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

578 篇 会议
2 篇 期刊文献

馆藏范围

580 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

118 篇 工学
- 76 篇 计算机科学与技术...
- 53 篇 软件工程
- 38 篇 建筑学
- 37 篇 土木工程
- 37 篇 测绘科学与技术
- 13 篇 电气工程
- 11 篇 控制科学与工程
- 9 篇 光学工程
- 9 篇 电子科学与技术（可...
- 8 篇 信息与通信工程
- 8 篇 石油与天然气工程
- 7 篇 机械工程
- 7 篇 仪器科学与技术
- 7 篇 安全科学与工程
- 6 篇 材料科学与工程（可...
- 4 篇 化学工程与技术
- 4 篇 交通运输工程
44 篇 管理学
- 31 篇 管理科学与工程(可...
- 25 篇 工商管理
- 15 篇 图书情报与档案管...
32 篇 理学
- 14 篇 数学
- 12 篇 物理学
- 5 篇 化学
- 4 篇 统计学（可授理学、...
10 篇 法学
- 8 篇 社会学
9 篇 经济学
- 9 篇 应用经济学
8 篇 医学
- 8 篇 基础医学(可授医学...
- 8 篇 临床医学
- 8 篇 公共卫生与预防医...
4 篇 教育学
- 4 篇 教育学
3 篇 农学
1 篇 文学

主题

235 篇 visualization
161 篇 visual analytics
142 篇 accuracy
125 篇 data models
106 篇 real-time system...
75 篇 feature extracti...
72 篇 training
71 篇 data visualizati...
68 篇 deep learning
56 篇 speech processin...
50 篇 computational mo...
49 篇 predictive model...
49 篇 convolutional ne...
47 篇 signal processin...
42 篇 analytical model...
41 篇 adaptation model...
39 篇 transformers
35 篇 semantics
33 篇 data mining
32 篇 robustness

机构

5 篇 department of el...
4 篇 symbiosis instit...
4 篇 department of bi...
3 篇 department of co...
3 篇 hindustan instit...
3 篇 rajalakshmi engi...
3 篇 school of comput...
3 篇 chitkara univers...
3 篇 department of el...
3 篇 data analytics h...
3 篇 department of it...
3 篇 saveetha school ...
3 篇 department of el...
3 篇 saveetha school ...
2 篇 department of co...
2 篇 faculty of compu...
2 篇 shanghai jiao to...
2 篇 department of co...
2 篇 department of co...
2 篇 nagpur campus pu...

作者

7 篇 n. mohankumar
5 篇 r. sathya
5 篇 m. rajmohan
4 篇 asha sundaram
4 篇 p kumar
3 篇 l.n. jayanthi
3 篇 senthil pandi s.
3 篇 mustafa keskin
3 篇 alp a. yalman
3 篇 k. karthikeyan
3 篇 arpana prasad
3 篇 v asha
3 篇 rajmohan m.
3 篇 mohankumar n.
3 篇 enis teper
3 篇 emre rençberoğlu
3 篇 sinan keçeci
3 篇 t. r. ganeshbabu
2 篇 s. muthumarilaks...
2 篇 chuan-xian ren

语言

482 篇 英文
98 篇 其他
9 篇 中文

检索条件"任意字段=2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025"

共 580 条记录，以下是381-390 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：

METAMORPH - A Metamodeling Approach for Robot Morphology

METAMORPH - A Metamodeling Approach for Robot Morphology

引用

ACM/IEEE international conference on Human-Robot Interaction (HRI)

作者： Rachel Ringe Robin Nolte Nima Zargham Robert Porzel Rainer Malaka Digital Media Lab University of Bremen Bremen Germany

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

Robot appearance crucially shapes Human-Robot Interaction (HRI) but is typically described via broad categories like anthropomorphic, zoomorphic, or technical. More precise approaches focus almost exclusively on anthropomorphic features, which fail to classify robots across all types, limiting the ability to draw meaningful connections between robot design and its effect on interaction. In response, we present METAMORPH, a comprehensive framework for classifying robot morphology. Using a metamodeling approach, METAMORPH was synthesized from 222 robots in the IEEE Robots Guide, offering a structured method for comparing visual features. This model allows researchers to assess the visual distances between robot models and explore optimal design traits tailored to different tasks and contexts.

关键词： visualization Systematics Shape Metamodeling Human-robot interaction Morphology data models Robots Context modeling Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Research on Design and Optimization of Personalized visual Interaction System Based on Affective Computing

Research on Design and Optimization of Personalized Visual I...

引用

Digital Analysis and Processing, Intelligent Computation (DAPIC), international conference on

作者： Hongmei Wang Xiaoou He College of Fine Arts and Design University of Jinan Jinan Shandong China School of Art Soochow University Suzhou China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

This study plans to build and improve personalized visual interaction models, enhance the recognition accuracy and instant feedback effect of the system in emotion detection, train and test the emotion recognition model based on the AffectNet dataset, implement emotion analysis in combination with convolutional neural network technology, and use data enhancement and cross-validation technology to improve the generalization ability of the model. The key to system performance evaluation is to comprehensively consider the accuracy of emotion recognition, response speed, resource usage, and user experience. The test results show that the optimized system generally exceeds 9 5 % in terms of emotion recognition accuracy, the processing speed is maintained in the range of 220 milliseconds to 250 milliseconds, the CPU occupancy rate and memory usage are in an appropriate range, and the quality of user interaction is maintained. After analyzing the evaluation feedback after user use, the emotion recognition and response functions of the system are highly praised.

关键词： Emotion recognition visualization Analytical models Accuracy System performance data models User experience Real-time systems Convolutional neural networks Resource management

来源：评论

学校读者我要写书评

暂无评论

Learning Rank Constrained Exposure Correction from Unpaired data

Learning Rank Constrained Exposure Correction from Unpaired ...

引用

international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhuoyue Gong Qing Zhang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper presents a novel unpaired learning based exposure correction network that can robustly deal with both under- and over-exposed images. Given an input image in any exposure conditions, we first obtain its intermediate under- and over-exposure corrected versions by predicting dual illuminations for Retinex-based enhancement, the two outputs together with the original input are then fed to a multi-exposure fusion module to adaptively locate the best-exposed regions in the three images and then seamlessly fuse them into a well-exposed output. To ensure that the generated result is visually natural and free of disturbing visual artifacts such as loss of details and contrast degradation, we introduce a novel rank loss. Experiments show that our method outperforms existing methods in terms of both quantitative and qualitative results.

关键词： Degradation visualization Fuses Lighting Estimation Speech enhancement Signal processing Benchmark testing Acoustics Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Mitigating data Sparsity in Point-of-Interest Recommendation Systems Using Multi-Modal User Profiles

Mitigating Data Sparsity in Point-of-Interest Recommendation...

引用

international ECTI Northern Section conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI-NCON)

作者： Sudarat Arthan Kreangsak Tamee Department of Computer Science and Information Technology Naresuan University Phitsanulok Thailand Department of Computer Science and Information Technology Naresuan University Research Center for Academic Excellence in Nonlinear Analysis and Optimization Naresuan University Phitsanulok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

This study presents a solution to the data sparsity issue in POI recommendation systems by introducing a multi-modal user profile approach called visual-Textual Collaborative Filtering (VTCF). VTCF integrates textual POI descriptions from Wikipedia with user-generated photos to improve the representation of user preferences. Using publicly available geo-tagged photo datasets, we compared VTCF with various baseline methods, including traditional user-based collaborative filtering and approaches based on visual and contextual preferences. The experimental results demonstrate that our approach successfully addresses the challenges of sparse check-in data, resulting in more accurate and relevant recommendations. The findings suggest that VTCF is a promising method for improving recommendation accuracy. Future work could explore additional data sources and techniques to further enhance POI recommendation systems. Moreover, computational trade-offs and scalability should be considered, as integrating textual and visual data adds system complexity. Strategies such as batch processing and parallel computation could help mitigate these issues for large-scale applications.

关键词： visualization Accuracy Collaborative filtering Soft sensors Scalability Batch production systems Robustness Complexity theory Resource management Recommender systems

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Advertisement Design: A PIL-Based Approach for Quality and Performance Analysis

AI-Powered Advertisement Design: A PIL-Based Approach for Qu...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), international conference

作者： Harshitha Chilupuri G. Ramesh J. Praveen Venkataramaiah Gude Dept. of Artificial Intelligence and Machine Learning Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Dept. of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Department of Electrical and Electronics Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad Telangana India GP Technologies LLC U.S.A.

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The paper presents the development of a data Science solution that applies generative AI models in order to create high-quality images to be used in visual marketing and advertising. Using the Python library PIL (Pillow) along with machine learning frameworks, the solution combines predefined product images with the selected backgrounds, enhancing image synthesis techniques for more appealing and contextually relevant visuals. This leads to improved efficiency and effectiveness in the creation of content by automatically placing product images onto the background images used in marketing campaigns. The approach demonstrated a 98.06% SSIM (Structural similarity Index) score, indicating significant visual quality improvement. Initial results suggest a 15% enhancement in visual appeal compared to traditional image creation methods.

关键词： visualization Image transformation Generative AI data science Libraries Performance analysis Indexes Advertising Optimization Python

来源：评论

学校读者我要写书评

暂无评论

Integration of Large Language Models and Computer Vision Algorithms in LMS: A Methodology for Automated Verification of Software Tasks and Multimodal Analysis of Educational data

Integration of Large Language Models and Computer Vision Alg...

引用

international Russian Smart Industry conference (SmartIndustryCon)

作者： E. I. Markin V. V. Zuparova A. I. Martyshkin Penza state technological University PSTU Penza Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

This paper presents a study on the design and development of a learning management system (LMS) integrated with large language models (LLMs) and image recognition/generation algorithms to automate software task validation and multimodal educational data analysis. The purpose of the development is to improve the quality of feedback for learners, deepen the understanding of errors made and expand the capabilities of the system by synthesizing formal LLM models and visual processing algorithms. The system is based on the use of domestic LLMs such as GigaChat and YandexGPT, Retrieval-Augmented Generation (RAG) technology, and modern computer vision algorithms. The system architecture is described, including GitVerse for code storage, GitVerse Actions for automated testing of solutions in Docker containers, and image processing modules for analyzing and generating visual data in the educational process. The conducted experiment demonstrates the effectiveness of the integrative approach, which allows to improve the quality of feedback and increase the performance of students. Prospects for further research include optimization of computational resources and development of techniques for integrated analysis of multimodal educational data.

关键词： visualization Computer vision Codes Image recognition Costs Large language models Computational modeling Software algorithms Trajectory Testing

来源：评论

学校读者我要写书评

暂无评论

VisTa: visual-contextual and Text-augmented Zero-shot Object-level OOD Detection

VisTa: Visual-contextual and Text-augmented Zero-shot Object...

引用

international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Bin Zhang Xiaoyang Qu Guokuan Li Jiguang Wan Jianzong Wang Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China Ping An Technology (Shenzhen) Co. Ltd Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

As object detectors are increasingly deployed as black-box cloud services or pre-trained models with restricted access to the original training data, the challenge of zero-shot object-level out-of-distribution (OOD) detection arises. This task becomes crucial in ensuring the reliability of detectors in open-world settings. While existing methods have demonstrated success in image-level OOD detection using pre-trained vision-language models like CLIP, directly applying such models to object-level OOD detection presents challenges due to the loss of contextual information and reliance on image-level alignment. To tackle these challenges, we introduce a new method that leverages visual prompts and text-augmented in-distribution (ID) space construction to adapt CLIP for zero-shot object-level OOD detection. Our method preserves critical contextual information and improves the ability to differentiate between ID and OOD objects, achieving competitive performance across different benchmarks.

关键词： Training visualization Adaptation models Training data Detectors Benchmark testing Signal processing Reliability Speech processing Context modeling

来源：评论

学校读者我要写书评

暂无评论

Exploratory data analysis to study the impact of MGNREGA on employment generation

Exploratory data analysis to study the impact of MGNREGA on ...

引用

Emerging Systems and Intelligent Computing (ESIC), international conference on

作者： Nandini Hazarika Balin Hazarika Department of Computer Science and Engineering Dayananda Sagar University Bengaluru India Department of Commerce Girijananda Chaudhury University Guwahati India

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

The Mahatma Gandhi National Rural Employment Guarantee Act (MGNREGA) was designed the enhance the livelihood of rural households all across India, providing opportunities for wage employment. In recent years the program has faced a lot of challenges in terms of providing 100 days of employment to all the rural households. There has been a decline in wage employment opportunities beyond the year 2020-2021, due to ineffective management practices. In order to dive deeper into the issue, the researcher performs data-driven analysis of the MGNREGA scheme utilizing the open-source data available in the MGNREGA official website, focusing on the years 2014 to 2024, exploring the contributing factors for the decline in the scheme’s effectiveness. The researcher uncovers hidden valuable insights and visually represented them, by performing Exploratory data Analysis on the data obtained. The data and insights generated are visually represented by employing various python libraries in Jupyter Notebook, identifying trends, correlations among variables and patterns, as well as shedding light on the scheme’s performance and area of improvement. By performing in depth analysis and visualization of the data, the researcher aims to provide valuable insights on the effectiveness and challenges faced by the MGNREGA scheme, ensuring effective implementation of the scheme. Ensuring the improvement in the economic wellbeing and livelihoods of the rural communities across India, the insights gained from the visual representation of the data, allows the policy makers to take well informed decisions, ultimately ensuring the scheme’s success.

关键词： Economics visualization data analysis Pandemics Government Livelihood data visualization Market research Libraries Python

来源：评论

学校读者我要写书评

暂无评论

Multimodal Sentiment Analysis Using TriFusion Attention Network

Multimodal Sentiment Analysis Using TriFusion Attention Netw...

引用

international conference on Wireless Communications, Signal Processing and Networking (WiSPNET)

作者： Prasika L Dinesh Kumar S Manoj S Department of Artificial Intelligence and Data Science Mepco Schlenk Engineering College Sivakasi Tamil Nadu India

ISBN: (数字)9798331524227

ISBN: (纸本)9798331524234

Multimodal sentiment analysis, which uses data from several modalities like text, audio, and video, has emerged as crucial. It is difficult to combine these many modalities while dealing with noise and redundancy, both of which can impact performance. We propose TriFAN (Trimodal Fusion Attention Network), a cutting-edge method intended to improve multi-modal sentiment analysis, as a solution to these problems. TriFAN has a two-channel architecture: the first channel captures complex cross-modal interactions using attention mechanisms, and the second channel concentrates on removing unnecessary visual and audio elements to leave only the most significant and distinctive information. Our method achieves a 95.6% accuracy rate on the CMU-MOSI dataset, demonstrating its capacity to merge multi-modal data and improve sentiment prediction.

关键词： Wireless communication Sentiment analysis visualization Accuracy Attention mechanisms Scalability Redundancy Noise Complexity theory Resilience

来源：评论

学校读者我要写书评

暂无评论

Semantic Graph Embedded Energy Minimization Learning for Scene Graph Generation

Semantic Graph Embedded Energy Minimization Learning for Sce...

引用

international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jinghang Chen Chi Zhang Yuehu Liu Le Wang Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China National Engineering Research Center for Visual Information and Applications National Key Laboratory of Human-Machine Hybrid Augmented Intelligence

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The performance of current scene graph generation models is affected by training with cross-entropy loss, exacerbating the problem of prediction bias stemming from biased training data. Energy-based model adopts a learning method for joint image and scene graph to alleviate this challenge. However, this method only focuses on the visual features of images, neglecting the rich relation information contained in the semantic space. To address this issue, we innovatively employ powerful pre-trained large models to realize a simple yet effective semantic graph embedded energy minimization framework for the SGG task. Specifically, we use large models to generate image descriptions and extract relation triplets, which are then transformed into semantic graphs with entities as nodes and relations as edges. Moreover, by mapping these graphs into the same space using GNN to learn the minimal energy value, our approach enables SGG model to learn structural information in both semantic and visual spaces. We validate the effectiveness and efficiency of our method on the SGG benchmark visual Genome dataset. Compared with prevailing models and EBM, we achieve a significant performance improvement of up to 2.99% and 2.24%, respectively.

关键词： Training Learning systems visualization Image edge detection Semantics Training data Signal processing Predictive models Minimization Speech processing

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58页 << < 35 36 37 38 39 40 41 42 43 44 > >>

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：