical interactions (e.g., turn-taking and addressing), the human interactions considered here are incorporated with semantics, i.e., user intention or attitude toward a topic. We adopt a collaborative approach for capturing interactions by employing multiple sensors, such as video cameras, microphones, and motion sensors. A multimodal method is proposed for interaction recognition based on a variety of contexts, including head gestures, attention from others, speech tone, speaking time, interaction occasion (spontaneous or reactive), and information about the previous interaction. A support vector machines (SVM) classifier is used to classify human interaction based on these features. A graphical user interface called MMBrowser is presented for interaction visualization. Experimental results have shown the effectiveness of our approach. ©2009 IEEE.

关键词： Video cameras

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

ON THE EXPECTED DISTORTION BOUND OF DIRECT RANDOM PROJECTION AND ITS APPLICATIONS

ON THE EXPECTED DISTORTION BOUND OF DIRECT RANDOM PROJECTION...

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： YUE-XIAN HOU PENG ZHANG Shool of Computer Science and Technology Tianjin University Tianjin 300072 China

By Johnson and Lindcnstrauss lemma, n points in d-dimensional Euclidean space can be projected down to k=O(ε-2 logn) dimensions while incurring at most 1+ε bi-Lipschitz distortion in pairwise distance. However, most current projection methods requires a k-by-d matrix;and mapping n point takes O(kdn) time. In this paper, a O(dn) complexity random projection method, Directly Random Projection (DKP), is proposed. The performance of DRP is investigated in terms of expected distortion analysis. We prove: 1) an expected distortion bound of DKP;and 2) given moderate conditions, the DRP with appropriate expected distortion can be found in O(1) random time. Furthermore, we propose a simple heuristic to facilitate finding an appropriate DRP. Experimental results on both simulated and real-life data demonstrate DKP can perform quite well and be consistent with our theoretical analysis.

关键词： Dimensionality Reduction Random Projection Ezpected Distortion Analysis

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

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

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

ISBN: (数字)9798331540685

ISBN: (纸本)9798331540692

关键词： Deepfakes Accuracy Computational modeling Transfer learning Neural networks Pressing Signal processing

来源：评论

学校读者我要写书评

暂无评论

PoW and PoS and Related Applications

PoW and PoS and Related Applications

引用

2021 International Conference on Electronic Information Engineering and computer science, EIECS 2021

作者： Ouyang, Zhiqiang Shao, Jie Zeng, Yifeng School of Computer Science and Engineering Sun Yat-sen University Guangzhou China University of Washington Department of Mathematics WA United States Shool of Software Dalian University of Technology Dalian China

ISBN: (纸本)9781665416740

Consensus protocols can help guarantee security and sustainability to maintain the decentralized Blockchain system used in different scenarios and applications due to their different features. There are two main prevalent protocols, Proof of Work (PoW) used in Bitcoin and Proof of Stake (PoS) used in Ethereum. This paper reviews these two consensus protocols, PoW and PoS, and their related improvements and applications. We first introduce the basic concepts, implementations, advantages, and disadvantages of PoW and PoW and make a detailed comparison between these two protocols. We find that though providing security when honest participants are the majority, PoW may lead to excessive power consumption. While PoS is relatively insecure and leads to monopoly (centralization), though energy efficient by discarding complex hash operations. Therefore, some newly proposed consensus protocols have attempted to find a pleasant compromise between these two classic protocols. After a detailed analysis, we investigate the researches related to the defect improvements of PoS and PoW. Finally, we describe various applications of PoS and PoW, including cryptocurrencies and information storage. © 2021 IEEE.

关键词： Blockchain

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：