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

4,639 篇 期刊文献
4,164 篇 会议
41 册 图书

馆藏范围

8,844 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,608 篇 工学
- 4,242 篇 计算机科学与技术...
- 3,514 篇 软件工程
- 1,191 篇 信息与通信工程
- 769 篇 生物工程
- 724 篇 控制科学与工程
- 709 篇 电气工程
- 532 篇 生物医学工程（可授...
- 480 篇 光学工程
- 461 篇 电子科学与技术（可...
- 280 篇 机械工程
- 248 篇 化学工程与技术
- 202 篇 安全科学与工程
- 197 篇 网络空间安全
- 194 篇 交通运输工程
- 180 篇 仪器科学与技术
- 178 篇 动力工程及工程热...
3,335 篇 理学
- 1,761 篇 数学
- 908 篇 物理学
- 864 篇 生物学
- 644 篇 统计学（可授理学、...
- 298 篇 化学
- 285 篇 系统科学
1,593 篇 管理学
- 918 篇 管理科学与工程(可...
- 745 篇 图书情报与档案管...
- 471 篇 工商管理
533 篇 医学
- 465 篇 临床医学
- 398 篇 基础医学(可授医学...
- 232 篇 公共卫生与预防医...
- 222 篇 药学(可授医学、理...
283 篇 法学
- 241 篇 社会学
164 篇 经济学
106 篇 农学
105 篇 教育学
21 篇 文学
12 篇 军事学
7 篇 艺术学
1 篇 历史学

主题

276 篇 accuracy
272 篇 deep learning
231 篇 machine learning
227 篇 feature extracti...
219 篇 training
184 篇 computational mo...
180 篇 semantics
161 篇 predictive model...
144 篇 data models
133 篇 real-time system...
120 篇 federated learni...
111 篇 optimization
108 篇 convolutional ne...
107 篇 reinforcement le...
105 篇 graph neural net...
94 篇 internet of thin...
90 篇 artificial intel...
88 篇 image segmentati...
88 篇 neural networks
87 篇 contrastive lear...

机构

551 篇 college of compu...
173 篇 university of ch...
131 篇 nanyang technolo...
103 篇 national enginee...
102 篇 college of compu...
98 篇 beijing advanced...
97 篇 school of data a...
84 篇 school of comput...
81 篇 cas key lab of n...
71 篇 shandong provinc...
70 篇 school of comput...
65 篇 national enginee...
63 篇 department of co...
60 篇 cas key laborato...
50 篇 school of comput...
50 篇 college of intel...
47 篇 college of compu...
46 篇 shandong enginee...
44 篇 school of comput...
41 篇 data science ins...

作者

259 篇 niyato dusit
157 篇 cheng xueqi
70 篇 hai jin
63 篇 guo jiafeng
51 篇 sun geng
51 篇 tao dacheng
48 篇 jin hai
44 篇 shen huawei
37 篇 zheng wei-shi
35 篇 peng hao
35 篇 xiaofei liao
31 篇 jin xiaolong
30 篇 liu yang
27 篇 e. j. siskind
27 篇 r. bellazzini
26 篇 shen linlin
25 篇 chen chen
25 篇 li jianxin
25 篇 guo yike
24 篇 j. b. thayer

语言

7,512 篇 英文
1,285 篇 其他
74 篇 中文
2 篇 斯洛文尼亚文

检索条件"机构=Data Science and Computing"

共 8844 条记录，以下是471-480 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：

The evolution,applications,and future prospects of large language models:An in-depth overview

The evolution,applications,and future prospects of large lan...

引用

作者： Jiayin Li School of Computing and Data Science Xiamen University Malaysia

The evolution of natural language processing has transpired through three primary phases,with large-scale language models significantly transforming the *** models have heightened the machine's capability to understand,produce,and interact with human language in unprecedented *** from RNNs to transformer models,transitioning from encoder-decoder frameworks to decoder-centric designs,and the journey from BERT to the Chat-GPT series have marked significant shifts in the academic ***,these sophisticated models have infiltrated a range of sectors,including finance,healthcare,biology,and education,revolutionizing both traditional and emerging ***,as these advancements are celebrated,the ethical and economic challenges they introduce must also be *** these pivotal issues and harnessing technology for societal betterment has become a priority for academia and industry alike,sparking intense research endeavors in recent *** review dives into the history of natural language processing,highlighting the pivotal developments and core principles of large language *** provides a comprehensive perspective on their adoption and influence within the financial sector,crafting a detailed narrative of their *** conclusion,the analysis reflects on the current challenges posed by these models and presents potential *** study stands as a definitive guide,offering readers an in-depth understanding of the development,application,and future trajectories of large-scale language models.

关键词： large language models natural language processing challenges and opportunities

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Agnostic Weakly Supervised Method For Describing Textures

An Encoder-Agnostic Weakly Supervised Method For Describing ...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Shangbo Mao Deepu Rajan College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Recent advances in Large Language Models (LLMs) have enabled the semantic description of textures in natural language, aiming to capture them in richer detail. However, most methods are confined to either depending on supervised training with pairs of images and manually annotated visual attributes that most texture datasets lack or using Vision-Language Models (VLMs) such as CLIP. In this paper, we develop an encoder-agnostic Weakly supervised Texture Description Generator (WTDG) that employs a novel Scaled Ranked Kullback-Leibler divergence (SR-KL) loss between image and text modalities. Within the SR-KL loss formulation, we leverage category information, which is always available as ground-truths for all benchmark texture recognition datasets. We further extend our proposed WTDG to assist in texture recognition by using its generated texture descriptions. Thus, we develop a multimodal framework, called $T e x^2$ , which is adept at simultaneous generation of texture description and recognition. Our approach exhibits promising performance in describing and recognizing textures on benchmark datasets.

关键词： Training Visualization Computer vision Accuracy Large language models Semantics Natural languages Benchmark testing Generators

来源：评论

学校读者我要写书评

暂无评论

A Bias-Free Revenue-Maximizing Bidding Strategy for data Consumers in Auction-based Federated Learning 33

A Bias-Free Revenue-Maximizing Bidding Strategy for Data Con...

引用

33rd International Joint Conference on Artificial Intelligence, IJCAI 2024

作者： Tang, Xiaoli Yu, Han Li, Zengxiang Li, Xiaoxiao College of Computing and Data Science Nanyang Technological University Singapore ENN Group Beijing China Department of Electrical and Computer Engineering The University of British Columbia Canada

ISBN: (纸本)9781956792041

Auction-based Federated Learning (AFL) is a burgeoning research area. However, existing bidding strategies for AFL data consumers (DCs) primarily focus on maximizing expected accumulated utility, disregarding the more complex goal of revenue maximization. They also only consider winning bids, leading to biased estimates by overlooking information from losing bids. To address these issues, we propose a Bias-free Revenue-maximizing Federated bidding strategy for DCs in AFL (BR-FEDBIDDER). Our theoretical exploration of the relationships between Return on Investment (ROI), bid costs, and utility, and their impact on overall revenue underscores the complexity of maximizing revenue solely by prioritizing ROI enhancement. Leveraging these insights, BR-FEDBIDDER optimizes bid costs with any given ROI constraint. In addition, we incorporate an auxiliary task of winning probability estimation into the framework to achieve bias-free learning by leveraging bid records from historical bid requests, including both winning and losing ones. Extensive experiments on six widely used benchmark datasets show that BR-FEDBIDDER outperforms eight state-of-the-art methods, surpassing the best-performing baseline by 5.66%, 6.08% and 2.44% in terms of the total revenue, ROI, and test accuracy of the resulting FL models, respectively. © 2024 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing OSS Remediation with Patch Backporting

Enhancing OSS Remediation with Patch Backporting

引用

International Conference on Software Engineering - Companion, ICSE, Companion

作者： Lyuye Zhang College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798331536831

ISBN: (纸本)9798331536848

Nowadays existing vulnerability remediation methods mainly rely on version upgrades which often struggle to eliminate all vulnerabilities in complex scenarios. Therefore, this paper proposes a patch-porting-based tool aiming to automate the porting of patches to vulnerable versions, achieving remediation beyond traditional upgrading. The experiment indicates that 85% of the vulnerabilities successfully generated patches for 20 CVEs, and 70% passed validation, demonstrating that PPR can serve as a supplement to existing vulnerability remediation tools.

关键词： Software Security Software engineering

来源：评论

学校读者我要写书评

暂无评论

Generative Deduplication For Socia Media data Selection

Generative Deduplication For Socia Media Data Selection

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Li, Xianming Li, Jing Department of Computing The Hong Kong Polytechnic University Hong Kong Research Centre on Data Science & Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9798891761681

Social media data exhibits severe redundancy caused by its noisy nature. It leads to increased training time and model bias in its processing. To address this issue, we propose a novel Generative Deduplication framework for social media data selection by removing semantically duplicate data. While related work involves data selection in task-specific training, our model acts as an efficient pre-processing method to universally enhance social media NLP pipelines. Specifically, we train a generative model via self-supervised learning to predict a keyword to capture the semantics of noisy social media text for deduplication. Meanwhile, time-dimensional Gaussian noise is added to improve training complexity and avoid learning trivial features. Extensive experiments suggest that our model can better reduce training samples while improving performance than baselines. The results show our model's potential to broadly advance social media language understanding in effectiveness and efficiency. © 2024 Association for Computational Linguistics.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings

BeLLM: Backward Dependency Enhanced Large Language Model for...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Li, Xianming Li, Jing Department of Computing Hong Kong Polytechnic University Hong Kong Research Centre on Data Science and Artificial Intelligence Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9798891761148

Sentence embeddings are crucial in measuring semantic similarity. Most recent studies employed large language models (LLMs) to learn sentence embeddings. Existing LLMs mainly adopted autoregressive architecture without explicit backward dependency modeling. Therefore, we examined the effects of backward dependencies in LLMs for semantic similarity measurements. Concretely, we propose a novel model: backward dependency enhanced large language model (BeLLM). It learns sentence embeddings via transforming specific attention layers from uni- to bi-directional. We extensively experiment across various semantic textual similarity (STS) tasks and downstream applications. BeLLM achieves state-of-the-art performance in varying scenarios. It shows that auto-regressive LLMs benefit from backward dependencies for sentence embeddings. © 2024 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

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition 38

LF-ViT: Reducing Spatial Redundancy in Vision Transformer fo...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Hu, Youbing Cheng, Yun Lu, Anqi Cao, Zhiqiang Wei, Dawei Liu, Jie Li, Zhijun AIoT Lab Faculty of Computing Harbin Institute of Technology China Swiss Data Science Center Zurich Switzerland School of Cyber Engineering Xidian University China

ISBN: (纸本)1577358872

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present the Localization and Focus Vision Transformer (LF-ViT). This model operates by strategically curtailing computational demands without impinging on performance. In the Localization phase, a reduced-resolution image is processed;if a definitive prediction remains elusive, our pioneering Neighborhood Global Class Attention (NGCA) mechanism is triggered, effectively identifying and spotlighting class-discriminative regions based on initial findings. Subsequently, in the Focus phase, this designated region is used from the original image to enhance recognition. Uniquely, LF-ViT employs consistent parameters across both phases, ensuring seamless end-to-end optimization. Our empirical tests affirm LF-ViT's prowess: it remarkably decreases Deit-S's FLOPs by 63% and concurrently amplifies throughput twofold. Code of this project is at https://***/edgeai1/***. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Salient Object Detection via a Unified Diffusion Model

Multi-modal Salient Object Detection via a Unified Diffusion...

引用

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

作者： Zhang, Shuo Huang, Jiaming Tang, Wenbing Tian, Lili Wei, Yuang Liu, Jing Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Huolala Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science and Technology East China Normal University China

ISBN: (纸本)9798350368741

Salient Object Detection (SOD) aims to identify and segment the most striking elements within an image. Salient object detection methods can be differentiated into several types according to the input data, such as RGB-D (Depth) and RGB-T (Thermal). Previous research primarily focused on saliency detection for single data types. However, forcing an RGB-D SOD model to process RGB-T data will degrade its performance significantly. In addition, current methods still face challenges in detecting fine edge details of salient objects and achieving end-to-end training. To address these issues, we introduce diffSOD, which leverages stable diffusion and cross-modal feature rectification and fusion module for saliency detection by transforming salient object detection into a denoising process from a noisy mask to an object mask. It offers a unified solution for salient object detection that seamlessly spans both RGB-D SOD and RGB-T SOD. Extensive experiments validate the effectiveness of the proposed diffSOD, demonstrating its ability to efficiently detect salient objects across both RGB-D and RGB-T data, while achieving superior performance over state-of-the-art methods. © 2025 IEEE.

关键词： attention interaction fusion latent diffusion model multi-modal salient object detection

来源：评论

学校读者我要写书评

暂无评论

data vault modelling as alternative to dimensional modelling to embrace complexity in data driven decision systems: a critical systems perspective

Data vault modelling as alternative to dimensional modelling...

引用

2022 IEEE Asia-Pacific Conference on Computer science and data Engineering, CSDE 2022

作者： Goede, Roelien North-West University Unit for Data Science and Computing Potchefstroom South Africa

ISBN: (纸本)9781665453059

We live in a complex world where uncertainty is the only certainty. Today's compelling business problem is replaced tomorrow with a problem which was not even imagined yesterday. data driven decision systems are used by managers in support of their strategic decisions and should be agile and flexibility to survive in our ever change world of complex decisions. The argument presented in this conceptual paper is that data vault modeling is inherently better equipped than dimensional modelling to handle the turbulations of our complex world. The paper investigates the underlying assumptions of dimensional modelling and data vault modelling in terms of requirements collection and the resulting data modelling techniques. It uses critical systems thinking as guiding philosophy to reflect on the benefits of understanding and modelling a variety of perspectives in a problem situation. Critical systems thinking also promotes equal opportunity and accountability. It is argued that both these aspirations can better be achieved by using dimensional modeling as alternative to dimensional modelling. We hope to promote the development of sustainable data driven decision systems which can stand the test of our turbulent times. © 2022 IEEE.

关键词： Systems thinking

来源：评论

学校读者我要写书评

暂无评论

Beyond Precision: A Study on Recall of Initial Retrieval with Neural Representations 1

引用

28th China Conference on Information Retrieval, CCIR 2022

作者： Xiao, Yan Fan, Yixing Zhang, Ruqing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (数字)9783031247552

ISBN: (纸本)9783031247545

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic relatedness, leading to new possibilities to alleviate the vocabulary mismatch problem in IR. However, most existing efforts in this direction have been devoted to the re-ranking stage. That is to leverage neural representations to help re-rank a set of candidate documents, which are typically obtained from an initial retrieval stage based on some symbolic index and search scheme (e.g., BM25 over the inverted index). This naturally raises a question: if the relevant documents have not been found in the initial retrieval stage due to vocabulary mismatch, there would be no chance to re-rank them to the top positions later. Therefore, in this paper, we study the problem how to employ neural representations to improve the recall of relevant documents in the initial retrieval stage. Specifically, to meet the efficiency requirement of the initial stage, we introduce a neural index for the neural representations of documents, and propose two hybrid search schemes based on both neural and symbolic indices, namely the parallel search scheme and the sequential search scheme. Our experiments show that both hybrid index and search schemes can improve the recall of the initial retrieval stage with small overhead. © 2023, Springer Nature Switzerland AG.

关键词： Semantics

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500页 << < 44 45 46 47 48 49 50 51 52 53 > >>

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：