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

282,603 篇 会议
17,623 册 图书

馆藏范围

299,995 篇 电子文献
263 种 纸本馆藏

日期分布

学科分类号

281,828 篇 工学
- 277,751 篇 计算机科学与技术...
- 67,717 篇 软件工程
- 14,895 篇 信息与通信工程
- 8,439 篇 电气工程
- 8,089 篇 控制科学与工程
- 4,688 篇 生物医学工程（可授...
- 974 篇 生物工程
- 827 篇 光学工程
- 605 篇 机械工程
- 568 篇 仪器科学与技术
- 494 篇 测绘科学与技术
- 492 篇 交通运输工程
35,837 篇 理学
- 28,677 篇 数学
- 5,532 篇 生物学
- 1,683 篇 物理学
- 1,126 篇 统计学（可授理学、...
- 517 篇 系统科学
- 482 篇 化学
30,399 篇 医学
- 22,124 篇 临床医学
- 9,245 篇 特种医学
- 3,035 篇 基础医学(可授医学...
- 1,217 篇 医学技术（可授医学...
10,775 篇 管理学
- 6,492 篇 管理科学与工程(可...
- 3,323 篇 图书情报与档案管...
- 1,770 篇 工商管理
- 743 篇 公共管理
4,314 篇 教育学
- 4,041 篇 教育学
2,337 篇 法学
- 1,997 篇 社会学
1,680 篇 文学
- 1,179 篇 新闻传播学
- 526 篇 外国语言文学
467 篇 艺术学
372 篇 经济学
149 篇 农学
98 篇 历史学
65 篇 哲学
24 篇 军事学

主题

10,830 篇 artificial intel...
4,631 篇 computer communi...
3,945 篇 deep learning
3,861 篇 information syst...
3,741 篇 computers
3,637 篇 software enginee...
3,332 篇 machine learning
3,243 篇 algorithm analys...
3,223 篇 semantics
2,288 篇 information stor...
2,190 篇 pattern recognit...
1,834 篇 neural networks
1,820 篇 user interfaces ...
1,820 篇 image processing...
1,805 篇 database managem...
1,794 篇 logics and meani...
1,777 篇 mathematical log...
1,770 篇 cryptography
1,757 篇 software enginee...
1,707 篇 data mining and ...

机构

651 篇 univ chinese aca...
541 篇 carnegie mellon ...
403 篇 univ chinese aca...
359 篇 univ calif berke...
353 篇 shanghai jiao to...
318 篇 stanford univ st...
307 篇 chinese acad sci...
288 篇 shanghai jiao to...
285 篇 inria
248 篇 tech univ munich...
241 篇 tech univ darmst...
225 篇 swiss fed inst t...
212 篇 univ waterloo wa...
207 篇 nanjing univ sta...
203 篇 tsinghua univ pe...
199 篇 ist austria klos...
198 篇 natl univ singap...
186 篇 mit cambridge ma...
185 篇 univ maryland co...
183 篇 chinese acad sci...

作者

212 篇 shen dinggang
104 篇 navab nassir
98 篇 zhang lei
94 篇 wang wei
92 篇 susilo willy
85 篇 liu yang
83 篇 rueckert daniel
81 篇 wang lei
81 篇 wang xin
76 篇 auer soeren
66 篇 golland polina
64 篇 weske mathias
61 篇 zhang yong
54 篇 liu wei
52 篇 zhang li
51 篇 zhou jie
49 篇 jiang xiaoyi
47 篇 zhang tao
47 篇 zhang yu
47 篇 ishai yuval

语言

298,284 篇 英文
1,937 篇 中文
1 篇 加泰罗尼亚文
1 篇 法文

检索条件"丛书名=Lecture Notes in Computer Science"

共 300226 条记录，以下是1151-1160 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：

Dual-Task Feedback Learning for Tongue Detection via Super-Resolution Integration 31st

Dual-Task Feedback Learning for Tongue Detection via Super-R...

引用

31st International Conference on Multimedia Modeling

作者： Sun, Ying Wei, Meiyi Chen, Gang Wuhan Univ Minist Educ Key Lab Aerosp Informat Secur & Trusted Comp Sch Cyber Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9789819620531;9789819620548

Traditional Chinese Medicine (TCM) has gained prominence in clinical practice, with tongue diagnosis, a key technique, now being integrated with Artificial Intelligence (AI) to achieve more objective and quantifiable results, thereby mitigating reliance on subjective judgment. However, challenges such as poor lighting conditions and limited imaging equipment often compromise image clarity, complicating tongue detection and identification. To address these issues, we propose a DualTask Feedback Learning (DTFL) framework, designed to enhance tongue detection in patient images by improving image quality. In our approach, Super-Resolution (SR) serves as a preliminary task preceding Tongue Detection (TD), enabling the TD network to process high-quality images for more accurate results. To further improve the interaction between SR and TD tasks, we incorporate Feature Alignment (FA) loss, which establishes a feedback connection that allows the SR network to acquire task-specific knowledge from the TD network. Additionally, we introduce a quality fusion augmentation and alternate training strategy to address potential challenges associated with FA loss during training. To the best of our knowledge, we are the first to integrate SR into TD. Experiments demonstrate that DTFL significantly improves performance by generating SR images that are optimally suited for TD.

关键词： Traditional Chinese Medicine Tongue Detection Super-Resolution Artificial Intelligence Multi-Task Learning

来源：评论

学校读者我要写书评

暂无评论

SpecifyThis Bridging Gaps Between Program Specification Paradigms: Track Introduction 12th

SpecifyThis Bridging Gaps Between Program Specification Para...

引用

12th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation

作者： Ernst, Gidon Herber, Paula Huisman, Marieke Ulbrich, Mattias Ludwig Maximilians Univ Munchen Munich Germany Univ Munster Munster Germany Univ Twente Enschede Netherlands Karlsruhe Inst Technol Karlsruhe Germany

We motivate and summarise the track SpecifyThis - Bridging gaps between program specification paradigms, taking place at the International Symposium on Leveraging Applications of Formal Methods, ISoLA 2024.

ISBN: (纸本)9783031753794;9783031753800

关键词： Specification Verification Formal methods

来源：评论

学校读者我要写书评

暂无评论

Refined and Locality-Enhanced Feature for Handwritten Mathematical Expression Recognition 7th

Refined and Locality-Enhanced Feature for Handwritten Mathem...

引用

7th Chinese Conference on Pattern Recognition and computer Vision

作者： Yu, Liu Du, Xiangcheng Liu, Ziang Dong, Daoguo He, Liang East China Normal Univ Shanghai Peoples R China Fudan Univ Shanghai Peoples R China

ISBN: (纸本)9789819785100;9789819785117

Many studies have been conducted on handwritten mathematical expression recognition (HMER) based on encoder-decoder architecture. However, the previous methods fail to predict accurate results due to low-quality images such as blur, complex background and distortion. In addition, ambiguous or subtle symbols caused by different handwriting styles are often recognized incorrectly. In this paper, we propose an efficient method for HMER to deal with the above issues. Specifically, we propose a Dual-branch Refinement Module (DRM) to deal with the challenging disturbances. In terms of ambiguous or subtle symbols, we believe that the combination of local and global information is beneficial to recognizing these symbols. Therefore, we design a Local Feature Enhancement Module (LFEM) to enhance local features, which can cooperate with global information extracted by the following transformer decoder. Extensive experimental results on CROHME and HME100K datasets verify the effectiveness of our method.

关键词： Handwritten mathematical expression recognition feature refinement local feature enhancement transformer

来源：评论

学校读者我要写书评

暂无评论

ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation 18th

ItTakesTwo: Leveraging Peer Representations for Semi-supervi...

引用

18th European Conference on computer Vision (ECCV)

作者： Liu, Yuyuan Chen, Yuanhong Wang, Hu Belagiannis, Vasileios Reid, Ian Carneiro, Gustavo Univ Adelaide Australian Inst Machine Learning AIML Adelaide SA Australia Mohamed Bin Zayed Univ Artificial Intelligence MB Abu Dhabi U Arab Emirates Univ Erlangen Nurnberg Erlangen Germany Univ Surrey Ctr Vis Speech & Signal Proc CVSSP Guildford Surrey England

ISBN: (纸本)9783031732317;9783031732324

The costly and time-consuming annotation process to produce large training sets for modelling semantic LiDAR segmentation methods has motivated the development of semi-supervised learning (SSL) methods. However, such SSL approaches often concentrate on employing consistency learning only for individual LiDAR representations. This narrow focus results in limited perturbations that generally fail to enable effective consistency learning. Additionally, these SSL approaches employ contrastive learning based on the sampling from a limited set of positive and negative embedding samples. This paper introduces a novel semi-supervised LiDAR semantic segmentation framework called ItTakesTwo (IT2). IT2 is designed to ensure consistent predictions from peer LiDAR representations, thereby improving the perturbation effectiveness in consistency learning. Furthermore, our contrastive learning employs informative samples drawn from a distribution of positive and negative embeddings learned from the entire training set. Results on public benchmarks show that our approach achieves remarkable improvements over the previous state-of-the-art (SOTA) methods in the field. The code is available at: https://***/yyliu01/IT2.

关键词： Semi-supervised Learning LiDAR Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

CDAF3D: Cross-Dimensional Attention Fusion for Indoor 3D Object Detection 7th

CDAF3D: Cross-Dimensional Attention Fusion for Indoor 3D Obj...

引用

7th Chinese Conference on Pattern Recognition and computer Vision

作者： Wang, Shilin Huang, Hai Zhu, Yueyan Tang, Zhenqi Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing 100876 Peoples R China

ISBN: (纸本)9789819784929;9789819784936

3D object detection is a crucial task in computer vision and autonomous systems, which is widely utilized in robotics, autonomous driving, and augmented reality. With the advancement of input devices, researchers propose to use multimodal information to improve the detection accuracy. However, integrating 2D and 3D features effectively to harness their complementary nature for detection tasks is still a challenge. In this paper, we note that the complementary nature of geometric and visual texture information can effectively strengthen feature fusion, which plays a key role in detection. To this end, we propose the Cross-Dimensional Attention Fusion-based indoor 3D object detection method (CDAF3D). This method dynamically learns geometric information with corresponding 2D image texture details through a cross-dimensional attention mechanism, enabling the model to capture and integrate spatial and textural information effectively. Additionally, due to the nature of 3D object detection, where intersecting entities with different specific labels are unrealistic, we further propose Preventive 3D Intersect Loss (P3DIL). This loss enhances detection accuracy by addressing intersections between objects of different labels. We evaluate the proposed CDAF3D on the SUN RGB-D and Scannet v2 datasets. Our results achieve 78.2 mAP@0.25 and 66.5 mAP@0.50 on ScanNetV2 and 70.3 mAP@0.25 and 54.1 mAP@0.50 on SUN RGB-D. The proposed CDAF3D outperforms all the multi-sensor-based methods with 3D IoU thresholds of 0.25 and 0.5.

关键词： Indoor 3D Object Detection Fusion Features Point Cloud

来源：评论

学校读者我要写书评

暂无评论

Challenges of Multilingual Program Specification and Analysis 12th

Challenges of Multilingual Program Specification and Analysi...

引用

12th International Symposium on Leveraging Applications of Formal Methods, Verification and Validation

作者： Furia, Carlo A. Tiwari, Abhishek USI Univ Svizzera Italiana Software Inst Lugano Switzerland

ISBN: (纸本)9783031753794;9783031753800

Multilingual programs, whose implementations are made of different languages, are gaining traction especially in domains, such as web programming, that particularly benefit from the additional flexibility brought by using multiple languages. In this paper, we discuss the impact that the features commonly used in multilingual programming have on our capability of specifying and analyzing them. To this end, we first outline a few broad categories of multilingual programming, according to the mechanisms that are used for inter-language communication. Based on these categories, we describe several instances of multilingual programs, as well as the intricacies that formally reasoning about their behavior would entail. We also summarize the state of the art in multilingual program analysis, including the challenges that remain open. These contributions can help understand the lay of the land in multilingual program specification and analysis, and motivate further work in this area.

关键词： Specification languages

来源：评论

学校读者我要写书评

暂无评论

Foreground-Background Partitioning and Feature Fusion for Weakly Supervised Fine-Grained Image Recognition 7th

Foreground-Background Partitioning and Feature Fusion for We...

引用

7th Chinese Conference on Pattern Recognition and computer Vision

作者： Liu, Chenglin Li, Jiuliang Chen, Yanmin Luo, Jun Zhou, Mengyao Yang, Jian Li, Zhenfei Huazhong Agr Univ Coll Informat Wuhan 430070 Peoples R China

ISBN: (纸本)9789819785018;9789819785025

Fine-grained image recognition (FGIR) aims to distinguish visual objects belonging to different subclasses within the same category. Existing methods mainly focus on identifying discriminative regions and extracting the most prominent features. However, this approach leads to scale imbalance between the foreground and background of an image. And it tends to focus on extracting features from salient foreground regions while neglecting valuable information present in the background. To address these two challenges, we propose a weakly supervised foreground-background partitioning and feature fusion framework. Specifically, a foreground-background image partition module is employed to separate the foreground and background regions to resolve the scale imbalance in image. We incorporate a feature similarity calculation module to weigh the foreground and background features. To leverage the background information while capturing discriminative regions, we introduce a selective mask feature module. Comprehensive experiments on four popular and competitive datasets demonstrated the superiority of the proposed method in comparison with the state-of-the-art methods.

关键词： Fine-grained image recognition Foreground-background partitioning Scale imbalance

来源：评论

学校读者我要写书评

暂无评论

Empathizing Before Generation: A Double-Layered Framework for Emotional Support LLM 7th

Empathizing Before Generation: A Double-Layered Framework fo...

引用

7th Chinese Conference on Pattern Recognition and computer Vision

作者： Zhu, Jiahao Jiang, Zijian Zhou, Boyu Su, Jionglong Zhang, Naming Li, Zhihao Shantou Univ Shantou Peoples R China Chinese Univ Hong Kong Ma Liu Shui Hong Kong Peoples R China Mind Win Heart Robot Co Ltd Shenzhen Peoples R China Xian Jiaotong Liverpool Univ Suzhou Peoples R China

ISBN: (纸本)9789819784899;9789819784905

Large Language Models (LLMs) have found extensive use across different applications due to its diverse capabilities and proficiency in executing instructions. In the case of chatbots, they are frequently required to show empathy when used in the context of emotional support. However, to date their performance is still not satisfactory due to the lack of deep understanding of user related issues. Hence, we introduce the Empathizing Before Generation (EBG), a two-step learning framework that allows LLMs to analyze the chain of thought (COT) prior to generating a response. This model also enables the inference of the 24 emotions conveyed in the user's text as well as facilitates the generation of empathetic, high-quality and appropriate responses. We create a COT version of the dataset for sentiment inference by utilizing a publicly accessible sentiment dialogue. This dataset is then used as support for the training of two layers of EBG. Experiments indicate that models integrated with the EBG outperform other models in demonstrating empathy, with 98.2% and 92.8% accuracy in emotional attributes and labels respectively. Additionally, there is a notable enhancement in the model's capacity to comprehend COT instructions, infer emotions, and generate answers that are more satisfactory than other models.

关键词： Large language model Emotional support Chain of thought

来源：评论

学校读者我要写书评

暂无评论

Tackling Domain Generalization for Out-of-Distribution Endoscopic Imaging 15th

Tackling Domain Generalization for Out-of-Distribution Endos...

引用

15th International Workshop on Machine Learning in Medical Imaging

作者： Ali Teevno, Mansoor Ochoa-Ruiz, Gilberto Ali, Sharib Tecnol Monterrey Sch Engn & Sci Monterrey Mexico Univ Leeds Sch Comp Leeds W Yorkshire England

ISBN: (纸本)9783031732928;9783031732904

While recent advances in deep learning (DL) for surgical scene segmentation have yielded promising results on single-centre and single-imaging modality data, these methods usually do not generalise to unseen distribution or unseen modalities. Even though human experts can identify visual appearances, DL methods often fail to do so if data samples do not follow the similar data distribution. Current literature for tackling domain gaps in modality changes has been done mostly for natural scene data. However, these methods cannot be directly applied to the endoscopic data as the visual cues are very limited compared to the natural scene data. In this work, we exploit the style and content information in the image by performing instance normalization and feature covariance mapping techniques for preserving robust and generalizable feature representations. Further, to eliminate the risk of removing salient feature representation associated with the objects of interest, we introduce a restitution module within the feature learning ResNet backbone that allows the retention of useful task-relevant features. Our proposed method obtained 13.7% improvement over the baseline DeepLabv3+ and nearly 8% improvement on recent state-of-the-art (SOTA) methods for the target (different modality) set of EndoUDA polyp dataset. Similarly, our method achieved 19% improvement over the baseline and 6% over best performing SOTA on EndoUDA Barrett's esophagus (BE) data.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection 7th

CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Po...

引用

7th Chinese Conference on Pattern Recognition and computer Vision

作者： Li, Xuejing Zhang, Weijia Ma, Chao Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9789819785070;9789819785087

Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and novel classes with very few annotations. Thus far, this challenging task has been approached using prototype learning, but the performance remains far from satisfactory. We find that in existing methods, the prototypes are only loosely constrained and lack of fine-grained awareness of the semantic and geometrical correlation embedded within the point cloud space. To mitigate these issues, we propose to leverage the inherent contrastive relationship within the semantic and geometrical subspaces to learn more refined and generalisable prototypical representations. To this end, we first introduce contrastive semantics mining, which enables the network to extract discriminative categorical features by constructing positive and negative pairs within training batches. Meanwhile, since point features representing local patterns can be clustered into geometric components, we further propose to impose contrastive relationship at the primitive level. Through refined primitive geometric structures, the transferability of feature encoding from base to novel classes is significantly enhanced. The above designs and insights lead to our novel Contrastive Prototypical VoteNet (CP-VoteNet). Extensive experiments on two FS3D benchmarks FS-ScanNet and FS-SUNRGBD demonstrate that CP-VoteNet surpasses current state-of-the-art methods by considerable margins across different FS3D settings. Further ablation studies conducted corroborate the rationale and effectiveness of our designs.

关键词： Few-shot point cloud object detection Contrastive learning Prototype learning

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 << < 112 113 114 115 116 117 118 119 120 121 > >>

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：