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

5,196 篇 期刊文献
4,316 篇 会议
28 册 图书

馆藏范围

9,540 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6,137 篇 工学
- 3,753 篇 计算机科学与技术...
- 3,066 篇 软件工程
- 1,397 篇 信息与通信工程
- 839 篇 控制科学与工程
- 744 篇 电子科学与技术（可...
- 741 篇 电气工程
- 564 篇 生物工程
- 537 篇 光学工程
- 511 篇 机械工程
- 408 篇 仪器科学与技术
- 346 篇 化学工程与技术
- 334 篇 生物医学工程（可授...
- 248 篇 动力工程及工程热...
- 201 篇 交通运输工程
- 194 篇 核科学与技术
- 170 篇 材料科学与工程（可...
- 154 篇 网络空间安全
- 150 篇 安全科学与工程
4,071 篇 理学
- 1,892 篇 物理学
- 1,664 篇 数学
- 630 篇 生物学
- 583 篇 统计学（可授理学、...
- 433 篇 化学
- 289 篇 系统科学
- 181 篇 地球物理学
1,407 篇 管理学
- 884 篇 管理科学与工程(可...
- 579 篇 图书情报与档案管...
- 319 篇 工商管理
294 篇 医学
- 249 篇 临床医学
- 201 篇 基础医学(可授医学...
183 篇 法学
105 篇 经济学
89 篇 农学
61 篇 教育学
31 篇 文学
24 篇 艺术学
16 篇 军事学
2 篇 历史学

主题

232 篇 feature extracti...
179 篇 deep learning
168 篇 training
167 篇 semantics
141 篇 computational mo...
122 篇 image segmentati...
113 篇 optimization
110 篇 accuracy
106 篇 hadron colliders
106 篇 machine learning
96 篇 hadrons
94 篇 face recognition
93 篇 object detection
89 篇 computer science
89 篇 predictive model...
83 篇 cloud computing
83 篇 bosons
82 篇 neural networks
82 篇 convolution
82 篇 data models

机构

1,431 篇 school of comput...
1,025 篇 cavendish labora...
845 篇 department of ph...
764 篇 oliver lodge lab...
763 篇 physikalisches i...
535 篇 fakultät physik ...
522 篇 department for p...
493 篇 infn sezione di ...
488 篇 university of ch...
479 篇 infn laboratori ...
474 篇 institute of phy...
469 篇 infn sezione di ...
467 篇 iccub universita...
450 篇 infn sezione di ...
444 篇 institute of phy...
441 篇 infn sezione di ...
441 篇 infn sezione di ...
432 篇 department of ph...
385 篇 department of ph...
385 篇 h.h. wills physi...

作者

276 篇 barter w.
269 篇 c. alexa
269 篇 c. amelung
267 篇 g. bella
267 篇 j. strandberg
267 篇 d. calvet
266 篇 j. m. izen
263 篇 brundu d.
261 篇 g. spigo
260 篇 f. siegert
249 篇 beiter a.
243 篇 blake t.
239 篇 y. tayalati
239 篇 bellee v.
239 篇 betancourt c.
238 篇 r. ströhmer
232 篇 m. rijssenbeek
232 篇 borsato m.
229 篇 s. jin
228 篇 g. gaudio

语言

7,747 篇 英文
1,650 篇 其他
158 篇 中文
1 篇 德文
1 篇 法文
1 篇 日文
1 篇 朝鲜文

检索条件"机构=School of Computer Science and Engineering Nanjing Univ. of Science and Technology"

共 9540 条记录，以下是81-90 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：

An Enhanced Vision-Language Pre-Training Approach for Scene Text Detection 5

An Enhanced Vision-Language Pre-Training Approach for Scene ...

引用

5th International Symposium on computer engineering and Intelligent Communications, ISCEIC 2024

作者： Gu, Tao Zhang, Chongyang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798331518677

Recent advancements in Vision-Language Pre-training (VLP) techniques have greatly improved performance in Scene Text Detection tasks by leveraging the rich visual and textual content in scene text images. We propose an innovative integration of contrastive learning with Masked Language Modeling (MLM) and Masked Image Modeling (MIM), inspired by the Masked Autoencoder (MAE) approach. This synthesis enhances self-supervised learning by combining discriminative and generative learning. Notably, we introduce masked image modeling for text detection, enabling effective representation learning in text image regions. To distinguish our approach from traditional BERT's MLM, we develop a custom tokenizer tailored for scene text detection. Our pre-trained model aligns visual and textual information, resulting in improved performance of existing scene text detectors. Extensive experiments on datasets such as ICDAR2015 show that our method significantly outperforms previous pre-training approaches. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

BiMoeFormer: A Novel Transformer-Based Framework for 3D Human Motion Prediction with Bi-Level Routing Attention and Mixture of Experts 5

BiMoeFormer: A Novel Transformer-Based Framework for 3D Huma...

引用

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Zhang, Wei Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350385557

We introduce a novel BiMoeFormer based on the Transformer architecture for 3D human motion prediction. Previous approaches primarily focus on the relationships between body joints in human poses, while neglecting their independencies. Our method addresses this by incorporating a Bi-Level Routing Attention (BRA) mechanism, which emphasizes balancing the correlation and independence among these joints. More specifically, BRA selects the top k most relevant joints for each joint, enhancing the overall modeling capability. Moreover, to accurately capture the diversity and complexity of human motion, we employ a Mixture of Experts (MoE) architecture to enhance the expressiveness of the Transformer. This allows us to control the model complexity by sharing the MoE across blocks. Comprehensive evaluations on the Human3.6M, AMASS, and 3DPW datasets demonstrate that our method consistently outperforms state-of-the-art baselines. © 2024 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Forecasting Cloud Workload through Reinforcement Learning-Based Ensemble Model 4

Forecasting Cloud Workload through Reinforcement Learning-Ba...

引用

4th International Conference on Electronic Information engineering and computer Communication, EIECC 2024

作者： Kang, Yuliang Li, Yongke Zhang, Gongxuan Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798331534622

The escalating demand for cloud computing has intensified the need for accurate workload forecasting to optimize resource allocation and maintain service quality. This paper presents a novel approach employing a reinforcement learning-based ensemble model to enhance the accuracy of workload predictions in cloud environments. The study addresses the challenges posed by complex and dynamic workload patterns, leveraging deep learning techniques to improve prediction outcomes. The proposed model dynamically selects the optimal subset of predictors, demonstrating superior performance on the Google Cluster dataset. The research aims to contribute to more efficient and intelligent resource management in cloud computing. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

An Embedded System I/O Isolation technology for Raspberry Pi 4

An Embedded System I/O Isolation Technology for Raspberry Pi

引用

4th International Conference on Intelligent technology and Embedded Systems, ICITES 2024

作者： Yaoyong, Wang Gongxuan, Zhang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798331506292

Nowadays user's data in devices is at high risk. To ensure security of program's runtime environment, Trusted Computing and Trusted Execution Environment(TEE) are proposed, which construct trusted base at the hardware level. Hardware vendors implement hardware trusted base for their new products, Intel's Software Guard eXtension(SGX) as an example. SGX lacks isolation for device I/O so there are many SGX-based mechanisms proposed that add protection for device I/O. However, all the above trusted mechanisms must be based on that the CPU has extensions for trusted computing, which means that lots of devices equipped with old chips and those embedded devices on other ISA like Arm and RISC-V have no possibility to support this trusted computing mechanism. Therefore, we proposes an I/O isolation technology for embedded devices and implements a trusted computing mechanism named XiRang(eXtended I/O Reliable Authentication Guard) for Raspberry Pi. Specifically, we do the following work. (1) Use an external trusted device as the physical trusted root for embedded devices, which made up for the lack of trusted computing extension of their chips. (2) On the premise of trusted hardware, XiRang realizes the trusted isolation of USB disk, uses trusted Linux container as the application runtime environment, and completes the trusted chain transfer from the external trusted device to the application. (3) Finally, we evaluate performance of XiRang. © 2024 IEEE.

关键词： Embedded System I/O Isolation Raspberry Pi Trusted Computing Trusted Execution Environment

来源：评论

学校读者我要写书评

暂无评论

MTPNet: Learning Multiple Twin-support Prototypes for Few-shot Medical Image Segmentation

MTPNet: Learning Multiple Twin-support Prototypes for Few-sh...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Song, Feifan Cheng, Ziming Li, Lunbo Zhang, Haofeng Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350386226

Given the high annotation costs and ethical considerations associated with medical images, leveraging a limited number of annotated samples for Few-Shot Medical Image Segmentation (FSMIS) has become increasingly prevalent. However, existing models tend to focus on visible foreground support information, often overlooking extreme foreground-background imbalances. In addition, query images sometimes have slight different appearance compared to support images of the same category due to the differences in size as well as slicing angle, thus employing only support images to generate prototypes inevitably leads to matching bias. To address these challenges, we present an innovative approach through learning a Multiple Twin-support Prototypes Network (MTPNet). Our approach includes the design of the Scale Consistent Sampling (SCS) module, which adaptively adjusts the foreground and background points within the support set, thereby balancing the influence of various structural elements in the image. Additionally, the Twin-support Prototypes Extraction (TPE) module facilitates the critical interaction between query and support features to extract twin-support prototypes. This module incorporates a Backtrace Interaction Filter (BIF) to eliminate erroneous interaction prototypes. Extensive experimental validation on three widely used medical image datasets demonstrates that our method surpasses current State-of-the-arts, showcasing its potential to address key limitations in FSMIS. The code is available at https://***/FeifanSong/MTPNet. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Guided Real Image Dehazing Using YCbCr Color Space 39

Guided Real Image Dehazing Using YCbCr Color Space

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Fang, Wenxuan Fan, Junkai Zheng, Yu Weng, Jiangwei Tai, Ying Li, Jun School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China

ISBN: (纸本)157735897X

Image dehazing, particularly with learning-based methods, has gained significant attention due to its importance in real-world applications. However, relying solely on the RGB color space often fall short, frequently leaving residual haze. This arises from two main issues: the difficulty in obtaining clear textural features from hazy RGB images and the complexity of acquiring real haze/clean image pairs outside controlled environments like smoke-filled scenes. To address these issues, we first propose a novel Structure Guided Dehazing Network (SGDN) that leverages the superior structural properties of YCbCr features over RGB. It comprises two key modules: Bi-Color Guidance Bridge (BGB) and Color Enhancement Module (CEM). BGB integrates a phase integration module and an interactive attention module, utilizing the rich texture features of the YCbCr space to guide the RGB space, thereby recovering clearer features in both frequency and spatial domains. To maintain tonal consistency, CEM further enhances the color perception of RGB features by aggregating YCbCr channel information. Furthermore, for effective supervised learning, we introduce a Real-World Well-Aligned Haze dataset, which includes a diverse range of scenes from various geographical regions and climate conditions. Experimental results demonstrate that our method surpasses existing state-of-the-art methods across multiple real-world smoke/haze datasets. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Observe before Generate: Emotion-Cause aware Video Caption for Multimodal Emotion Cause Generation in Conversations 24

Observe before Generate: Emotion-Cause aware Video Caption f...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Fanfan Ma, Heqing Shen, Xiangqing Yu, Jianfei Xia, Rui School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798400706868

Emotion cause analysis has attracted increasing attention in recent years. However, the integration of multimodal information with emotion causes remains underexplored. Existing studies merely extract utterances from conversations as cause evidence, which is too coarse-grained to locate the exact causes from other modalities, especially those that may be reflected only in a specific video frame of an utterance. To address these limitations, we introduce a new task named Multimodal Emotion Cause Generation in Conversations (MECGC), which aims to generate an abstractive summary clearly and intuitively describing the causes that trigger the given emotion based on the multimodal context of conversations. We accordingly construct a dataset named ECGF that contains 1,374 conversations and 7,690 emotion instances from TV series. We further develop a generative framework that first generates emotion-cause aware video captions (Observe) and then facilitates the generation of emotion causes (Generate). The captioning model is trained with examples synthesized by a Multimodal Large Language Model (MLLM). Experimental results demonstrate the effectiveness of our framework and the significance of multimodal information for emotion cause analysis. Our dataset and source codes are available at https://***/NUSTM/MECGC. © 2024 ACM.

关键词： emotion cause analysis in conversations

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Leakage Detection Based on χ2 Test of Independence 23

Multi-Channel Leakage Detection Based on χ2 Test of Indepen...

引用

23rd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2024

作者： Kou, Xiaoyong Yang, Wei Cong, Peijin Zhang, Gongxuan Nanjing University of Science & Technology School of Computer Science and Engineering Nanjing China

Side-channel analysis (SCA) is a critical tool for evaluating the security of cryptographic devices, as physical leakage can reveal sensitive information such as cryptographic keys. Multi-channel fusion attacks (MCFAs) have proven to be efficient in exploiting side-channel leakages. However, a crucial step before performing MCFA is to assess whether the leakages from different channels can be effectively fused. To address this, we propose a black-box approach based on the χ2 test of independence to assess multi-channel leakage suitability for fusion. By treating the leakages as categorical variables, our method evaluates their association without requiring knowledge of the cryptographic key or device implementation. © 2024 IEEE.

关键词： Leak detection

来源：评论

学校读者我要写书评

暂无评论

SCMotion: Predicting Human Motion Through Spatial Dependence and Center Anchoring 7

SCMotion: Predicting Human Motion Through Spatial Dependence...

引用

7th International Conference on computer Information science and Application technology, CISAT 2024

作者： Chen, Siqi Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350375107

Human motion prediction aims to predict future human motion based on past observations, playing important roles in several fields. However, previous works have often focused on the temporal sequential nature of human motion while neglecting the coordinated linkage of multiple components of the human body in space. Therefore, we introduce SCMotion, focused on predicting human motion using spatial dependencies. We divide the human body joints into four joint groups and predict each module individually. Additionally, SCMotion uses the more stable center of gravity of the human body as an anchor point for prediction, greatly enhancing accuracy. Our experiments on the H3.6M dataset demonstrate the excellent prediction capabilities of SCMotion. © 2024 IEEE.

关键词： Graph Convolutional Networks Human Motion Prediction Humanrobot Interaction

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Knowledge Graph Completion Enhanced by Muti-Level Attention Mechanisms 3

Multi-Modal Knowledge Graph Completion Enhanced by Muti-Leve...

引用

3rd International Conference on Cloud Computing, Big Data Application and Software engineering, CBASE 2024

作者： Zhang, Tingting Wang, Yongli Liu, Dongmei School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798331506582

Multimodel knowledge graph completion (MKGC) aims to predict missing entities in MKGs. Differing from prior Single-model knowledge graph completion efforts, MKGC leverages rich textual descriptions, images, and other multi-model information associated with entities. Traditional MKGC methods often use simple concatennation, weighted fusion, or tensor-based approaches for multi-modal information fusion, but they fail to capture the in-tra-modality and inter-modality dynamics. Moreover, traditional models like TransE and TransH, based on translational operations, struggle with complex relationships such as 1-N, N-N. To address these issue, this paper proposes a multi-modal information fusion enhanced by multi-level attention mechanism and relation-specific graph attention network method for MKGC. Firstly, obtaining text, attribute, and image embeddings of entities by leveraging pre-trained modals such as BERT and Vision Transformer. Secondly, using low-rank tensors for multimodal fusion and introducing self-attention and cross-attention blocks to capture complementary information within and across modalities respectively. Finally, constructing a multi-source node graph and a relation graph attention network is employed to capture the structural information of the graph. The ConvE modal is used as a decoder, and the performance is evaluated through link prediction tasks on real datasets. Experimental results show that new method out-performs other baselines, such as TransE, R-GCN, RSME, KG-BERT. © 2024 IEEE.

关键词： Knowledge graph

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 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：