检索结果-内蒙古大学图书馆

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： He, Xin School of Cyber Security and Computer Hebei University Baoding071002 China Institute of Intelligent Image and Document Information Processing Hebei University Baoding071002 China Hebei Machine Vision Engineering Research Center Hebei University Baoding071002 China

ISBN: (纸本)9789819605781

As the critical elements of scientific literature, mathematical formulas contribute significantly to the effectiveness of literature retrieval. Existing formula-based retrieval methods of scientific literature primarily focus on the number of matching symbols between formulas and often neglect the semantic relevance which leads to suboptimal retrieval outcomes. Additionally, existing literature retrieval methods frequently ignore the ontological relationships between literature, resulting in potential semantic information loss. To address these challenges, we propose a two-stage scientific literature retrieval model named SC-HNE (Symbol Contribution-Heterogeneous Network Enhancement). First, we introduce a Symbol Contribution Aware (SCA) module that calculates the contribution of each symbol based on its hierarchical position in the Operator Tree (OPT), and the symbols with the higher contributions will be paid more attention during the process of formula matching. Second, a heterogeneous network for scientific literature is constructed which uses Heterformer to enrich literature node embeddings with network-aware information and enhance literature representation. Finally, the similarity scores from two modules are combined to rank the top-K scientific literature. Experiments on the DBLP-Citation-network dataset demonstrated the effectiveness of the proposed method through MAP and NDCG metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of renal rejection after kidney transplantation

引用

International Congress Series 2005年 1281卷 773-778页

作者： Yuksel, S.E. El-Baz, A. Farag, A.A. Abo El-Ghar, M.E. Eldiasty, T.A. Ghoneim, M.A. Computer Vision and Image Processing Lab University of Louisville Louisville KY 40292 United States Mansoura University Urology and Nephrology Center Mansoura Egypt

Acute rejection is the most important reason of graft failure after kidney transplantation, and early detection is crucial to survive the kidney function. Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) is an imaging modality where a contrast agent (such as Gd-DTPA) is introduced into the kidney and rapid and repeated images are taken, which allows both the anatomic and functional information of the kidney to be monitored. Using these images, this paper introduces an accurate method for the segmentation of the kidney from the surrounding structures by introducing a shape model of the kidney into the external energy component of the deformable models. Secondly, registration algorithms are employed to account for the motion of the kidney due to patient breathing and finally, the perfusion curves obtained from the cortex that show the transportation of the contrast agent into the tissue are given for future classification of normal and acute rejection transplants. Applications of the proposed algorithms yield promising results. © 2005.

关键词： Contrast agents Deformable models Dynamic MRI Gd-DTPA Kidney transplantation Mutual information Renal rejection

来源：评论

学校读者我要写书评

暂无评论

2D and 3D shape based segmentation using deformable models

2D and 3D shape based segmentation using deformable models

引用

8th International Conference on Medical image Computing and computer-Assisted Intervention - MICCAI 2005

作者： El-Baz, Ayman Yuksel, Seniha E. Shi, Hongjian Farag, Aly A. El-Ghar, Mohamed A. Eldiasty, Tarek Ghoneim, Mohamed A. Computer Vision and Image Processing Laboratory University of Louisville Louisville KY 40292 Mansoura University Urology and Nephrology Center Mansoura Egypt

ISBN: (纸本)3540293264

A novel shape based segmentation approach is proposed by modifying the external energy component of a deformable model. The proposed external energy component depends not only on the gray level of the images but also on the shape information which is obtained from the signed distance maps of objects in a given data set. The gray level distribution and the signed distance map of the points inside and outside the object of interest are accurately estimated by modelling the empirical density function with a linear combination of discrete Gaussians (LCDG) with positive and negative components. Experimental results on the segmentation of the kidneys from low-contrast DCE-MRI and on the segmentation of the ventricles from brain MRFs show how the approach is accurate in segmenting 2-D and 3-D data sets. The 2D results for the kidney segmentation have been validated by a radiologist and the 3D results of the ventricle segmentation have been validated with a geometrical phantom. © Springer-Verlag Berlin Heidelberg 2005.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

When is a confidence measure good enough?

When is a confidence measure good enough?

引用

9th International Conference on computer vision Systems, ICVS 2013

作者： Márquez-Valle, Patricia Gil, Debora Hernàndez-Sabaté, Aura Kondermann, Daniel Computer Vision Center Universitat Autònoma de Barcelona Spain Heidelberg Collaboratory for Image Processing at the IWR University of Heidelberg Spain

ISBN: (纸本)9783642394010

Confidence estimation has recently become a hot topic in image processing and computer vision. Yet, several definitions exist of the term "confidence" which are sometimes used interchangeably. This is a position paper, in which we aim to give an overview on existing definitions, thereby clarifying the meaning of the used terms to facilitate further research in this field. Based on these clarifications, we develop a theory to compare confidence measures with respect to their quality. © 2013 Springer-Verlag.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Medial axis representation and encoding of scanned documents

引用

Journal of Visual Communication and image Representation 1991年第2期2卷 151-165页

作者： Brandt, Jonathan W. Jain, Anil K. Ralph Algazi, V. Computer Vision Research Lab CIPIC: The Center for Image Processing and Integrated Computing United States Department of Electrical Engineering and Computer Science University of California Davis CA 95616 United States

The medial axis transform (MAT) is a sparse representation of shape, which, being reversible, has potential for binary image compression. The MAT also provides structural information not accessible with alternative binary image codes. This structural information is often used for line extraction and pattern recognition. Therefore, the MAT occupies an interesting middle ground between lower-level, compressible image codes and higher-level, meaningful image representations. In an attempt to realize this middle ground, a MAT-based coding scheme which respects its structural properties is developed. The MAT-based coding method is applied to the CCITT facsimile test images. The resulting compression is comparable to that of known coding schemes for textual and somewhat better for graphical data. Some simple modifications to improve skeleton coding performance are suggested. To substantiate the claim that the MAT is effective for higher-level processing, the representation is extended to perform line segment and curve extraction. The extraction takes place under the control of a global error tolerance parameter and thus provides a new method to trade off data compression with distortion for binary images. © 1991.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interest point based tracking

Interest point based tracking

引用

2010 20th International Conference on Pattern Recognition, ICPR 2010

作者： Kloihofer, Werner Kampel, Martin Research and Development Image Processing Center Communication Systems GmbH Vienna Austria Computer Vision Lab. Vienna University of Technology Vienna Austria

ISBN: (纸本)9780769541099

This paper deals with a novel method for object tracking. In the first step interest points are detected and feature descriptors around them are calculated. Sets of known points are created, allowing tracking based on point matching. The set representation is updated online at every tracking step. Our method uses one-shot learning with the first frame, so no offline and no supervised learning is required. Following an object recognition based approach there is no need for a background model or motion model, allowing tracking of abrupt motion and with non-stationary cameras. We compare our method to MeanShift and Tracking via Online Boosting, showing the benefits of our approach. © 2010 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

From early biological models to CNNs: Do they look where humans look? 25

From early biological models to CNNs: Do they look where hum...

引用

25th International Conference on Pattern Recognition, ICPR 2020

作者： Cadoni, Marinella Iole Lagorio, Andrea Grosso, Enrico Jia Huei, Tan Chee Seng, Chan Computer Vision Laboratory University of Sassari Sassari Italy Center of Image and Signal Processing Department of Artificial Intelligence Faculty of Computer Science and Information Technology University of Malaya Malaysia

ISBN: (纸本)9781728188089

Early hierarchical computational visual models as well as recent deep neural networks have been inspired by the functioning of the primate visual cortex system. Although much effort has been made to dissect neural networks to visualize the features they learn at the individual units, the scope of the visualizations has been limited to a categorization of the features in terms of their semantic level. Considering the ability humans have to select high semantic level regions of a scene, the question whether neural networks can match this ability, and if similarity with humans attention is correlated with neural networks performance naturally arise. To address this question we propose a pipeline to select and compare sets of feature points that maximally activate individual networks units to human fixations. We extract features from a variety of neural networks, from early hierarchical models such as HMAX up to recent deep convolutional neural netwoks such as Densnet, to compare them to human fixations. Experiments over the ETD database show that human fixations correlate with CNNs features from deep layers significantly better than with random sets of points, while they do not with features extracted from the first layers of CNNs, nor with the HMAX features, which seem to have low semantic level compared with the features that respond to the automatically learned filters of CNNs. It also turns out that there is a correlation between CNN's human similarity and classification performance. © 2020 IEEE

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Experiments on sensitivity of template matching for lung nodule detection in low dose CT scans

Experiments on sensitivity of template matching for lung nod...

引用

ISSPIT 2007 - 2007 IEEE International Symposium on Signal processing and Information Technology

作者： Elhabian, Shireen Y. El Munim, Hossam Abd Elshazly, Salwa Farag, Aly A. Aboelghar, Mohamed Computer Vision and Image Processing Laboratory Univ. of Louisville Louisville KY 40292 United States Urology and Nephrology Center Mansoura University Mansoura Egypt

ISBN: (纸本)9781424418350

Template matching is a common approach for detection lung nodules from CT scans. Templates may take different shapes, size and intensity distribution. The process of nodule detection is essentially two steps: isolation of candidate nodules, and elimination of false positive nodules. The processes of outlining the detected nodules and their classification (i.e., assigning pathology for each nodule) complete the CAD system for early detection of lung nodules. This paper is concerned with the template design and evaluating the effectiveness of the first step in the nodule detection process. The paper will neither address the problem of reducing false positives nor would it deal with nodule segmentation and classification. Only parametric templates are considered. Modeling the gray scale distribution for the templates based on the prior knowledge of typical nodules extracted by radiologists. The effectiveness of the template matching is investigated by cross validation with respect to the ground truth and is described by hit rate curves indicating the probability of detection as function of shape, size and orientation, if applicable, of the templates. We used synthetic and sample real CT scan images in our experiments. It is found that template matching is more sensitive to additive noise than image blurring when tests conducted on synthetic data. On the sample CT scans small size circular and hollow-circular templates provided comparable results to human experts. ©2007 IEEE.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

Learning Robust Models Using the Principle of Independent Causal Mechanisms 43rd

Learning Robust Models Using the Principle of Independent ...

引用

43rd DAGM German Conference on Pattern Recognition, DAGM GCPR 2021

作者： Müller, Jens Schmier, Robert Ardizzone, Lynton Rother, Carsten Köthe, Ullrich Heidelberg Collaboratory for Image Processing Heidelberg University Heidelberg Germany Computer Vision and Learning Lab Heidelberg University Heidelberg Germany Bosch Center for Artificial Intelligence Renningen Germany

ISBN: (纸本)9783030926588

Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, [31]) can turn this weakness into an opportunity: one can take advantage of distribution shift between different environments during training in order to obtain more robust models. We propose a new gradient-based learning framework whose objective function is derived from the ICM principle. We show theoretically and experimentally that neural networks trained in this framework focus on relations remaining invariant across environments and ignore unstable ones. Moreover, we prove that the recovered stable relations correspond to the true causal mechanisms under certain conditions, turning domain generalization into a causal discovery problem. In both regression and classification, the resulting models generalize well to unseen scenarios where traditionally trained models fail. © 2021, Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Detecting regional abnormal cardiac contraction in short-axis MR images using independent component analysis

引用

7th International Conference on Medical Imaging and computer Assisted Intervention, MICCAI 2004

作者： Suinesiaputra, A. Üzümcü, M. Frangi, A.F. Kaandorp, T. Reiber, J. Lelieveldt, B. Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Computer Vision Group Aragon Institute of Engineering University of Zaragoza Zaragoza Spain

ISBN: (纸本)3540229760

Regional myocardial motion analysis is used in clinical routine to inspect cardiac contraction in myocardial diseases such as infarction or hypertrophy. Physicians/radiologists can recognize abnormal cardiac motion because they have knowledge about normal heart contraction. This paper explores the potential of Independent Component Analysis (ICA) to extract local myocardial contractility patterns and to use them for the automatic detection of regional abnormalities. A qualitative evaluation was performed using 42 healthy volunteers to train the ICA model and 6 infarct patients to test the detection and localization. This experiment shows that the evaluation results correlate very well to the clinical gold standard: delayed-enhancement MR images. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：