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

494 篇 会议
25 册 图书
2 篇 期刊文献

馆藏范围

521 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

224 篇 工学
- 176 篇 计算机科学与技术...
- 131 篇 软件工程
- 61 篇 光学工程
- 38 篇 电气工程
- 33 篇 控制科学与工程
- 25 篇 电子科学与技术（可...
- 21 篇 信息与通信工程
- 16 篇 仪器科学与技术
- 15 篇 机械工程
- 14 篇 生物医学工程（可授...
- 14 篇 生物工程
- 12 篇 力学（可授工学、理...
- 12 篇 材料科学与工程（可...
- 10 篇 建筑学
- 9 篇 化学工程与技术
- 7 篇 安全科学与工程
- 6 篇 动力工程及工程热...
- 6 篇 土木工程
- 5 篇 冶金工程
- 5 篇 交通运输工程
144 篇 理学
- 92 篇 物理学
- 74 篇 数学
- 26 篇 统计学（可授理学、...
- 16 篇 生物学
- 11 篇 系统科学
- 9 篇 化学
24 篇 管理学
- 12 篇 图书情报与档案管...
- 11 篇 管理科学与工程(可...
- 9 篇 工商管理
19 篇 医学
- 17 篇 临床医学
6 篇 教育学
4 篇 法学
2 篇 经济学
1 篇 军事学
1 篇 艺术学

主题

95 篇 computer vision
40 篇 solid modeling
39 篇 computational mo...
34 篇 shape
33 篇 humans
32 篇 layout
31 篇 physics
29 篇 machine vision
26 篇 biological syste...
25 篇 physics computin...
23 篇 cameras
21 篇 image segmentati...
21 篇 image processing...
20 篇 computer science
20 篇 pattern recognit...
19 篇 application soft...
18 篇 computer graphic...
18 篇 artificial intel...
18 篇 geometry
17 篇 object recogniti...

机构

3 篇 the robotics ins...
3 篇 department of co...
3 篇 department of co...
2 篇 department of co...
2 篇 department of co...
2 篇 robotics institu...
2 篇 faculty of physi...
2 篇 international nu...
2 篇 department of co...
2 篇 department of me...
2 篇 heidelberg unive...
2 篇 sony semiconduct...
2 篇 ano «scientific ...
2 篇 department of el...
2 篇 department of co...
2 篇 department of co...
2 篇 leti grenoble
2 篇 department of co...
2 篇 univ of florida ...
2 篇 department of me...

作者

5 篇 d. metaxas
3 篇 k. ikeuchi
3 篇 t. kanade
3 篇 y. shirai
3 篇 bao-liang lu
3 篇 s.g. narasimhan
3 篇 a. pentland
3 篇 m. willander
3 篇 james kwok
3 篇 s.k. nayar
3 篇 d.b. goldgof
3 篇 liqing zhang
2 篇 p.r. davidson
2 篇 wang lei
2 篇 d.j. kriegman
2 篇 wang yulun
2 篇 kitahara itaru
2 篇 g. healey
2 篇 h.r. sirisena
2 篇 h. inoue

语言

496 篇 英文
21 篇 其他
4 篇 中文
3 篇 俄文

检索条件"任意字段=Proceedings of the Workshop on Physics-Based Modeling in Computer Vision"

共 521 条记录，以下是41-50 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：

A coarse-To-fine multi-view stereo network based on attention mechanisms 12

A coarse-To-fine multi-view stereo network based on attentio...

引用

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Xu, Yanan Zuo, Zhiyong Luo, Zhenbao Cui, Yuyong Wu, Zhongjian Southwest Institute of Technical Physics Chengdu610041 China

ISBN: (数字)9781510674967

ISBN: (纸本)9781510674950

Multi-view stereo is a method that analyzes and processes images from multiple perspectives to estimate the 3D geometric information of the scene to achieve 3D reconstruction. To improve the accuracy of 3D reconstruction in large-scale scenes and reduce the complexity of the reconstruction algorithm, in this paper, we propose a coarse-To-fine multi-view stereo network based on attention mechanism. First, we use a feature pyramid to extract multi-scale features, introducing richer geometric information and more contextual information at different levels of the pyramid to improve modeling accuracy. Then, we use position encoding on the coarse-scale feature map and introduce an attention mechanism to obtain more context information. We adopt a cascade structure to achieve high-resolution depth map construction. We use the reference image to refine the final result again and enhance details such as edges. We conduct experiments on the publicly available DTU dataset. Experimental results show that our proposed method improves accuracy compared with existing algorithms. In addition, we also conduct experiments on other representative public datasets. The accuracy of the experimental results further validates the effectiveness of our proposed method. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

1st Deep Breast workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care, Deep-Breath 2024

1st Deep Breast Workshop on AI and Imaging for Diagnostic an...

引用

1st Deep Breast workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care, Deep-Breath 2024

ISBN: (纸本)9783031777882

The proceedings contain 23 papers. The special focus in this conference is on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care. The topics include: DuEU-Net: Dual Encoder UNet with Modality-Agnostic Training for PET-CT Multi-modal Organ and Lesion Segmentation;One for All: UNET Training on Single-Sequence Masks for Multi-sequence Breast MRI Segmentation;Multimodal Breast MRI Language-Image Pretraining (MLIP): An Exploration of a Breast MRI Foundation Model;enhancing the Utility of Privacy-Preserving Cancer Classification Using Synthetic Data;Efficient Generation of Synthetic Breast CT Slices By Combining Generative and Super-Resolution Models;Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification;Virtual Dynamic Contrast Enhanced Breast MRI Using 2D U-Net Architectures;Optimizing BI-RADS 4 Lesion Assessment Using Lightweight Convolutional Neural Network with CBAM in Contrast Enhanced Mammography;mammographic Breast Positioning Assessment via Deep Learning;endpoint Detection in Breast Images for Automatic Classification of Breast Cancer Aesthetic Results;thick Slices for Optimal Digital Breast Tomosynthesis Classification With Deep-Learning;predicting Aesthetic Outcomes in Breast Cancer Surgery: A Multimodal Retrieval Approach;vision Mamba for Classification of Breast Ultrasound Images;breast Cancer Molecular Subtyping from H&E Whole Slide Images Using Foundation Models and Transformers;graph Neural Networks for Modelling Breast Biomechanical Compression;a Generative Adversarial Approach to Remove Moiré Artifacts in Dark-Field and Phase-Contrast X-Ray Images;MRI Breast Tissue Segmentation Using nnU-Net for Biomechanical modeling;Fat-Suppressed Breast MRI Synthesis for Domain Adaptation in Tumour Segmentation;Guiding Breast Conservative Surgery by Augmented Reality from Preoperative MRI: Initial System Design and Retrospective Trials;ELK: Enhanced Learning Through Cross-Modal Knowledge Transf

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pgnn-based Approach for Robust 3D Light Direction Estimation in Outdoor Images

Pgnn-Based Approach for Robust 3D Light Direction Estimation...

引用

International workshop on Content-based Multimedia Indexing, CBMI

作者： Marcello Zanardelli Mahyar Gohari Riccardo Leonardi Sergio Benini Nicola Adami Department of Information Engineering University of Brescia Brescia Italy

ISBN: (数字)9798350378443

ISBN: (纸本)9798350378450

Estimating the 3D light direction from 2D outdoor images is a crucial task in computer vision, especially useful in the context of image forgery detection. In this paper, we propose a novel approach that leverages a physics-guided neural network (PGNN) to achieve accurate global 3D light direction estimation. The proposed architecture incorporates an illumination model that enables the network to indirectly learn geometric information and improve the accuracy of the estimated light direction. To evaluate the performance of our proposed approach, we train and test our models on two datasets that were curated for the global light direction estimation. The proposed PGNN method demonstrates superior performance compared to existing state-of-the-art approaches, where direct comparisons were feasible. To further investigate the benefits provided by embedding the physical model in our approach, we conducted an extensive ablation study, demonstrating that the use of the illumination model significantly enhances the accuracy of the light direction estimation compared to a purely data-driven approach. The proposed PGNN is available as open-source software, providing an accessible and useful tool for researchers in computer vision and graphics.

关键词： computer vision Three-dimensional displays Accuracy Computational modeling Estimation Lighting computer architecture Predictive models Forgery Light sources

来源：评论

学校读者我要写书评

暂无评论

Revisiting Disparity from Dual-Pixel Images: physics-Informed Lightweight Depth Estimation

Revisiting Disparity from Dual-Pixel Images: Physics-Informe...

引用

IEEE workshop on Applications of computer vision (WACV)

作者： Teppei Kurita Yuhi Kondo Legong Sun Takayuki Sasaki Sho Nitta Yasuhiro Hashimoto Yoshinori Muramatsu Yusuke Moriuchi Sony Semiconductor Solutions Corporation

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

In this study, we propose a high-performance disparity (depth) estimation method using dual-pixel (DP) images with few parameters. Conventional end-to-end deep-learning methods have many parameters but do not fully ex-ploit disparity constraints, which limits their performance. Therefore, we propose a lightweight disparity estimation method based on a completion-based network that explicitly constrains disparity and learns the physical and systemic disparity properties of DP. By modeling the DP-specific dis-parity error parametrically and using it for sampling during training, the network acquires the unique properties of DP and enhances robustness. This learning also allows us to use a common RGB-D dataset for training without a DP dataset, which is labor-intensive to acquire. Further-more, we propose a non-learning-based refinement frame-work that efficiently handles inherent disparity expansion errors by appropriately refining the confidence map of the network output. As a result, the proposed method achieved state-of-the-art results while reducing the overall system size to 1/5 of that of the conventional method, even without using the DP dataset for training, thereby demonstrating its effectiveness. The code and dataset are available on our project site.

关键词： Training computer vision Codes Depth measurement Refining Estimation Robustness

来源：评论

学校读者我要写书评

暂无评论

UnDIVE: Generalized Underwater Video Enhancement Using Generative Priors

UnDIVE: Generalized Underwater Video Enhancement Using Gener...

引用

IEEE workshop on Applications of computer vision (WACV)

作者： Suhas Srinath Aditya Chandrasekar Hemang Jamadagni Rajiv Soundararajan Prathosh A P Indian Institute of Science Qualcomm National Institute of Technology Karnataka

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

With the rise of marine exploration, underwater imaging has gained significant attention as a research topic. Under-water video enhancement has become crucial for real-time computer vision tasks in marine exploration. However, most existing methods focus on enhancing individual frames and neglect video temporal dynamics, leading to visually poor enhancements. Furthermore, the lack of ground-truth references limits the use of abundant available underwater video data in many applications. To address these issues, we propose a two-stage framework for enhancing underwater videos. The first stage uses a denoising diffusion probabilistic model to learn a generative prior from unlabeled data, capturing robust and descriptive feature representations. In the second stage, this prior is incorporated into a physics-based image formulation for spatial enhancement, while also enforcing temporal consistency between video frames. Our method enables real-time and computationally-efficient processing of high-resolution underwater videos at lower resolutions, and offers efficient enhancement in the presence of diverse water-types. Extensive experiments on four datasets show that our approach generalizes well and outperforms existing enhancement methods. Our code is available at github. com/suhas-srinath/undive.

关键词： Degradation computer vision Computational modeling Noise reduction Imaging Streaming media Diffusion models Real-time systems Spatial resolution Software development management

来源：评论

学校读者我要写书评

暂无评论

Positive Concave Deep Equilibrium Models 41

Positive Concave Deep Equilibrium Models

引用

41st International Conference on Machine Learning, ICML 2024

作者： Gabor, Mateusz Piotrowski, Tomasz Cavalcante, Renato L.G. Faculty of Electronics Photonics and Microsystems Wroclaw University of Science and Technology Wroclaw Poland Faculty of Physics Astronomy and Informatics Nicolaus Copernicus University Toruń Poland Fraunhofer Heinrich Hertz Institute Berlin Germany

Deep equilibrium (DEQ) models are widely recognized as a memory efficient alternative to standard neural networks, achieving state-of-the-art performance in language modeling and computer vision tasks. These models solve a fixed point equation instead of explicitly computing the output, which sets them apart from standard neural networks. However, existing DEQ models often lack formal guarantees of the existence and uniqueness of the fixed point, and the convergence of the numerical scheme used for computing the fixed point is not formally established. As a result, DEQ models are potentially unstable in practice. To address these drawbacks, we introduce a novel class of DEQ models called positive concave deep equilibrium (pcDEQ) models. Our approach, which is based on nonlinear Perron-Frobenius theory, enforces nonnegative weights and activation functions that are concave on the positive orthant. By imposing these constraints, we can easily ensure the existence and uniqueness of the fixed point without relying on additional complex assumptions commonly found in the DEQ literature, such as those based on monotone operator theory in convex analysis. Furthermore, the fixed point can be computed with the standard fixed point algorithm, and we provide theoretical guarantees of its geometric convergence, which, in particular, simplifies the training process. Experiments demonstrate the competitiveness of our pcDEQ models against other implicit models. Copyright 2024 by the author(s)

关键词： Fixed point arithmetic

来源：评论

学校读者我要写书评

暂无评论

The Concept of Neuromorphic vision Systems based on Memristive Devices 6

The Concept of Neuromorphic Vision Systems based on Memristi...

引用

6th Scientific School "Dynamics of Complex Networks and their Applications", DCNA 2022

作者： Shchanikov, Sergey Bordanov, Ilya Murom Institute Vladimir State University Ai Systems Design Laboratory Murom Russia Lobachevsky University Laboratory of Stochastic Multistable Systems Nizhny Novgorod Russia

ISBN: (数字)9781665461740

ISBN: (纸本)9781665461740

Here we propose the concept of neuromorphic analog memristive vision systems. The main feature of this concept is the rejection of analog-to-digital and digital-to-analog conversions when capturing input visual data for a spiking neural network (SNN) based on memristive devices. This can be achieved by combining photodiodes and memristors and directly feeding analog pulses from the output of such a circuit to the input of a SNN circuit. This concept relates to the field of in-memory and in-sensor computing and will makes it possible to create more compact, energy-efficient visual processing units for wearable, on-board and embedded electronics for such areas as robotics, the Internet of Things, neuroprosthetics and other practical applications in the field of artificial intelligence. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

13th International workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2022

13th International Workshop on Statistical Atlases and Compu...

引用

13th International workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2022

ISBN: (纸本)9783031234422

The proceedings contain 48 papers. The special focus in this conference is on Statistical Atlases and Computational Models of the Heart. The topics include: An Atlas-based Analysis of Biventricular Mechanics in Tetralogy of Fallot;Review of Data Types and Model Dimensionality for Cardiac DTI SMS-Related Artefact Removal;improving Echocardiography Segmentation by Polar Transformation;spatiotemporal Cardiac Statistical Shape modeling: A Data-Driven Approach;interpretable Prediction of Post-Infarct Ventricular Arrhythmia Using Graph Convolutional Network;Unsupervised Echocardiography Registration Through Patch-based MLPs and Transformers;sensitivity Analysis of Left Atrial Wall modeling Approaches and Inlet/Outlet Boundary Conditions in Fluid Simulations to Predict Thrombus Formation;APHYN-EP: physics-based Deep Learning Framework to Learn and Forecast Cardiac Electrophysiology Dynamics;unsupervised Machine Learning Exploration of Morphological and Haemodynamic Indices to Predict Thrombus Formation in the Left Atrial Appendage;learning Correspondences of Cardiac Motion from Images Using Biomechanics-Informed modeling;geometrical Deep Learning for the Estimation of Residence Time in the Left Atria;explainable Electrocardiogram Analysis with Wave Decomposition: Application to Myocardial Infarction Detection;A Systematic Study of Race and Sex Bias in CNN-based Cardiac MR Segmentation;mesh U-Nets for 3D Cardiac Deformation modeling;skeletal Model-based Analysis of the Tricuspid Valve in Hypoplastic Left Heart Syndrome;simplifying Disease Staging Models into a Single Anatomical Axis - A Case Study of Aortic Coarctation In-utero;point2Mesh-Net: Combining Point Cloud and Mesh-based Deep Learning for Cardiac Shape Reconstruction;post-Infarction Risk Prediction with Mesh Classification Networks;statistical Shape modeling of Biventricular Anatomy with Shared Boundaries;computerized Analysis of the Human Heart to Guide Targeted Treatment of Atrial Fibrillation;Multi-modal Latent-

关键词：

来源：评论

学校读者我要写书评

暂无评论

Progressive Optimization of Deep Learning-based Fight Detection Model

Progressive Optimization of Deep Learning-Based Fight Detect...

引用

Technologies for Defense and Security (TechDefense), IEEE International workshop on

作者： Azamat Mukhamediya Tilek Zhumabek Department of Electrical and Computer Engineering School of Engineering and Digital Sciences Nazarbayev University Astana Kazakhstan Department of Physics School of Sciences and Humanities Nazarbayev University Astana Kazakhstan

ISBN: (数字)9798331505585

ISBN: (纸本)9798331505592

Building a fight detection system is essential to enhance public safety and develop automated security surveillance systems. Given the success of deep learning-based models in computer vision and pattern recognition, it is common to use deep convolutional and recurrent neural networks to accurately predict fight scenes. However, the required computational resources hinder the use of these models in memory-limited devices. In this work, we aim to obtain the fight detection model that satisfies both memory constraints and accurate classification performance. First, we design a complex model and then reduce its complexity by leveraging a three-stage progressive model optimization strategy. As a result, we obtained accurate detection models, which are $\sim 2$ and $\sim 5$ times lighter compared to the starting complex model. The experiments are performed using two publicly available datasets, namely Hockey and Movie Fights.

关键词： Accuracy Recurrent neural networks Computational modeling Surveillance Memory management Motion pictures Public security Security Optimization Sports

来源：评论

学校读者我要写书评

暂无评论

Versatile energy-based probabilistic models for high energy physics 23

Versatile energy-based probabilistic models for high energy ...

引用

proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Taoli Cheng Aaron Courville Mila University of Montreal

As a classical generative modeling approach, energy-based models have the natural advantage of flexibility in the form of the energy function. Recently, energy-based models have achieved great success in modeling high-dimensional data in computer vision and natural language processing. In line with these advancements, we build a multi-purpose energy-based probabilistic model for High Energy physics events at the Large Hadron Collider. This framework builds on a powerful generative model and describes higher-order inter-particle interactions. It suits different encoding architectures and builds on implicit generation. As for applicative aspects, it can serve as a powerful parameterized event generator for physics simulation, a generic anomalous signal detector free from spurious correlations, and an augmented event classifier for particle identification.

关键词：

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53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：