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

4,423 篇 会议
232 篇 期刊文献
55 册 图书
10 篇 学位论文
3 篇 资讯

馆藏范围

4,723 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,622 篇 工学
- 1,500 篇 计算机科学与技术...
- 885 篇 电气工程
- 773 篇 软件工程
- 463 篇 信息与通信工程
- 331 篇 控制科学与工程
- 292 篇 生物医学工程（可授...
- 223 篇 光学工程
- 210 篇 机械工程
- 162 篇 电子科学与技术（可...
- 143 篇 仪器科学与技术
- 126 篇 生物工程
- 89 篇 材料科学与工程（可...
- 68 篇 测绘科学与技术
- 58 篇 化学工程与技术
- 32 篇 土木工程
- 27 篇 建筑学
- 25 篇 力学（可授工学、理...
1,484 篇 理学
- 925 篇 物理学
- 656 篇 数学
- 431 篇 统计学（可授理学、...
- 228 篇 系统科学
- 139 篇 生物学
- 64 篇 化学
759 篇 医学
- 594 篇 临床医学
- 222 篇 特种医学
- 78 篇 基础医学(可授医学...
- 44 篇 药学(可授医学、理...
214 篇 管理学
- 119 篇 管理科学与工程(可...
- 103 篇 图书情报与档案管...
- 25 篇 工商管理
24 篇 农学
17 篇 法学
13 篇 教育学
12 篇 经济学
10 篇 艺术学
9 篇 文学
2 篇 军事学

主题

548 篇 image processing
461 篇 image segmentati...
390 篇 stochastic proce...
365 篇 statistical anal...
259 篇 feature extracti...
231 篇 bayesian methods
224 篇 image reconstruc...
188 篇 signal processin...
187 篇 image analysis
141 篇 pixel
135 篇 image restoratio...
109 篇 statistics
106 篇 pattern recognit...
105 篇 image edge detec...
103 篇 hidden markov mo...
103 篇 image coding
99 篇 noise reduction
96 篇 testing
96 篇 robustness
95 篇 histograms

机构

10 篇 school of electr...
8 篇 indian statistic...
7 篇 univ penn dept r...
7 篇 department of el...
7 篇 department of el...
7 篇 univ waterloo de...
7 篇 univ michigan de...
6 篇 nanyang technol ...
6 篇 smart computer v...
6 篇 computer vision ...
5 篇 georgia inst tec...
5 篇 microsoft resear...
5 篇 carnegie mellon ...
5 篇 signal and image...
5 篇 peng cheng lab p...
4 篇 google res mount...
4 篇 texas a&m univ.
4 篇 department of sy...
4 篇 ivan kozhedub kh...
4 篇 tokyo metropolit...

作者

9 篇 landman bennett ...
8 篇 vorapoj patanavi...
8 篇 dougherty er
8 篇 h. krim
7 篇 yannick berthoum...
7 篇 a.s. willsky
7 篇 sang hwa lee
6 篇 astola jaakko t.
6 篇 prince jerry l.
6 篇 umapada pal
6 篇 alexander wong
6 篇 udupa jk
6 篇 nam ik cho
6 篇 w. pieczynski
6 篇 fessler jeffrey ...
6 篇 w.c. karl
6 篇 pesquet jean-chr...
6 篇 pal umapada
6 篇 jong-il park
6 篇 pieczynski w

语言

4,631 篇 英文
49 篇 其他
31 篇 中文
13 篇 土耳其文
1 篇 西班牙文
1 篇 法文
1 篇 俄文

检索条件"任意字段=Conference on Statistical and Stochastic Methods for Image Processing"

共 4723 条记录，以下是691-700 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 Bottom-up Fast CU Partition Scoring Mechanism for AVS3

A Bottom-up Fast CU Partition Scoring Mechanism for AVS3

引用

IEEE Visual Communications and image processing (VCIP)

作者： Shiyi Liu Zhenyu Wang Ke Qiu Jiayu Yang Ronggang Wang School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China

ISBN: (纸本)9781728173221

The third generation of Audio Video Coding Standard (AVS3) achieves 22% coding performance improvement compared with High Efficiency Video Coding (HEVC). However, the improvement of encoding efficiency comes from a more flexible block partition scheme is at the cost of much higher encoding complexity. This paper proposes a bottom-up fast algorithm to prune the time-consuming search process of the CU partition tree. To be specific, we design a scoring mechanism based on the splitting patterns traced back from the bottom to predict the possibility of a partition type to be selected as optimal. The score threshold to skip the exhaustive Rate-Distortion Optimization (RDO) procedure of the partition type is determined by statistical analysis. The experimental results show that the proposed methods can achieve 24.56% time-saving with 0.37% BDBR loss under Random Access configuration and 12.50% complexity reduction with 0.08% BDBR loss under All Intra configuration. The effectiveness leads to the adoption by the open-source platform of AVS3 after evaluated by the AVS working group.

关键词： image coding Visual communication statistical analysis Software algorithms Rate-distortion Encoding Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Nonconvex Distributed stochastic Zeroth-order Coordinate Method

Convergence Analysis of Nonconvex Distributed Stochastic Zer...

引用

IEEE conference on Decision and Control

作者： Shengjun Zhang Yunlong Dong Dong Xie Lisha Yao Colleen P. Bailey Shengli Fu OS-CAR Laboratory University of North Texas Denton TX USA School of Artificial Intelligence and Automation the MOE Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan China University of North Texas Denton TX USA

ISBN: (纸本)9781665436601

This paper investigates the stochastic distributed nonconvex optimization problem of minimizing a global cost function formed by the summation of n local cost functions. We solve such a problem by involving zeroth-order (ZO) information exchange. In this paper, we propose a ZO distributed primal–dual coordinate method (ZODIAC) to solve the stochastic optimization problem. Agents approximate their own local stochastic ZO oracle along with coordinates under an adaptive smoothing parameter. We show that the proposed algorithm achieves the convergence rate of ${\mathcal{O}}(\sqrt p /\sqrt T )$ for general nonconvex cost functions. We demonstrate the efficiency of proposed algorithms through a numerical example in comparison with the existing state-of-the-art centralized and distributed ZO algorithms.

关键词： Smoothing methods conferences Benchmark testing Cost function Approximation algorithms Information exchange Convergence

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Range Profile Recognition Method of Vehicle Targets Based on Accelerated T-SNE with Multi-polarization Fusion

High-Resolution Range Profile Recognition Method of Vehicle ...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Hao Wu Dahai Dai Penghui Ji Bo Pang Xuesong Wang State Key Laboratory of Complex Electromagnetic Environment Effects and Electronics and Information System National University of Defense Technology Changsha China College of Electronic Science National University of Defense Technology Changsha China

ISBN: (纸本)9781665446006

Polarization plays an important role in analyzing radar targets. Full polarization information has a better ability to inverse fine structures of the target. However, previous studies of high-resolution range profile (HRRP) mainly neglected effects of polarization. Therefore, a novel radar target recognition algorithm based on accelerated t-Distributed stochastic Neighbor Embedding(t-SNE) and multi-polarization weighted fusion has been proposed. Firstly, three single polarization channels, odd and even-bounce mechanism HRRP, and full polarization HRRP are described. The accelerated t-SNE method based on Barnes-Hut approximation improves the dimensionality reduction speed of processing HRRPs while maintaining the initial information of each HRRP. Also, it is capable of visualizing different targets. With the weighted fusion of posterior probabilities of multiple support vector machines (SVMs), we are able to realize recognition of targets. Experimental results of vehicle targets based on electromagnetic calculations show that recognition performance of this algorithm is superior to other methods, and it shows strong robustness under the condition of large azimuth angle.

关键词： Support vector machines Dimensionality reduction image recognition image resolution Target recognition Fuses Radar

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Breast Cancer in Mammographic images Using Efficient image Segmentation Technique

Detection and Classification of Breast Cancer in Mammographi...

引用

National conference on Control, Signal processing and Energy Systems, CSPES 2018

作者： Chanda, Pramit Brata Sarkar, Subir Kumar Computer Science and Engineering Kalyani Government Engineering College KalyaniWest Bengal India Electronics and Tele Communication Engineering Jadavpur University KolkataWest Bengal India

ISBN: (纸本)9789813293458

Breast cancer has become one of the major types of cancer-caused deaths among women of different countries throughout the world. One of the major problems of this type of cancer disease are quick detection or identifying of disease in early stages. In the cases of technologically lagging countries mortality rates are very high due to lack of early diagnosis technology of disease. According to the opinion of different clinical experts, today mammography is one of the most effective diagnosis technologies in medical science domain. So there is a requirement for more accurate methods which can easily diagnose any type of abnormalities in women breast without any kind of human intervention with higher accuracy rates. Segmentation is an approach that is very much required to identify the unambiguous region from the mammogram image. Intensity, texture, and shapes are extracted from the segmented mammogram image. The role of image processing is to detect cancer in human body when input data is in the form of images. For mammogram image classification, the feature extraction of an image with statistical parameter measurement is very important approach. Different types of feature extraction methods are generally used for better classification of abnormality present in mammogram. This technique will provide higher accuracy rates at a comparative higher speed. The statistical parameter includes entropy, mean, regression, correlation, skew, standard deviation. The experimental results achieved 89% accuracy, 74% specificity, and 89% sensitivity, illustrating the usefulness of the technique for identifying and classifying the cancer in mammogram images with maintaining more accuracy. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Joint estimation of image rotation angle and scaling factor

Joint estimation of image rotation angle and scaling factor

引用

Asia-Pacific Signal and Information processing Association Annual Summit and conference (APSIPA)

作者： Kun Yu Rongsong Yang Hui Zeng Anjie Peng School of Computer Science & Technology Southwest University of Science and Technology Mianyang China

ISBN: (纸本)9781665441629

Scaling and rotation are often involved in image tampering, and thus have attracted wide attention in image forensics. However, existing studies usually focus on detection or parameter estimation of a single operation, e. g., scaling or rotation. When a probe image has been both scaled and rotated, the statistical characteristics on which previous methods are based become much complicated and the parameter estimation task becomes much challenging. By analyzing the interaction between the features of both operations, a joint parameter estimation method is proposed in this paper. Firstly, some candidate estimations of the rotation angle are derived from the cyclic spectrum of the questioned image. Then, by taking the dependence between the peaks caused by rotation and those caused by scaling-then-rotation into consideration, these candidates can be further checked. Finally, both the scaling factor and the rotation angle can be derived with the proposed method. The proposed method is verified by conducting experiments on a subset of the BOSSbase dataset, achieves accuracy of 84.96% in rotation angle estimation, 78.88% in scaling factor estimation, and 77.13% in the estimation of both parameters.

关键词： image forensics Parameter estimation Estimation Transforms Information processing Feature extraction Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Comparative Investigation of Supervised Classification Approaches to Mapping Flooded areal extent in and around Puzhal Lake, Chennai, using image processing

A Comparative Investigation of Supervised Classification App...

引用

Advances in Computing, Communication Control and Networking (ICAC3N), International conference on

作者： Vidhya Saveetha Radhika Baskar S. Padma Saveetha Manoj Nallanathel School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India

Flooding is a natural occurrence that can result in detrimental effects on people’s mental health as well as their financial well-being. Flood inundation maps not only assist in the process of urban planning but also assist in the localization of regions that are likely to be flooded in the event of future floods. In the event of a catastrophe, when it is not possible to collect ground data using traditional methods, satellite photos are the method of choice for collecting real-time imagery. The technique and classification methods used for the development of flood maps in and around Puzhal reservoir, which is located close to Chennai, Tamil Nadu, in the Indian subcontinent, are discussed in this study. Puzhal reservoir is in Tamil Nadu. The floods that struck the southern part of the state in November and December 2015 were caused by century-high rainfall records, and the maps that have been generated are based on satellite data that was recovered both before and after the floods. Both the pre-flood and post-flood image data were processed with three supervised classification methods, namely the parallelepiped classifier, the minimum distance classifier, and the maximum likelihood classifier, and the error in the user selection of features was determined with the help of a confusion matrix. These methods were used to analyse the data obtained from the images taken before and after the flood. In addition, the data were checked for accuracy by utilising statistical data that was produced from the values of indices such as the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Water Index (NDWI). The maximum accuracy of the selected region was obtained using the parallelepiped classifier for the data gathered before the flood, while the greatest accuracy was obtained using the maximum likelihood classifier for the data gathered after the flood. It was discovered that there has been a considerable increase in the cover of green vegetation and t

关键词： Location awareness Satellites Urban planning Vegetation mapping Mental health Reservoirs Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Efficient statistical Learning Framework with Applications to Human Activity and Facial Expression Recognition 5

Efficient Statistical Learning Framework with Applications t...

引用

5th International conference on Advanced Technologies for Signal and image processing (ATSIP)

作者： Najar, Fatma Bourouis, Sami Alshar'e, Marwan Alroobaea, Roobaea Bouguila, Nizar Al Badi, Ali H. Channoufi, Ines Univ Tunis El Manar ENIT Lab RISC Robot Informat & Syst Complexes Tunis 1002 Tunisia Gulf Coll Fac Comp Sci Muscat Oman Gulf Coll Ctr Postgrad Studies & Res Muscat Oman Univ Tunis El Manar ENIT Lab LR SITI Signal Image & Technol Informat Tunis 1002 Tunisia Taif Univ At Taif Saudi Arabia Concordia Univ Concordia Inst Informat Syst Engn CIISE Montreal PQ H3G 1T7 Canada

ISBN: (纸本)9781728175133

In this paper, we address the problem of human activities and facial expression recognition by investigating the effectiveness of Bayesian inference methods. Indeed, a novel method termed as Bayesian learning for finite multivariate generalized Gaussian mixture model is developed. The multivariate generalized Gaussian distribution is encouraged by its ability to model a large range of data and its shape flexibility. Our main contribution in this work is to develop a Markov Chain Monte Carlo within Metropolis-Hastings algorithm for proposed generative model. In this research, we tackle also some key issues related to machine learning and pattern recognition such as the statistical model's parameters estimation. We demonstrate the merits of our developed learning framework over two challenging applications that concern human activity recognition and facial expression recognition.

关键词： Machine learning Multivariate Generalized Gaussian mixture models Bayesian learning Face expression recognition Human action recognition MCMC

来源：评论

学校读者我要写书评

暂无评论

VBLFI: VISUALIZATION-BASED BLIND LIGHT FIELD image QUALITY ASSESSMENT

VBLFI: VISUALIZATION-BASED BLIND LIGHT FIELD IMAGE QUALITY A...

引用

IEEE International conference on Multimedia and Expo (ICME)

作者： Xiang, Jianjun Yu, Mei Chen, Hua Xu, Haiyong Song, Yang Jiang, Gangyi Ningbo Univ Fac Informat Sci & Engn Ningbo 315211 Peoples R China

ISBN: (纸本)9781728113319

Light field image (LFI) contains the intensity and direction information of the scene. The huge amount of data and different visualization methods of LFI brings great challenges to LFI processing and its blind LFI quality assessment. This paper analyzes the human visual perception from the LFI's visualization, and proposes a novel Visualization-based Blind Light Field image quality assessment (VBLFI) model. With LFI's visualization and its depth cues, we compute mean difference image from LFI to reduce redundant information of LFI and to describe depth and structural information of LFI. LFI's multi-scale expression with curvelet transform is used to reflect the multi-channel characteristics of human visual system. So, the corresponding natural scene statistical features and energy features are extracted from the mean difference image and sub-aperture images of LFI in curvelet transform domain to form the feature vector, further used to predict the LFI quality. Compared to the representative 2D image quality assessment models and the state-of-the-art LFIQA models, the proposed VBLFI model has better prediction accuracy and stability in the public LFI databases.

关键词： light field image blind light field image quality assessment visualization curvelet transform

来源：评论

学校读者我要写书评

暂无评论

Software Auto Trigger Recording for Super Slow Motion Videos Using statistical Change Detection 1

引用

5th International conference on Computer Vision and image processing, CVIP 2020

作者： Shukla, Rakshit Jain, Ishu Pradeep Kumar, S.K. Samsung R&D Institute Bangalore Bagmane Tech Park Doddanekundi Bangalore560037 India

ISBN: (数字)9789811611032

ISBN: (纸本)9789811611025

Handheld devices like smartphones have an inherent disadvantage in recording high frame rate (greater than 480 fps) videos because of limited RAM, limited CPU and GPU capabilities and memory. Almost all handheld devices cannot record such videos indefinitely and have a time limit (usually around 1 s) to keep the system from straining and crashing. In this time limit, anywhere around 480 or 960 or more full HD (resolution 1920 × 1080) frames are recorded per second (around 1 GB data per second is encoded and stored). Most handheld devices that have the capability to record high frame-rate videos and are designed for the common user, use hardware sensor trigger to automatically detect events and record slow motion videos. High framer-rate videos are generally used to record high speed events, the user cannot be expected to press/start the recording manually by timing the event. Therefore the need arises for a method to automatically detect events and trigger the recording. Hardware sensor triggers are basically a camera sensor with an attached circuit board that detects events in the scene. However hardware triggers are expensive, have limited peripheral memory, supports fixed frame rate, cannot overcome global motion, are incompatible with heterogeneous architecture, supports fixed sensor type and inefficient in low lighting conditions. Such limitations are efficiently overcome with the proposed method without compromising on performance and accuracy. Proposed method uses statistical inference along with global motion vectors to detect event in the scene (video frames) for Super Slow Motion (SSM) video capture. The qualitative performance prior to testing on device is elucidated along with quantitative analysis with leaderboard motion detection methods. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Random access storage

来源：评论

学校读者我要写书评

暂无评论

Why is the winner the best?

Why is the winner the best?

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Eisenmann, M. Reinke, A. Weru, V. Tizabi, M. D. Isensee, F. Adler, T. J. Ali, S. Andrearczyk, V. Aubreville, M. Baid, U. Bakas, S. Balu, N. Bano, S. Bernal, J. Bodenstedt, S. Casella, A. Cheplygina, V. Daum, M. de Bruijne, M. Depeursinge, A. Dorent, R. Egger, J. Ellis, D. G. Engelhardt, S. Ganz, M. Ghatwary, N. Girard, G. Godau, P. Gupta, A. Hansen, L. Harada, K. Heinrich, M. Heller, N. Hering, A. Huaulme, A. Jannin, P. Kavur, A. E. Kodym, O. Kozubek, M. Li, J. Li, H. Ma, J. Martin-Isla, C. Menze, B. Noble, A. Oreiller, V. Padoy, N. Pati, S. Payette, K. Raedsch, T. Rafael-Patino, J. Bawa, V. Singh Speidel, S. Sudre, C. H. van Wijnen, K. Wagner, M. Wei, D. Yamlahi, A. Yap, M. H. Yuan, C. Zenk, M. Zia, A. Zimmerer, D. Aydogan, D. Bhattarai, B. Bloch, L. Bruengel, R. Cho, J. Choi, C. Dou, Q. Ezhov, I. Friedrich, C. M. Fuller, C. Gaire, R. R. Galdran, A. Faura, A. Garcia Grammatikopoulou, M. Hong, S. Jahanifar, M. Jang, I. Kadkhodamohammadi, A. Kang, I. Kofler, F. Kondo, S. Kuijf, H. Li, M. Luu, M. Martincic, T. Morais, P. Naser, M. A. Oliveira, B. Owen, D. Pang, S. Park, J. Park, S. Plotka, S. Puybareau, E. Rajpoot, N. Ryu, K. Saeed, N. Shephard, A. Shi, P. Stepec, D. Subedi, R. Tochon, G. Torres, H. R. Urien, H. Vilaca, J. L. Wahid, K. A. Wang, H. Wang, J. Wang, L. Wang, X. Wiestler, B. Wodzinski, M. Xia, F. Xie, J. Xiong, Z. Yang, S. Yang, Y. Zhao, Z. Maier-Hein, K. Jaeger, P. F. Kopp-Schneider, A. Maier-Hein, L. German Canc Res Ctr Div Intelligent Med Syst Heidelberg Germany German Canc Res Ctr Helmholtz Imaging Heidelberg Germany Heidelberg Univ Fac Math & Comp Sci Heidelberg Germany German Canc Res Ctr Div Biostat Heidelberg Germany German Canc Res Ctr Div Med Image Comp Heidelberg Germany Univ Leeds Fac Engn & Phys Sci Sch Comp Leeds W Yorkshire England HES SO Valais Wallis Univ Appl Sci & Arts Western Inst Informat Sch Management Sierre Switzerland Lausanne Univ Hosp Dept Nucl Med & Mol Imaging Lausanne Switzerland Tech Hsch Ingolstadt Ingolstadt Germany Univ Penn Ctr Artificial Intelligence & Data Sci Integrated Philadelphia PA USA Univ Penn Ctr Biomed Image Comp & Analyt Philadelphia PA USA Univ Penn Dept Pathol & Lab Med Perelman Sch Med Philadelphia PA USA Univ Penn Dept Radiol Perelman Sch Med Philadelphia PA USA Univ Washington Dept Radiol Seattle WA USA UCL Wellcome EPSRC Ctr Intervent & Surg Sci WEISS London England UCL Dept Comp Sci London England Univ Autonoma Barcelona Barcelona Spain Comp Vis Ctr Barcelona Spain Natl Ctr Tumor Dis NCT UCC Div Translat Surg Oncol Dresden Germany Ist Italiano Tecnol Dept Adv Robot Genoa Italy Politecn Milan Dept Elect Informat & Bioengn Milan Italy IT Univ Copenhagen Copenhagen Denmark Heidelberg Univ Hosp Dept Gen Visceral & Transplantat Surg Heidelberg Germany Erasmus MC Dept Radiol & Nucl Med Biomed Imaging Grp Rotterdam Rotterdam Netherlands Univ Copenhagen Dept Comp Sci Copenhagen Denmark Univ Appl Sci Western Switzerland HES SO Inst Informat Syst Sierre Switzerland Harvard Med Sch Brigham & Womens Hosp Boston MA USA Kings Coll London Sch Biomed Engn & Imaging Sci London England Univ Hosp Essen AoR Inst Artificial Intelligence Med IKIM Essen Germany Univ Nebraska Med Ctr Omaha NE USA Heidelberg Univ Hosp Dept Internal Med 3 Heidelberg Germany Rigshosp Copenhagen Univ Hosp Neurobiol Res Unit Copenhagen Denmark Arab Acad Sci & Technol Cairo Egypt CIBM Ctr Biomed Imaging L

ISBN: (纸本)9798350301298

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multi-center study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The "typical" lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work. [GRAPHICS] .

关键词： cell microscopy Medical and biological vision

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473页 << < 66 67 68 69 70 71 72 73 74 75 > >>

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：