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

1,039 篇 会议
40 篇 期刊文献
6 册 图书

馆藏范围

1,085 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

470 篇 工学
- 329 篇 计算机科学与技术...
- 211 篇 软件工程
- 85 篇 电气工程
- 64 篇 控制科学与工程
- 51 篇 机械工程
- 33 篇 信息与通信工程
- 26 篇 生物医学工程（可授...
- 25 篇 动力工程及工程热...
- 25 篇 石油与天然气工程
- 23 篇 仪器科学与技术
- 21 篇 土木工程
- 20 篇 化学工程与技术
- 16 篇 电子科学与技术（可...
- 15 篇 生物工程
- 14 篇 光学工程
- 14 篇 建筑学
- 14 篇 安全科学与工程
- 13 篇 测绘科学与技术
192 篇 理学
- 107 篇 数学
- 71 篇 物理学
- 27 篇 统计学（可授理学、...
- 22 篇 系统科学
- 17 篇 化学
- 16 篇 生物学
79 篇 管理学
- 61 篇 管理科学与工程(可...
- 31 篇 工商管理
- 25 篇 图书情报与档案管...
58 篇 医学
- 47 篇 临床医学
- 16 篇 特种医学
12 篇 经济学
- 12 篇 应用经济学
7 篇 教育学
5 篇 农学
4 篇 法学
3 篇 艺术学

主题

502 篇 visualization
245 篇 optimization
108 篇 data visualizati...
65 篇 accuracy
61 篇 feature extracti...
58 篇 computational mo...
57 篇 training
45 篇 three-dimensiona...
43 篇 robustness
41 篇 cameras
37 篇 real-time system...
35 篇 deep learning
31 篇 machine learning
30 篇 data models
27 篇 optimization met...
27 篇 measurement
27 篇 solid modeling
26 篇 predictive model...
26 篇 image color anal...
23 篇 rendering (compu...

机构

3 篇 department of cs...
3 篇 school of comput...
3 篇 school of comput...
3 篇 college of compu...
3 篇 maharishi school...
3 篇 university of br...
3 篇 department of co...
3 篇 new york univers...
2 篇 univ granada dep...
2 篇 univ texas texas...
2 篇 vrvis res ctr au...
2 篇 halliburton unit...
2 篇 department of co...
2 篇 centre of resear...
2 篇 nanjing universi...
2 篇 seoul natl univ
2 篇 chongqing munici...
2 篇 school of comput...
2 篇 department of co...
2 篇 department of co...

作者

3 篇 ertl thomas
3 篇 vladislav golyan...
3 篇 grimme christian
3 篇 r. raja subraman...
3 篇 qu huamin
3 篇 kerschke pascal
2 篇 takeshi hatanaka
2 篇 yasuyuki matsush...
2 篇 zhou chenn q.
2 篇 brian c. lovell
2 篇 a. sakly
2 篇 nassir navab
2 篇 bobick a
2 篇 barthel kai uwe
2 篇 velasco f
2 篇 vucinic dean
2 篇 gaither kelly p.
2 篇 xi wang
2 篇 lin ming c.
2 篇 rubio-sanchez m.

语言

1,071 篇 英文
12 篇 其他
3 篇 中文
1 篇 法文
1 篇 俄文

检索条件"任意字段=Conference on Visualization and Optimization Techniques"

共 1085 条记录，以下是31-40 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：

Hybrid Deep Learning Model with ResNet50 and SVM for Diabetic Retinopathy Classification

Hybrid Deep Learning Model with ResNet50 and SVM for Diabeti...

引用

Electronics and Renewable Systems (ICEARS), International conference on

作者： Sreedhar Kollem Belide Preethi Goli Kiran Kumar Rudrarapu Sai Prasad Ksheerasagar Praneeth Samineni Peddakrishna Dept. of ECE SR University Warangal India School of Electronics Engineering VIT-AP University Andhra Pradesh India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Diabetic eye diseases such diabetic retinopathy, cataracts, and macular edema are the primary risks to visual acuity if they are not appropriately detected. In order to guarantee appropriate action and lower the risk of visual impairment, early diagnosis is crucial. This paper introduces a novel hybrid deep learning framework for classifying diabetic eye disorders by integrating Convolutional Neural Networks (CNNs) with Support Vector Machines (SVMs). The model aims to enhance the classification by incorporating an SVM algorithm at the last layers of a deep neural network. This framework basically consists of three major steps: data preprocessing, feature extraction, and then classification. The ResNet50 architecture underwent systematic optimization and calibration to enhance detection accuracy across various stages of diabetic retinopathy. The findings indicate that the proposed method surpasses traditional techniques in achieving higher accuracy in the identification of diabetic ocular conditions, thereby facilitating improved management and treatment strategies.

关键词： Deep learning Diabetic retinopathy visualization Accuracy Systematics Visual impairment Support vector machine classification Eye diseases Convolutional neural networks Residual neural networks

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

Advanced Pest Identification: An Efficient Deep Learning Approach Using VGG Networks

Advanced Pest Identification: An Efficient Deep Learning App...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE conference on

作者： K. Lakshminadh Divvela Chandu Venkateswara Guptha Jujjuri Sai Kandula Rajesh Sireesha Moturi Yaragani Neelima Dodda Venkata Reddy Department of CSE Narasaraopeta Engineering College Narasaraopeta India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

Accurate pest identification is crucial for both effective pest management and crop protection. Pests must be found early in order to minimise damage and guarantee crop security. Conventional techniques typically entail visual examination and professional involvement, which might be time-consuming and susceptible to errors by humans. On the other hand, deep learning-powered high-performance systems can now more accurately identify pests thanks to developments in computer vision. In this work, we employed the Keras-based deep learning models VGG16 and VGG19 to construct a passive pest detection system. We greatly improved the efficacy of these models in identifying pest species by using strategies such data augmentation, model optimization, and modification of validated models. The VGG16 model produced an amazing accuracy rate of 99.8% and VGG19 model produced an accuracy of 96.8 % in our testing.

关键词： Deep learning visualization Accuracy Computational modeling Transfer learning Crops Data augmentation Data models Agriculture Convolutional neural networks

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

DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing

DiTAS: Quantizing Diffusion Transformers via Enhanced Activa...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Zhenyuan Dong Sai Qian Zhang New York University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Diffusion Transformers (DiTs) have recently attracted significant interest from both industry and academia due to their enhanced capabilities in visual generation, surpassing the performance of traditional diffusion models that employ U-Net. However, the improved performance of DiTs comes at the expense of higher parameter counts and implementation costs, which significantly limits their deployment on resource-constrained devices like mobile phones. We propose DiTAS, a data-free post-training quantization (PTQ) method for efficient DiT inference. DiTAS relies on the proposed temporal-aggregated smoothing techniques to mitigate the impact of the channel-wise outliers within the input activations, leading to much lower quantization error under extremely low bitwidth. To further enhance the performance of the quantized DiT, we adopt the layer-wise grid search strategy to optimize the smoothing factor. Moreover, we integrate a training-free LoRA module for weight quantization, leveraging alternating optimization to minimize quantization errors without additional fine-tuning. Experimental results demonstrate that our approach enables 4-bit weight, 8-bit activation (W4A8) quantization for DiTs while maintaining comparable performance as the full-precision model. Code is available at https://***/DZY122/DiTAS

关键词： Performance evaluation Industries visualization Quantization (signal) Smoothing methods Transformers Search problems Diffusion models Mobile handsets optimization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Deviation Learning for Visual Anomaly Detection with Data Contamination

Adaptive Deviation Learning for Visual Anomaly Detection wit...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Anindya Sundar Das Guansong Pang Monowar Bhuyan Urneå University Sweden Singapore Management University Singapore

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Visual anomaly detection targets to detect images that notably differ from normal pattern, and it has found extensive application in identifying defective parts within the manufacturing industry. These anomaly detection paradigms predominantly focus on training detection models using only clean, unlabeled normal samples, assuming an absence of contamination; a condition often unmet in real-world scenarios. The performance of these methods significantly depends on the quality of the data and usually decreases when exposed to noise. We introduce a systematic adaptive method that employs deviation learning to compute anomaly scores end-to-end while addressing data contamination by assigning relative importance to the weights of individual instances. In this approach, the anomaly scores for normal instances are designed to approximate scalar scores obtained from the known prior distribution. Meanwhile, anomaly scores for anomaly examples are adjusted to exhibit statistically significant deviations from these reference scores. Our approach incorporates a constrained optimization problem within the deviation learning framework to update instance weights, resolving this problem for each mini-batch. Comprehensive experiments on the MVTec and VisA benchmark datasets indicate that our proposed method surpasses competing techniques and exhibits both stability and robustness in the presence of data contamination. 1 1 Our source code is available at https://***/anindyasdas/ADL4VAD/

关键词： Training visualization Systematics Source coding Noise Stability analysis Robustness Contamination Anomaly detection optimization

来源：评论

学校读者我要写书评

暂无评论

Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models

Test-Time Low Rank Adaptation via Confidence Maximization fo...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Raza Imam Hanan Gani Muhammad Huzaifa Karthik Nandakumar Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) UAE

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time involves tuning learnable prompts, i.e., test-time prompt tuning. This paper introduces Test-Time Low-rank adaptation (TTL) as an alternative to prompt tuning for zero-shot generalization of large-scale VLMs. Taking inspiration from recent advancements in efficiently fine-tuning large language models, TTL offers a test-time parameter-efficient adaptation approach that updates the attention weights of the transformer encoder by maximizing prediction confidence. The self-supervised confidence maximization objective is specified using a weighted entropy loss that enforces consistency among predictions of augmented samples. TTL introduces only a small amount of trainable parameters for low-rank adapters in the model space while keeping the prompts and backbone frozen. Extensive experiments on a variety of natural distribution and cross-domain tasks show that TTL can outperform other techniques for test-time optimization of VLMs in strict zero-shot settings. Specifically, TTL outperforms test-time prompt tuning baselines with a significant improvement on average. Our code is available at https://***/Razaimam45/TTLTest-Time-Low-Rank-Adaptation.

关键词： Adaptation models visualization Computer vision Codes Large language models Transformers Entropy Tuning optimization

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

Fire Detection and Autonomous Evacuation Guidance System

Fire Detection and Autonomous Evacuation Guidance System

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International conference on

作者： Sandyarani Vadlamudi D Roja Ramani S Preetham Ganesh Dagadi Nipun Goyal Harshavardhan V Mantri Department of AIML New Horizon College of Engineering Bengaluru India Department of CSE New Horizon College of Engineering Bengaluru India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Effective fire emergency responses are critical to ensuring safety and minimizing damage. This research exhibits an innovative fire detection and evacuation system that utilizes deep-learning and real-time video analysis to improve response times and efficiency. Utilizing convolution neural nets (CNNs), the system is able to detect fires with high precision and minimal delay, while dynamically generating evacuation plans depending on the fire's location. The system integrates advanced machine learning techniques to analyse building layouts and determine the safest, shortest evacuation routes. This information is conveyed to occupants via a public address system, enabling a streamlined and well-coordinated evacuation process. By combining real-time fire detection with intelligent route optimization, the system offers a significant advancement over traditional fire safety technologies. The paper also addresses key challenges such as processing latency and the system's ability to operate effectively in real-world conditions. Experimental results demonstrate the reliability of the CNN model—Inception V3 for fire recognition and Dijkstra algorithm for route planning—in both accuracy and speed aspects. The system's ability to handle complex visual data while maintaining operational efficiency is a highlight of this research. Along with technical details, the research explores the practical implications of implementing this system in various environments. Key challenges include maintaining low latency in video streaming and fire detection, as well as ensuring the effectiveness of the escape route analysis in complex environments. Future improvements focus on scalability, with plans to expand the system's capabilities to support multi-camera setups and larger buildings, making it adaptable for widespread use.

关键词： visualization Scalability Buildings Neural networks Streaming media Real-time systems Convolutional neural networks Time factors Reliability optimization

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Visual Anagram as Multi-task Learning

Diffusion-based Visual Anagram as Multi-task Learning

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Zhiyuan Xu Yinhe Chen Huan-ang Gao Weiyan Zhao Guiyu Zhang Hao Zhao Institute for AI Industry Research (AIR) Tsinghua University University of Chinese Academy of Sciences Central South University Beijing Institute of Technology

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Visual anagrams are images that change appearance upon transformation, like flipping or rotation. With the advent of diffusion models, generating such optical illusions can be achieved by averaging noise across multiple views during the reverse denoising process. However, we observe two critical failure modes in this approach: (i) concept segregation, where concepts in different views are independently generated, which can not be considered a true anagram, and (ii) concept domination, where certain concepts overpower others. In this work, we cast the visual anagram generation problem in a multi-task learning setting, where different viewpoint prompts are analogous to different tasks, and derive denoising trajectories that align well across tasks simultaneously. At the core of our designed framework are two newly introduced techniques, where (i) an anti-segregation optimization strategy that promotes overlap in cross-attention maps between different concepts, and (ii) a noise vector balancing method that adaptively adjusts the influence of different tasks. Additionally, we observe that directly averaging noise predictions yields suboptimal performance because statistical properties may not be preserved, prompting us to derive a noise variance rectification method. Extensive qualitative and quantitative experiments demonstrate our method's superior ability to generate visual anagrams spanning diverse concepts.

关键词： visualization Noise Noise reduction Multitasking Optical imaging Diffusion models Vectors Trajectory Optical noise optimization

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109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：