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

1,917 篇 会议
84 篇 期刊文献
12 篇 学位论文
4 册 图书

馆藏范围

2,017 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,166 篇 工学
- 946 篇 计算机科学与技术...
- 566 篇 软件工程
- 400 篇 信息与通信工程
- 240 篇 电气工程
- 61 篇 控制科学与工程
- 51 篇 电子科学与技术（可...
- 38 篇 光学工程
- 33 篇 仪器科学与技术
- 22 篇 机械工程
- 22 篇 生物医学工程（可授...
- 19 篇 生物工程
- 13 篇 网络空间安全
- 11 篇 化学工程与技术
- 11 篇 交通运输工程
- 10 篇 航空宇航科学与技...
- 9 篇 建筑学
255 篇 理学
- 113 篇 数学
- 110 篇 物理学
- 33 篇 统计学（可授理学、...
- 27 篇 系统科学
- 22 篇 生物学
- 12 篇 化学
207 篇 管理学
- 140 篇 图书情报与档案管...
- 72 篇 管理科学与工程(可...
- 34 篇 工商管理
143 篇 医学
- 136 篇 临床医学
- 11 篇 基础医学(可授医学...
33 篇 教育学
- 32 篇 教育学
28 篇 法学
- 21 篇 社会学
10 篇 文学
- 9 篇 新闻传播学
5 篇 经济学
4 篇 军事学
2 篇 艺术学

主题

356 篇 multimedia syste...
154 篇 multimedia commu...
154 篇 streaming media
136 篇 content based re...
83 篇 internet
77 篇 bandwidth
73 篇 image retrieval
71 篇 information retr...
70 篇 content manageme...
65 篇 quality of servi...
63 篇 multimedia
62 篇 multimedia datab...
51 篇 computer science
51 篇 indexing
51 篇 delay
50 篇 data mining
50 篇 algorithm design...
49 篇 feature extracti...
46 篇 resource managem...
46 篇 mobile communica...

机构

5 篇 tsinghua univ de...
5 篇 department of el...
4 篇 ibm thomas j. wa...
4 篇 school of comput...
4 篇 beijing universi...
3 篇 institute for in...
3 篇 suv
3 篇 ibm corp thomas ...
3 篇 distributed mult...
3 篇 univ chinese aca...
3 篇 integrated media...
3 篇 packetvideo finl...
3 篇 department of ma...
3 篇 univ milano bico...
3 篇 open univ catalo...
3 篇 school of electr...
3 篇 fit dept informa...
3 篇 computer school ...
3 篇 university of br...
3 篇 tsinghua univ gr...

作者

7 篇 hellwagner herma...
5 篇 li cs
5 篇 smith jr
5 篇 shu-ching chen
5 篇 smith john r.
4 篇 van de walle r
4 篇 sun lifeng
4 篇 de sutter r
4 篇 liu zhu
4 篇 hermann hellwagn...
4 篇 li y
4 篇 lerouge s
4 篇 zeng wj
4 篇 christodoulakis ...
4 篇 r. luling
4 篇 mylonas phivos
4 篇 schedl markus
4 篇 van de walle rik
4 篇 ebrahimi touradj
4 篇 wang zhi

语言

1,988 篇 英文
14 篇 其他
13 篇 中文
1 篇 葡萄牙文
1 篇 土耳其文

检索条件"任意字段=Conference on Multimedia Content Access - Algorithms and Systems"

共 2017 条记录，以下是151-160 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：

Image Captioning with Reinforcement Learning

Image Captioning with Reinforcement Learning

引用

Computer Vision and Machine Intelligence (CVMI), International conference on

作者： Anand Verma Saurabh Agarwal K.V. Arya Ivan Petrlik Roberto Esparza Ciro Rodriguez Department of Information Technology ABV-IIITM Gwalior Madhya Pradesh India Department of Computer Science and Engineering Multimedia and Information Security Research Group ABV-Indian Institute of Information Technology and Management Gwalior India Faculty of Industrial and Systems Engineering National University Federico Villarreal Lima Peru Faculty of Systems Engineering and Informatics National University Mayor de San Marcos

Image captioning involves generating a natural language description that accurately represents the content and context of an image. To achieve this, image captioning utilises various machine learning techniques and fields, such as computer vision and natural language processing. In the field of image captioning, a lot of advances have been made with encoder-decoder models and reinforcement learning algorithms. However, there are still problems of imbalance between testing and training, as reinforcement learning only handles single comparator metrics such as CIDEr, SPICE, and BLEU and could not perform better in multiple metrics at once. Which is why a lack of diversity can be seen in generated captions. This idea proposes a general technique for collaborative updating that can bridge the gap between evaluation measures and test metrics to produce captions that are more human-like. To increase the precision of image captions, the approach involves using a compiled reward system that considers multiple evaluation metrics to compare the generated sentence with the provided sentences. We will evaluate the model's performance and the reward updating process on standard datasets like MS COCO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallel Asynchronous Stochastic Dual Coordinate Descent algorithms for High Efficiency and Stable Convergence

Parallel Asynchronous Stochastic Dual Coordinate Descent Alg...

引用

29th Euromicro International conference on Parallel, Distributed and Network-Based Processing (PDP)

作者： Chen, Yung-Chen Liu, Pangfeng Wu, Jan-Jan Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei Taiwan Natl Taiwan Univ Grad Inst Networking & Multimedia Taipei Taiwan Acad Sinica Inst Informat Sci Taipei Taiwan

ISBN: (纸本)9781665414555

Parallel asynchronous stochastic dual coordinate descent algorithm (PASSCoDe) is an efficient method to train linear models in multi-core shared-memory systems. PASSCoDe enjoys a good speedup when the number of threads is less than 8 on sparse datasets, i.e., the percentage of nonzero elements in the training data is relatively small. However, due to the memory conflict and delayed parameter access problem in parallel execution, it often diverges or does not converge to the best accuracy as a serial dual coordinate descent algorithm does. In this paper, we propose two algorithms - Adaptive Hybrid algorithm and Lazy-Sync algorithm, to overcome the convergence issues in parallel execution. Both algorithms use the current accuracy to guide the execution and strike a balance between accuracy and efficiency. Experimental results indicate that both algorithms converge to the same high accuracy as a sequential program does on all datasets tested except on an extremely small one. On the other hand, PASSCoDe sometimes converges to a less accurate value or does not converge at all on some datasets. Our methods also outperform PASSCoDe-Fix, an improved version of PASSCoDe, in stable convergence, execution speed, and scalability. For example, the Adaptive llybrid algorithm runs up to 2.8 times faster than PASSCoDe-Fix, and the Lazy-Sync algorithm runs 11 times faster than PASSCoDe-Fix on dataset covt ype with 10 threads.

关键词： Machine learning parallel dual coordinate descent asynchronous algorithm linear model support vector machine

来源：评论

学校读者我要写书评

暂无评论

Social Inclusion in Curated Contexts: Insights from Museum Practices 22

Social Inclusion in Curated Contexts: Insights from Museum P...

引用

5th ACM conference on Fairness, Accountability, and Transparency, FAccT 2022

作者： Huang, Han-Yin Liem, Cynthia C. S. Multimedia Computing Group Delft University of Technology Netherlands

ISBN: (纸本)9781450393522

Artificial intelligence literature suggests that minority and fragile communities in society can be negatively impacted by machine learning algorithms due to inherent biases in the design process, which lead to socially exclusive decisions and policies. Faced with similar challenges in dealing with an increasingly diversified audience, the museum sector has seen changes in theory and practice, particularly in the areas of representation and meaning-making. While rarity and grandeur used to be at the centre stage of the early museum practices, folk life and museums' relationships with the diverse communities they serve become a widely integrated part of the contemporary practices. These changes address issues of diversity and accessibility in order to offer more socially inclusive services. Drawing on these changes and reflecting back on the AI world, we argue that the museum experience provides useful lessons for building AI with socially inclusive approaches, especially in situations in which both a collection and access to it will need to be curated or filtered, as frequently happens in search engines, recommender systems and digital libraries. We highlight three principles: (1) Instead of upholding the value of neutrality, practitioners are aware of the influences of their own backgrounds and those of others on their work. By not claiming to be neutral but practising cultural humility, the chances of addressing potential biases can be increased. (2) There should be room for situational interpretation beyond the stages of data collection and machine learning. Before applying models and predictions, the contexts in which relevant parties exist should be taken into account. (3) Community participation serves the needs of communities and has the added benefit of bringing practitioners and communities together. © 2022 Owner/Author.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Enhancing motion deblurring in high-speed scenes with spike streams 23

Enhancing motion deblurring in high-speed scenes with spike ...

引用

Proceedings of the 37th International conference on Neural Information Processing systems

作者： Shiyan Chen Jiyuan Zhang Yajing Zheng Tiejun Huang Zhaofei Yu School of Computer Science Peking University and National Key Laboratory for Multimedia Information Processing Peking University School of Computer Science Peking University and National Key Laboratory for Multimedia Information Processing Peking University and Institute for Artificial Intelligence Peking University

Traditional cameras produce desirable vision results but struggle with motion blur in high-speed scenes due to long exposure windows. Existing frame-based deblurring algorithms face challenges in extracting useful motion cues from severely blurred images. Recently, an emerging bio-inspired vision sensor known as the spike camera has achieved an extremely high frame rate while preserving rich spatial details, owing to its novel sampling mechanism. However, typical binary spike streams are relatively low-resolution, degraded image signals devoid of color information, making them unfriendly to human vision. In this paper, we propose a novel approach that integrates the two modalities from two branches, leveraging spike streams as auxiliary visual cues for guiding deblurring in high-speed motion scenes. We propose the first spike-based motion deblurring model with bidirectional information complementarity. We introduce a content-aware motion magnitude attention module that utilizes learnable mask to extract relevant information from blurry images effectively, and we incorporate a transposed cross-attention fusion module to efficiently combine features from both spike data and blurry RGB images. Furthermore, we build two extensive synthesized datasets for training and validation purposes, encompassing high-temporal-resolution spikes, blurry images, and corresponding sharp images. The experimental results demonstrate that our method effectively recovers clear RGB images from highly blurry scenes and outperforms state-of-the-art deblurring algorithms in multiple settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLM-MHR: A LLM-Augmented Multimodal Hashtag Recommendation Algorithm

LLM-MHR: A LLM-Augmented Multimodal Hashtag Recommendation A...

引用

IEEE International conference on Web Services (ICWS)

作者： Zhijie Tan Yuzhi Li Xiang Yuan Shengwei Meng Weiping Li Tong Mo School of Software and Microelectronics Peking University Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

The recommendation of suitable hashtags for mi-croposts encompassing multimodal content stands as a pivotal challenge for numerous Social Networking Service (SNS) applications such as Instagram, Weibo, etc. The accuracy of multimodal hashtag recommendation algorithms relies heavily on the comprehension of multimodal information, user historical information, and the reasoning ability based on such information. However, most previous works have not effectively utilized both historical and additional information simultaneously. Large Language Models (LLMs) learn a vast amount of implicit knowledge during the pre-training stage, which can serve as potential knowledge bases while also possessing strong reasoning abilities. Therefore, LLMs can provide additional information to help understand the micropost content and infer suitable hashtags with strong reasoning ability. However, introducing LLMs for multimodal hashtag recommendation faces three main challenges. Firstly, LLMs require an efficient modality alignment module to accept a multimodal input. Secondly, LLMs are highly sensitive to input order, while utilizing user historical information requires accepting multiple historical samples, necessitating the design of a robust historical information processing module to eliminate the influence of input order. Thirdly, fine-tuning LLMs entails substantial computational overheads, necessitating the reduction of additional trainable parameters. To address the first two challenges, this paper designs an efficient modality alignment module capable of processing multiple historical samples, simultaneously addressing the sensitivity of LLMs to input order changes. To tackle the third challenge, a hybrid prompt learning approach utilizing both soft and hard prompts is proposed to achieve parameter-efficient fine-tuning of LLMs. Finally, a LLM-augmented Multimodal Hashtag Recommendation algorithm (LLM-MHR) is implemented. Comprehensive experiments on the representative dataset

关键词： Sensitivity Web services Social networking (online) Large language models Computational modeling Knowledge based systems Information processing Cognition Web sites multimedia communication

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Sleep Control in 5G and Beyond Radio access Networks: An Overview

Deep Reinforcement Learning for Sleep Control in 5G and Beyo...

引用

International Wireless Communications and Mobile Computing conference, IWCMC

作者： Nessrine Trabelsi Rihab Maaloul Lamia Chaari Fourati Wael Jaafar Laboratory of Signals systeMs aRtificial intelligence and neTworkS – Digital Research Center of Sfax Sfax Tunisia Higher Institute of Computer Science of Mahdia (ISIMa) University of Monastir Tunisia Higher Institute of Computer Science and Multimedia in Sfax (ISIMS) University of Sfax Tunisia Department of Software and IT Engineering École de technologies supérieure (ÉTS) Montreal Canada

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The advent of 5G and beyond networks is envisioned to support lower latency, higher data rates, and wider connectivity than previous cellular network generations. However, given the denser deployment of base stations (BSs) to accommodate such improvements, this results inevitably in a significant and unsustainable increase in the network’s energy consumption. Sleep Control (SC), which allows switching off some BS hardware components during light-traffic time, is considered a viable solution for greener and more energy-efficient Radio access Networks (RAN). However, the optimization of SC is a highly challenging large-scale network combinatorial problem that depends on dynamic wireless channel conditions and varying traffic demands with stringent Quality-of-Service (QoS) requirements. Driven by the benefits and efficiency of Deep Reinforcement Learning (DRL), which has been successfully applied to multiple wireless network optimization problems, this paper investigates DRL approaches addressing sleep control in 5G and beyond RAN. To this end, we propose a taxonomy to classify the related literature. Then, we provide an overview of the different components of the Markov Decision Process (MDP) modeling the sequential decision-making of sleep control and the applied DRL algorithms. Finally, we highlight the main challenges in existing works and suggest novel strategies to address them.

关键词： 5G mobile communication Wireless networks Taxonomy Decision making Quality of service Switches Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Rabin-Karp Algorithm and Winnowing Algorithm for Document Abstraction Similarity Detection

Performance Comparison of Rabin-Karp Algorithm and Winnowing...

引用

International conference on Informatics, multimedia, Cyber and Information System (ICIMCIS)

作者： Anggit Dwi Hartanto Yoga Pristyanto Andy Saputra Eli Pujastuti Atik Nurmasani Ika Asti Astuti Department of Information System Universitas Amikom Yogyakarta Yogyakarta Indonesia Master Program of Informatics Universitas Amikom Yogyakarta Yogyakarta Country

ISBN: (纸本)9781665473286

Plagiarism is one of the actions that have the potential to occur in the academic environment. A real example is the plagiarism of assignments during the lecture process. One of the efforts to prevent plagiarism is to use a system that has been developed in recent years. However, the price of subscribing to the system for a period is quite high. Therefore, we need a plagiarism detection system that everyone can access for free. In developing the system, of course, modeling must be done. Two popular algorithms are often used to detect word similarity: Rabin-Karp and Winnowing. In this study, a performance comparison was made between Rabin-Karp and Winnowing. Comparisons were made using the same dataset of 30 abstraction data from scientific publications. Based on the research, the performance of the Rabin-Karp algorithm and the Winnowing algorithm is almost as good. However, based on the two evaluation parameters used by the Winnowing algorithm, it produces more similarity scores than Rabin-Karp. The same thing also applies to the evaluation of processing time. Winnowing is slightly longer than Rabin-Karp. With the results of this comparison, it can be concluded that if you want a model sensitive to similarity, then Winnowing is recommended. However, if processing time is the target, it is recommended to use Rabin-Karp. In future research, tuning the parameter values of k or n in the Rabin-Karp and Winnowing algorithms is recommended. In addition, it is also recommended to experiment with another distance scoring.

关键词： Plagiarism multimedia systems Informatics Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

Interaction Based Credibility Analysis of News on Facebook Using Machine Learning Methodologies

Interaction Based Credibility Analysis of News on Facebook U...

引用

International IEEE conference on Signal-Image Technologies and Internet-Based System

作者： Sadia Sharmin Sudipa Saha Tasin Hoque Khandaker Abrar Nadib Computer Science and Engineering Bangladesh University of Engineering and Technology

Fake news and its dissemination are growing more popular as social media becomes more pervasive in our daily lives and Facebook users are particularly vulnerable. Numerous studies on detecting fake news have already been published. However, a study focusing on fake news in low resource languages like Bengali propagated through Facebook is rare due to data extraction challenges. In this paper, we work with fake news in the Bengali language and used various supervised machine learning algorithms to classify Facebook posts as fake, real, or satire and found XGBoost to generate the best outputs. Instead of the content, we trained our model with the interaction data of the posts to make it resilient against adversarial attacks. We observed that ensemble methods perform well with such social media metrics.

关键词： Measurement Machine learning algorithms Video on demand Social networking (online) multimedia Web sites Focusing Market research

来源：评论

学校读者我要写书评

暂无评论

In-Class Vehicle Categorization Using Standard Convolutional Neural Networks Via Fiber Bragg Grating Sensor Array 19

In-Class Vehicle Categorization Using Standard Convolutional...

引用

19th IEEE International conference on Emerging eLearning Technologies and Applications, ICETA 2021

作者： Kamencay, Patrik Benedikovic, Daniel Dubovan, Jozef Markovic, Miroslav Dado, Milan University of Žilina Faculty of Electrical Engineering and Information Technology Department of Multimedia and Information-Communication Technologies Žilina01026 Slovakia

ISBN: (纸本)9781665421027

Internet of Things is a key innovation that will shape future systems, especially in future data-hungry applications. this mostly includes sensing, communication, biomedicine as well as smart buildings, military or automotive 4.0 industry, among other surging application areas. Internet of Things leverages the fact that inherently different physical systems are combined together, alongside with modern machine learning algorithms. To date, the IoT technology is ubiquitous for automotive domain due to its profound impact on vehicle classification, instant on-road control, or smart traffic management. In this work, we evaluate a fiber Bragg grating based dataset by using established open-access convolutional neural networks (AlexNet, GoogLeNet, and ResNet-50), enabling an effective vehicle categorization. In particular, we show that individual fiber Bragg grating technological platform can offer good detection accuracies for passing vehicles using standard convolutional neural networks. In this case, we obtained classification precisions between 34%-62% for AlexNet, 51%-77% for GoogleNet and 57%-78% for ResNet-50 architectures. Those detection accuracy levels are sufficiently high to pave a promising way for effective car categorization using passive fiber Bragg grating technology coupled with standard and open-access neural networks. © 2021 IEEE.

关键词： Fiber Bragg gratings

来源：评论

学校读者我要写书评

暂无评论

Breaking the Cycle: Countering Popularity Bias for Diverse content Discovery

Breaking the Cycle: Countering Popularity Bias for Diverse C...

引用

International conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Brandon Weaver Melody Moh Teng-Sheng Moh Department of Computer Science San Jose State University San Jose CA USA

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

The ways most people consume media have become very much driven by some pre-set algorithms. It is increasingly important to examine the outcome of these artificial intelligence (AI) models and ensure that any potentially dangerous long-term effects are addressed before they significantly impact our society. Popularity bias is one of these potentially harmful impacts, which stemmed from the shift from human intelligence to AI, or machine intelligence/machine learning (ML), when one explores the media and receives recommendations (often without requesting). In ML, three key steps usually occur; i.e., pre-processing, in-processing, and post-processing steps. The most common approach to address the issue of popularity bias is at the start of the pre-processing stage. This approach deals with the exposure bias, which believes that popularity bias occurs due to the inherited bias in the popularity distribution of the base version of the given data set the model trains on. This method, however, provides only a temporary solution to the root problem. To break the cycle of exposure bias and help end the resulting popularity bias, in this paper, we propose a novel post-processing algorithm called Closer-To-Average (CTA). Continuing and combining our previous work in the in-processing stage of the ML cycle, as the proposed countermeasures are used in the real world, will result in new, less biased datasets that future models can be trained on. This not only also provides users with more relevant recommendations, but more importantly, it helps break the continued cycle of popularity bias. Experimental results show that the CTA algorithm, when applied at the end of a modified version of the SASRec recommendation model, provided a 6% improvement in Blockbuster scores compared to the baseline models. In addition, when applying the proposed solution in a real-time, web-based system for movie recommendations, it only resulted in an additional overhead time of 0.3 seconds, a negligib

关键词： Training Machine learning algorithms Random access memory Media Motion pictures Real-time systems Information management Proposals Artificial intelligence Sorting

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202页 << < 12 13 14 15 16 17 18 19 20 21 > >>

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：