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

118 篇 会议
56 篇 期刊文献

馆藏范围

174 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

116 篇 工学
- 92 篇 计算机科学与技术...
- 80 篇 软件工程
- 24 篇 信息与通信工程
- 13 篇 光学工程
- 13 篇 控制科学与工程
- 9 篇 机械工程
- 9 篇 电气工程
- 9 篇 电子科学与技术（可...
- 9 篇 生物工程
- 8 篇 化学工程与技术
- 7 篇 建筑学
- 7 篇 交通运输工程
- 7 篇 网络空间安全
- 6 篇 土木工程
- 5 篇 仪器科学与技术
- 5 篇 生物医学工程（可授...
- 3 篇 动力工程及工程热...
- 3 篇 石油与天然气工程
- 3 篇 安全科学与工程
51 篇 理学
- 29 篇 数学
- 11 篇 生物学
- 9 篇 统计学（可授理学、...
- 8 篇 物理学
- 7 篇 化学
- 3 篇 大气科学
- 3 篇 系统科学
32 篇 管理学
- 18 篇 图书情报与档案管...
- 16 篇 管理科学与工程(可...
5 篇 医学
- 3 篇 临床医学
3 篇 法学
- 3 篇 社会学
1 篇 文学

主题

8 篇 graph neural net...
7 篇 wireless sensor ...
7 篇 semantics
6 篇 deep learning
5 篇 educational inst...
5 篇 data mining
4 篇 task analysis
4 篇 image segmentati...
4 篇 glass
4 篇 visualization
4 篇 feature extracti...
4 篇 training
3 篇 object detection
3 篇 distillation
3 篇 protocols
3 篇 correlation
3 篇 image color anal...
3 篇 data visualizati...
2 篇 computer science
2 篇 collaborative fi...

机构

62 篇 zhejiang provinc...
20 篇 school of softwa...
10 篇 college of compu...
9 篇 zhejiang key lab...
8 篇 zhejiang provinc...
8 篇 college of infor...
8 篇 college of compu...
6 篇 school of big da...
5 篇 alibaba-zhejiang...
5 篇 school of comput...
5 篇 the school of el...
5 篇 the state key la...
5 篇 state key lab. o...
5 篇 zhejiang univers...
5 篇 alibaba group
5 篇 zhejiang provinc...
4 篇 the school of ro...
4 篇 dbappsecurity lt...
4 篇 the college of i...
4 篇 school of electr...

作者

47 篇 bu jiajun
27 篇 jiajun bu
25 篇 chen chun
24 篇 yu zhi
15 篇 zhi yu
15 篇 chun chen
11 篇 wei dong
11 篇 zhou sheng
11 篇 wang haishuai
9 篇 gu jingjun
9 篇 wang wei
9 篇 he xiaofei
9 篇 huang chongwen
9 篇 wang can
8 篇 yuen chau
8 篇 cai deng
8 篇 zhang zhaoyang
7 篇 yi gao
6 篇 song mingli
6 篇 yang kailun

语言

157 篇 英文
15 篇 其他
2 篇 中文

检索条件"机构=Zhejiang Key Laboratory of Service Robot College of Computer Science"

共 174 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：

Matching Varying-Length Texts via Topic-Informed and Decoupled Sentence Embeddings

Matching Varying-Length Texts via Topic-Informed and Decoupl...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Zhou, Xixi Gu, Chunbin Jie, Xin Bu, Jiajun Wang, Haishuai Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University China

ISBN: (纸本)9798891761193

Measuring semantic similarity between texts is a crucial task in natural language processing. While existing semantic text matching focuses on pairs of similar-length sequences, matching texts with non-comparable lengths has broader applications in specific domains, such as comparing professional document summaries and content. Current approaches struggle with text pairs of non-comparable lengths due to truncation issues. To address this, we split texts into natural sentences and decouple sentence representations using supervised contrastive learning (SCL). Meanwhile, we adopt the embedded topic model (ETM) for specific domain data. Our experiments demonstrate the effectiveness of our model, based on decoupled and topic-informed sentence embeddings, in matching texts of significantly different lengths across three well-studied datasets. © 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

LiverSegNeXt: Improved MedNeXt for Liver Segmentation 2

LiverSegNeXt: Improved MedNeXt for Liver Segmentation

引用

2nd IEEE International Conference on Sensors, Electronics and computer Engineering, ICSECE 2024

作者： Gu, Jingjun Hu, Haoyu Zhang, Wei College of Computer Science Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot Hangzhou China

ISBN: (纸本)9798350373646

Liver segmentation is crucial for computer-assisted diagnosis and preoperative planning in hepatology. The scarcity of annotated medical datasets and segmentation architectures tailored for liver imaging, presents significant challenges. Inaccurate segmentation can severely impact the diagnosis of intrahepatic lesions and preoperative planning. Current state-of-the-art methods struggle with segmenting challenging liver regions, such as the hepatic apex, portal vein, base, and caudate lobe. To address this, we introduce LiverSegNeXt, an advanced technique based on the MedNeXt framework. LiverSegNeXt incorporates novel approaches, including the inception and ConvNeXt architecture. Additionally, the performance of existing methods is still limited by insufficient feature extraction. We propose a coarse training and fine-tuning approach, as well as an absolute position embedding approach, to leverage the consistent spatial positioning of the liver in CT scans. We evaluated LiverSegNeXt on our in-house dataset. Our method outperforms existing models and found that it surpasses other existing methods, improving the Dice coefficient by 0.21% compared to other approaches. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Segment anything model for subgrade distress detection with GPR 3

Segment anything model for subgrade distress detection with ...

引用

2023 IEEE 3rd International Conference on Data science and computer Application, ICDSCA 2023

作者： Ning, Kangjie Zhou, Chunpeng Yu, Zhi Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University School of Software Technology Hangzhou China Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University School of Computer Science Hangzhou China

ISBN: (纸本)9798350341546

The detection of distresses with ground-penetrating radar (GPR) images is a highly challenging task due to their complex structure, blurred boundaries, and varying scales. The Segment Anything Model (SAM) has demonstrated impressive performance in natural image segmentation tasks with its zero-shot segmentation capability and high efficiency, which effectively reduces annotation time. However, the applicability of SAM for GPR image analysis remains till now. To this end, we construct a GPR image dataset comprising 395 samples with segmention, which are jointly confirmed and annotated by multiple domain experts. We comprehensively evaluate the performance of various mainstream deep learning image segmentation models and different SAM models on this dataset, and analyze the results in detail. Our experiments confirm that SAM's performance in detecting underground radar distresses is limited or even completely inadequate. These findings demonstrate that SAM's current zero-shot segmentation capability is insufficient for direct application in subgrade distress with GPR data. © 2023 IEEE.

关键词： deep learning Foundation model ground-penetrating radar Intelligent traffic

来源：评论

学校读者我要写书评

暂无评论

An Artificial Intelligence-Based Segmentation Auxiliary Diagnostic System for Focal Liver Lesions 2

An Artificial Intelligence-Based Segmentation Auxiliary Diag...

引用

2nd International Conference on Mechatronics, IoT and Industrial Informatics, ICMIII 2024

作者： Gu, Jingjun Yu, Zhi Zhang, Wei Hu, Haoyu Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Hangzhou China Zhejiang University School of Software Technology Hangzhou China

ISBN: (纸本)9798350386639

In this paper, we introduce an artificial intelligence-based system designed for the segmentation and auxiliary diagnosis of focal liver lesions. This system can effectively segment lesions in both singlephase non-contrast CT images and multiphase contrast-enhanced CT images. Additionally, it has the capability to synchronize CT data from Picture Archiving and Communication Systems (PACS) and to visualize the segmentation results. Our AI system aims to meet the demand for rapid screening of liver lesions in primary hospitals and physical examination institutions, while also fulfilling the more precise segmentation needs of provincial and municipal hospitals. © 2024 IEEE.

关键词： Picture archiving and communication systems

来源：评论

学校读者我要写书评

暂无评论

Multi-label Classification of Road Cracks Based on Semantic-Aware Mixup 4

Multi-label Classification of Road Cracks Based on Semantic-...

引用

4th International Conference on computers, Information Processing and Advanced Education, CIPAE 2023

作者： Xu, Chengyang Zhou, Chunpeng Yu, Zhi Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Hangzhou China Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Hangzhou China Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Ningbo China

ISBN: (纸本)9798350342710

In the realm of road crack detection scenarios, Mixup, a widely used data augmentation technique, exhibits constrained effectiveness in multi-label classification, unlike its performance on general datasets. This paper investigates the reasons behind this limitation, identifying two main factors: (1) the mutually exclusive nature of road crack labels and (2) the potential generation of incorrect labels during image mixing. To address these issues, we propose an approach called Semantic-Aware Mixup (SA-Mixup), which focuses on enhancing crack samples specifically. Experimental evaluations on three distinct road crack datasets demonstrate the effectiveness and simplicity of our proposed method. The results highlight significant improvements in model performance, offering a promising solution for accurate and efficient multi-label classification in road crack detection tasks. © 2023 IEEE.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

A Heatmap Regression Approach for Right Ventricle Anatomical Landmarks Localization on Echocardiography

A Heatmap Regression Approach for Right Ventricle Anatomical...

引用

2023 IEEE International Conference on Image Processing and computer Applications, ICIPCA 2023

作者： Wan, Hailiang Gu, Jingjun Yu, Zhi Song, Shuyi Polytechnic Institute Zhejiang University Hangzhou China College of Computer Science Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot Hangzhou China School of Software Technology Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot Ningbo China DBAPPSecurity Ltd. College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9798350314670

In the process of quantitative cardiac analysis based on echocardiography, the localization of right ventricle anatomical landmarks is a critical step. However, manual labeling of these landmarks by professional physicians is a costly, time-consuming, and labor-intensive process that is also prone to both inter-observer and intra-observer variations. Therefore, we propose n heatmap regression approach to automatically locate right ventricle anatomical landmarks on echocardiography. Firstly, we propose an improved U-Net model, which has a stronger ability to extract features and exploit relationships between the coordinates of landmarks. Secondly, we analyze the limitations of L2 loss in our task. Building on this analysis, we propose a new loss function, Weighted Smooth L1 loss, which not only balances foreground and background pixels but also makes the model more robust to noise. Experiments show that the proposed improved U-Net and Weighted Smooth L1 loss can effectively enhance the landmark localization effect of the model. © 2023 IEEE.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks 40

CPDG: A Contrastive Pre-Training Method for Dynamic Graph Ne...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Bei, Yuanchen Xu, Hao Zhou, Sheng Chi, Huixuan Wang, Haishuai Zhang, Mengdi Li, Zhao Bu, Jiajun Meituan China College of Computer Science and Technology Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University China School of Software Technology Zhejiang University China Institute of Computing Technology Chinese Academy of Science China

ISBN: (纸本)9798350317152

Dynamic graph data mining has gained popularity in recent years due to the rich information contained in dynamic graphs and their widespread use in the real world. Despite the advances in dynamic graph neural networks (DGNNs), the rich information and diverse downstream tasks have posed significant difficulties for the practical application of DGNNs in industrial scenarios. To this end, in this paper, we propose to address them by pre-training and present the Contrastive Pre-Training Method for Dynamic Graph Neural Networks (CPDG). CPDG tackles the challenges of pre-training for DGNNs, including generalization capability and long-short term modeling capability, through a flexible structural-temporal subgraph sampler along with structural-temporal contrastive pre-training schemes. Extensive experiments conducted on both large-scale research and industrial dynamic graph datasets show that CPDG outperforms existing methods in dynamic graph pre-training for various downstream tasks under three transfer settings. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

End-to-End Solution for Braille-To-Chinese

End-to-End Solution for Braille-To-Chinese

引用

2023 IEEE International Conference on Sensors, Electronics and computer Engineering, ICSECE 2023

作者： Zheng, Yantian Xing, Hangdi Yu, Zhi Zhang, Xinhua Gao, Feiyu Bu, Jiajun Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Ningbo China Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Hangzhou China Zhejiang School for the Blind Hangzhou China DAMO Academy Alibaba Group Hangzhou China

ISBN: (纸本)9798350313734

In the field of education, Teachers of Students with Visual Impairments need to read and review student's Braille homework. Reading Braille consumes a lot of teachers' time and energy. We propose an end-to-end solution to translate Braille into Chinese. Our approach uses a deep learning method to detect and recognize Braille in images and translate them into Chinese and mathematical formulas. Finally, we reconstruct the translation results into the style of the input Braille image. Our approach is able to adapt to more complex Braille images and make the translation results easier to read and understand, significantly improving the speed of reading Braille for non-disabled. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Road Plant Image Classification Algorithm Based on Segmentation Prior 5

Road Plant Image Classification Algorithm Based on Segmentat...

引用

5th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2023

作者： Sun, Qiao Yang, Yi Gu, Jingjun Yu, Zhi College of Computer Science Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot Hangzhou China School of Electronic Engineering Naval University of Engineering Wuhan China

ISBN: (纸本)9798350333442

As an important part of urban ecology, it is of great significance to grasp and analyze the detailed distribution of road plants for both scientific research and landscape planning. However, due to the advancement of urbanization, the types and numbers of road plants are increasing, and it is difficult to obtain accurate and timely plant distribution information by traditional field research and remote sensing techniques. In order to solve this problem, we proposes a deep learning-based road plant image classification algorithm, which identifies plants in streetscape data by multi- label image classification to obtain the distribution of road plants. In order to solve the problem of feature information loss in the network, we increases the channel capacity of the bottleneck structure in the network, and introduces the group convolution structure to optimize the network performance. Due to the complexity of the image background, we proposes a road plant image classification algorithm based on a priori segmentation by training the binary classification segmentation model of plants and background through transfer learning. This makes the classification model pay more attention to the area of road plants in the image and improves the classification accuracy by 5.16%. © 2023 IEEE.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Road Surface Damage Detection Based on Knowledge Distillation

Road Surface Damage Detection Based on Knowledge Distillatio...

引用

2023 IEEE International Conference on Image Processing and computer Applications, ICIPCA 2023

ISBN: (纸本)9798350314670

As an important public infrastructure, road contributes to economic development and growth, brings significant social benefits. However, due to a variety of factors, the road surfaces will wear and deteriorate over time. When there is a slight crack in the pavement, most will deteriorate rapidly if not repaired promptly, which can greatly affect the life of the road. Therefore, developing a road surface damage detection algorithm is an urgent demand. We use the knowledge distillation technology to solve this problem. First, the similarity-preserving knowledge distillation was improved by adding a mask block to make the model transmit only the key feature information of the local region. Secondly, by making the boundary box of the teacher output and ground truth do non-maximum suppression, the image area of the distillation in the output layer is restricted, and the transmission of background information by the teacher is reduced. the performance of the student is improved by 1.2% in mAP@0.5 on average and 2.2% in mAP@0.5:0.95 on average compared with the state-of-the-art method. © 2023 IEEE.

关键词： Damage detection

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18页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：