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

1,724 篇 会议
38 册 图书
31 篇 期刊文献

馆藏范围

1,793 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,106 篇 工学
- 899 篇 计算机科学与技术...
- 452 篇 软件工程
- 279 篇 光学工程
- 278 篇 电气工程
- 218 篇 控制科学与工程
- 127 篇 机械工程
- 114 篇 信息与通信工程
- 80 篇 生物工程
- 54 篇 电子科学与技术（可...
- 53 篇 生物医学工程（可授...
- 43 篇 材料科学与工程（可...
- 38 篇 仪器科学与技术
- 35 篇 交通运输工程
- 35 篇 安全科学与工程
- 19 篇 动力工程及工程热...
- 18 篇 力学（可授工学、理...
- 15 篇 建筑学
- 15 篇 土木工程
- 15 篇 网络空间安全
486 篇 理学
- 392 篇 物理学
- 107 篇 数学
- 87 篇 生物学
- 26 篇 统计学（可授理学、...
161 篇 医学
- 156 篇 临床医学
- 28 篇 基础医学(可授医学...
- 19 篇 药学(可授医学、理...
140 篇 管理学
- 109 篇 管理科学与工程(可...
- 38 篇 图书情报与档案管...
- 30 篇 工商管理
18 篇 经济学
- 18 篇 应用经济学
15 篇 农学
12 篇 法学
12 篇 教育学
6 篇 文学
5 篇 艺术学
2 篇 军事学

主题

476 篇 computer vision
397 篇 machine vision
166 篇 machine learning
114 篇 deep learning
99 篇 cameras
90 篇 image processing
90 篇 training
82 篇 feature extracti...
66 篇 object detection
65 篇 computational mo...
63 篇 robot vision sys...
60 篇 accuracy
57 篇 artificial intel...
56 篇 neural networks
54 篇 visualization
51 篇 pattern recognit...
42 篇 computer archite...
40 篇 image segmentati...
37 篇 support vector m...
35 篇 robustness

机构

6 篇 center for machi...
5 篇 georgia inst tec...
4 篇 shanghai jiao to...
4 篇 massey universit...
4 篇 university of re...
4 篇 centro de invest...
3 篇 university of sc...
3 篇 machine vision a...
3 篇 univ michigan an...
3 篇 chongqing univer...
3 篇 vishwakarma inst...
3 篇 zhejiang univers...
3 篇 indian institute...
3 篇 microsoft resear...
3 篇 univ porto fac e...
3 篇 chitkara univers...
3 篇 south china norm...
3 篇 wuhan university
3 篇 faculty of scien...
3 篇 institute of aut...

作者

5 篇 lai shang-hong
4 篇 fang ming
4 篇 de-shuang huang
4 篇 alexander gelbuk...
4 篇 kweon in so
4 篇 rodner erik
4 篇 denzler joachim
3 篇 r.m. hodgson
3 篇 koshimizu h
3 篇 sergey vityazev
3 篇 sviatov kirill
3 篇 watanabe takashi
3 篇 r. osorio
3 篇 wu qi
3 篇 wu xintao
3 篇 kohei arai
3 篇 hongbin zha
3 篇 j. amat
3 篇 fujiwara takayuk...
3 篇 azar ahmad taher

语言

1,748 篇 英文
37 篇 其他
14 篇 中文
1 篇 法文
1 篇 土耳其文

检索条件"任意字段=Conference on Machine Vision and Its Optomechatronic Applications"

共 1793 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：

Utilizing Pretrained vision Transformers and Large Language Models for Epileptic Seizure Prediction

Utilizing Pretrained Vision Transformers and Large Language ...

引用

conference on Data Science and machine Learning applications (CDMA)

作者： Paras Parani Umair Mohammad Fahad Saeed Knight Foundation School of Computing and Information Sciences Florida International University Miami FL USA

ISBN: (数字)9798331539696

ISBN: (纸本)9798331539702

Repeated unprovoked seizures are a major source of concern for people with epilepsy. Predicting seizures before they occur is of interest to both machine-learning scientists as well as clinicians, and is an active area of research. The variability of EEG sensors, type of seizures, and specialized knowledge required for annotating the data complicates the large-scale annotation process essential for supervised predictive models. To address these challenges, we propose the use of vision Transformers (Vits) and Large Language Models (LLMs) that were originally trained on publicly available image or text data. Our work leverages these pre-trained models by refining the input, embedding, and classification layers in a minimalistic fashion to predict seizures. Our results demonstrate that LLMs outperforms the Vits in patient-independent seizure prediction achieving a sensitivity of 79.02% which is 8% higher compared to Vits and about 12% higher compared to a custom-designed ResNet-based model. Our work demonstrates the successful feasibility of pre-trained models for seizure prediction with its potential for improving the quality of life of people with epilepsy. Our code and related materials are available open-source at: https://***/pcdslab/UtilLLM_EPS/

关键词： Computer vision Sensitivity Large language models Refining Epilepsy machine learning Predictive models Brain modeling Transformers Sensors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Industrial Automation Flexibility Through Neural Network-Empowered machine vision applications 1st

Enhancing Industrial Automation Flexibility Through Neural N...

引用

1st International conference on Artificial Intelligence and its applications, ICAIA 2023

作者： George, Navin M. Rosero, Evelyn Mayakannan, S. Shameem, A. Divya, S. Arul, N. Electronics and Communication Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore641114 India Riobamba060155 Ecuador Department of Mechanical Engineering Vidya Vikas College of Engineering and Technology Namakkal Tamilnadu Tiruchengode India AMET Business School AMET University Tamilnadu Chennai India Erode Tamil Nadu Perundurai638057 India Department of Mechatronics Engineering Sona College of Technology Tamilnadu Salem India

ISBN: (纸本)9783031843969

vision-based systems provide non-contact sensory input for processing and feedback, expanding the capabilities of industrial automation applications. Prediction using ANNs aids such conformities in navigating nonlinear computational landscapes. They map the plethora of potential outcomes or zones of uncertainty introduced by the system’s constituents onto a set of feasible options for action. A measure of intelligence is transferred to robotic systems through the use of trained networks. Two uses of machine vision are presented here. The 3 DOF robotic assembly enables precision cutting of fragile materials with the help of visual guiding and pixel elimination. The 6-degrees-of-freedom robot uses a combination of visual feedback from an onboard camera and supervision from an external camera to achieve its goals. Pick-and-place operations are executed with a switching control method. Both systems improved in terms of computing time and convergence once ANN was used to make the strategies intelligent. The retrieved scene image features are put to use by the networks in a variety of ways. The simulation and experimental results that back up the suggested approaches demonstrates the value of artificial neural network in machine vision applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

Retaining and Enhancing Pre-trained Knowledge in vision-Language Models with Prompt Ensembling

Retaining and Enhancing Pre-trained Knowledge in Vision-Lang...

引用

IEEE Workshop on applications of Computer vision (WACV)

作者： Donggeun Kim Yujin Jo Myungjoo Lee Taesup Kim Graduate School of Data Science Seoul National University Nota Inc.

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robust zero-shot learning capabilities. These capabilities allow models to understand and respond to previously unseen data without task-specific training. However, adapting CLIP to integrate specialized knowledge from various domains while retaining its zero-shot capabilities remains a significant challenge. To address this, we introduce a novel prompt ensemble learning approach called Group-wise Prompt Ensemble (GPE). This method aims to enhance CLIP's zero-shot capabilities by incorporating new domain knowledge while improving its adaptability and robustness against data distribution shifts. Our approach hinges on three main strategies: prompt grouping with masked attention to optimize CLIP's adaptability while safeguarding its zero-shot capabilities; the incorporation of auxiliary prompts for the seamless integration of new domain insights without disrupting the original model's representation; and an ensemble learning strategy that effectively merges original and new knowledge. Through rigorous experimentation, including more challenging cross-dataset transfer evaluations, our GPE method redefines the benchmarks for the adaptability and efficiency of vision-language models, surpassing existing models across various scenarios.

关键词： Training Adaptation models Computer vision Computational modeling Zero shot learning Fasteners Benchmark testing Robustness Data models Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Authentication and Verification in Human-Robot Cooperative Robotic Cells using Stereo vision and Gesture Control

Authentication and Verification in Human-Robot Cooperative R...

引用

International Image Processing, applications and Systems conference (IPAS)

作者： Gábor Kovács Tamás Szirányi Machine Perception Research Laboratory HUN-REN Institute for Computer Science and Control Budapest Hungary

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

The integration of human-robot interaction (HRI) technologies with industrial automation has become increasingly essential for enhancing productivity and safety in manufacturing environments. In this paper, we propose a novel approach to address these challenges by using stereo vision and gesture control in cooperative robotic cells. Our system enables seamless authentication of operators and real-time verification of task execution, ensuring compliance with established protocols and safety *** features of our system include its gesture-based operation with gesture recognition algorithms, allowing operators to interact with robotic systems intuitively and efficiently. By leveraging stereo vision, our system accurately tracks the operators’ movement within the workspace, facilitating precise task execution and object *** present a detailed description of our system architecture, experimental configuration, and real-world performance assessment. Our results demonstrate the effectiveness and feasibility of our approach in enhancing operational efficiency, ensuring quality, and improving the overall user experience in industrial automation.

关键词： Automation Service robots Tracking Human-robot interaction Authentication Systems architecture User experience Real-time systems Stereo vision Safety

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Median Filter Hardware Chip for Image and Signal Processing

Performance Evaluation of Median Filter Hardware Chip for Im...

引用

Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), International conference on

作者： Sreesh Gaur Akash Goel Pawan Kumar Pal Amit Kumar Singh Sanger Department of Computer Science KIET Group of Institutions Ghaziabad India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

The median filter is a valuable image processing tool that can be used in many applications to advance picture quality, and inferior noise, and acquire data ready for more analysis. The median filter, a non-linear image processing technique, has excessive application in many diverse fields because of its capacity to remove noise while preserving edges. The filter is significant for both simple and complex imageprocessing occupations since it is together easy to comprehend and fast to use. An active method to attain real-time performance is to devise a median filter on a FieldProgrammable Gate Array (FPGA) for image signal processing and machine vision applications. FPGAs are well-suited for photo filtering due to their capability to achieve parallel processing, which is one of their prominent advantages. The research article meets with the design and simulation of the average filter in HDL and synthesis on the FPGA for assessing the performance indices.

关键词： Performance evaluation Filtering machine vision Noise Parallel processing Logic gates Hardware Real-time systems Delays Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning Based Knowledge Distillation on 3D Point Clouds

Adversarial Learning Based Knowledge Distillation on 3D Poin...

引用

IEEE Workshop on applications of Computer vision (WACV)

作者： Sanjay S J Akash J Sreehari Rajan Dimple A Shajahan Charu Sharma Machine Learning Lab IIIT Hyderabad India Department of Computer Science TKM College of Engineering Kollam India

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

The significant improvements in point cloud representation learning have increased its applicability in many real-life applications, resulting in the need for lightweight, better-performing models. One widely proposed efficient method is knowledge distillation, where a lightweight model uses knowledge from large models. Very few works exist on distilling the knowledge for point clouds. Most of the work focuses on cross-modal-based approaches that make the method expensive to train. This paper proposes PointKAD, an adversarial knowledge distillation framework for point cloud-based tasks. PointKAD includes adversarial feature distillation and response distillation with the help of discriminators to extract and distill the representation of feature maps and logits. We conduct extensive experimental studies on both synthetic (ModelNet40) and real (ScanObjectNN) datasets to show that PointKAD achieves state-of-the-art results compared to the existing knowledge distillation methods for point cloud classification. Additionally, we present results on the part segmentation task, highlighting the efficacy of the PointKAD framework. Our experiments further reveal that PointKAD is capable of transferring knowledge across different tasks and datasets, show-casing its versatility. Furthermore, we demonstrate that PointKAD can be applied to a cross-modal training setup, achieving competitive performance with cross-modal-based point cloud methods for classification.

关键词： Point cloud compression Training Representation learning Deep learning Image segmentation Computer vision Three-dimensional displays Feature extraction Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

RADA: Reconstruction Assisted Domain Adaptation for Nighttime Aerial Tracking 27th

RADA: Reconstruction Assisted Domain Adaptation for Nightti...

引用

27th International conference on Pattern Recognition, ICPR 2024

作者： Chouhan, Avinash Chandak, Mayank Sur, Arijit Chutia, Dibyajyoti Aggarwal, Shiv Prasad North Eastern Space Applications Centre Umiam793103 India Indian Institute of Technology Guwahati Assam Guwahati781039 India

ISBN: (纸本)9783031781919

Visual object tracking is a popular research area in computer vision due to its diverse applications. Despite the impressive progress made by numerous state-of-the-art trackers on large-scale datasets, visual object tracking at nighttime remains challenging because of low light (brightness) conditions, lack of contrast, very low variability among feature distributions, etc. In addition, the lack of paired (labeled) data for nighttime tracking makes it infeasible for supervised learning based modeling. Unsupervised domain adaptation based tracking can resolve this issue. In this work, we proposed static image style transfer-based Reconstruction Assisted Domain Adaptation (RADA) with adversarial learning for nighttime object tracking. The main contribution of the work is two-fold. First, a reconstruction-assisted adaptation is proposed for domain invariant feature extraction and to achieve input and feature level adaptation. Secondly, static style transfer is used to generate synthetic paired images (video frames) for supervised nighttime modeling for visual object tracking. Style adversarial alignment at multiple levels helped to adapt between the styled source domain and the target domain, which do not require pseudo labels. RADA attained feature and input level adaptation without external model requirements for low-light image enhancement. Static style transfer avoids negative domain transfer and enables domain transfer learning on true labels. The effectiveness of RADA is validated on six benchmark datasets. RADA achieved state-of-the-art results on two benchmark nighttime adaptation datasets with improvements in the range of 3.7% - 11.4%. RADA also attained state-of-the-art results on three other nighttime datasets without target adaptation. The tracking results and model weights are available at https://***/chouhan-avinash/RADA/. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

AI Based Targeting and Tracking System

AI Based Targeting and Tracking System

引用

Computational, Communication and Information Technology (ICCCIT), International conference on

作者： Megha Kolhekar Pratik Mhatre Omkar Yadav Arkam Khan Avantika Pardeshi Department of Electronics & Telecommunication Engineering Agnel Charities' Fr. C. Rodrigues Institute of Technology Navi Mumbai India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

This paper introduces an AI-driven tracking and targeting system poised to revolutionize precision across surveil- lance, defense, and tracking. Traditional systems often struggle with dynamic environments and accuracy optimization. Lever- aging AI, our system integrates advanced computer vision and deep neural networks for real-time object detection and tracking. Through machine learning, the system adapts to evolving scenarios, progressively enhancing tracking performance. Additionally, prevention of casualties with respect of loss of life, this model acts as a firewall from possible threats. This AI-based system signifies a significant advancement, promising heightened precision and efficiency across diverse applications. its integration of cutting- edge technologies positions it at the forefront of tracking and targeting systems, marking a noteworthy contribution to the field.

关键词： Computer vision Target tracking Firewalls (computing) Prevention and mitigation Image edge detection Object detection machine learning Real-time systems Information and communication technology Optimization

来源：评论

学校读者我要写书评

暂无评论

Design-O-Meter: Towards Evaluating and Refining Graphic Designs

Design-O-Meter: Towards Evaluating and Refining Graphic Desi...

引用

IEEE Workshop on applications of Computer vision (WACV)

作者： Sahil Goyal Abhinav Mahajan Swasti Mishra Prateksha Udhayanan Tripti Shukla K J Joseph Balaji Vasan Srinivasan IIT Roorkee IIIT Bangalore Adobe Research

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Graphic designs are an effective medium for visual communication. They range from greeting cards to corporate flyers and beyond. Off-late, machine learning techniques are able to generate such designs, which accelerates the rate of content production. An automated way of evaluating their quality becomes critical. Towards this end, we introduce Design-o-meter, a data-driven methodology to quantify the goodness of graphic designs. Further, our approach can suggest modifications to these designs to improve its visual appeal. To the best of our knowledge, Design-o-meter is the first approach that scores and refines designs in a unified framework despite the inherent subjectivity and ambiguity of the setting. Our exhaustive quantitative and qualitative analysis of our approach against baselines adapted for the task (including recent Multimodal LLM-based approaches) brings out the efficacy of our methodology. We hope our work will usher more interest in this important and pragmatic problem setting. Project Page: ***/Design-o-meter.

关键词： Visualization Computer vision Visual communication Refining Layout Production machine learning Pragmatics

来源：评论

学校读者我要写书评

暂无评论

Bridging the machine-Human Gap in Blurred-Image Classification via Entropy Maximisation

Bridging the Machine-Human Gap in Blurred-Image Classificati...

引用

International Image Processing, applications and Systems conference (IPAS)

作者： Emilio Sansano-Sansano Marina Martínez-García Javier Portilla INIT Universitat Jaume I Castellón de la Plana Spain IMAC Universitat Jaume I Castellón de la Plana Spain Instituto de Óptica CSIC Madrid Spain

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

Recent studies point to an accuracy gap between humans and Artificial Neural Network (ANN) models when classifying blurred images, with humans outperforming ANNs. To bridge this gap, we introduce a spectral channel-based range-constrained entropy merit function, from which we devise a zero-phase, circular symmetric blind deblurring method. We apply it as a pre-processing step for image classification and test it using pre-trained classification models and images blurred by Gaussian kernels. We compare our method to state-of-the-art restoration methods, showing its superiority, effectively bridging the machine-human gap for most models and blur levels. Our results also rank higher than the competitors in no-reference and full-reference image quality metrics. Notwithstanding the limitation to zero-phase blur, this work shows that, for image pre-processing aimed at visual tasks, it may be advantageous to use merit functions based on vision science and information theory, rather than on the expected error to the latent image.

关键词： Measurement Image quality Visualization Computer vision Artificial neural networks Entropy Kernel Optimization Information theory Image classification

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180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：