检索结果-内蒙古大学图书馆

Multi-Modal Curriculum Learning over Graphs

ACM Transactions on Intelligent Systems and technology 2019年第4期10卷 1–25页

作者： Chen Gong Jian Yang Dacheng Tao PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China UBTECH Sydney Artificial Intelligence Centre and the School of Computer Science Faculty of Engineering and Information Technologies the University of Sydney Sydney Australia

Curriculum Learning (CL) is a recently proposed learning paradigm that aims to achieve satisfactory performance by properly organizing the learning sequence from simple curriculum examples to more difficult ones. Up to now, few works have been done to explore CL for the data with graph structure. Therefore, this article proposes a novel CL algorithm that can be utilized to guide the label Propagation (LP) over graphs, of which the target is to “learn” the labels of unlabeled examples on the graphs. Specifically, we assume that different unlabeled examples have different levels of difficulty for propagation, and their label learning should follow a simple-to-difficult sequence with the updated curricula. Furthermore, considering that the practical data are often characterized by multiple modalities, every modality in our method is associated with a “teacher” that not only evaluates the difficulties of examples from its own viewpoint, but also cooperates with other teachers to generate the overall simplest curriculum examples for propagation. By taking the curriculums suggested by the teachers as a whole, the common preference (i.e., commonality) of teachers on selecting the simplest examples can be discovered by a row-sparse matrix, and their distinct opinions (i.e., individuality) are captured by a sparse noise matrix. As a result, an accurate curriculum sequence can be established and the propagation quality can thus be improved. Theoretically, we prove that the propagation risk bound is closely related to the examples’ difficulty information, and empirically, we show that our method can generate higher accuracy than the state-of-the-art CL approach and LP algorithms on various multi-modal tasks.

关键词： Curriculum learning label propagation multi-modal learning semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Learnable low-rank latent dictionary for subspace clustering

引用

Pattern Recognition 2021年 120卷

作者： Yesong Xu Shuo Chen Jun Li Lei Luo Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu 210094 China RIKEN Center for Advanced Intelligence Project Tokyo 103-0027 Japan JD Finance America Corporation USA

Recently, Self-Expressive-based Subspace Clustering (SESC) has been widely applied in pattern clustering and machine learning as it aims to learn a representation that can faithfully reflect the correlation between data points. However, most existing SESC methods directly use the original data as the dictionary, which miss the intrinsic structure (e.g., low-rank and nonlinear) of the real-word data. To address this problem, we propose a novel Projection Low-Rank Subspace Clustering (PLRSC) method by integrating feature extraction and subspace clustering into a unified framework. In particular, PLRSC learns a projection transformation to extract the low-dimensional features and utilizes a low-rank regularizer to ensure the informative and important structures of the extracted features. The extracted low-rank features effectively enhance the self-expressive property of the dictionary. Furthermore, we extend PLRSC to a nonlinear version (i.e., NPLRSC) by integrating a nonlinear activator into the projection transformation. NPLRSC cannot only effectively extract features but also guarantee the data structure of the extracted features. The corresponding optimization problem is solved by the Alternating Direction Method (ADM), and we also prove that the algorithm converges to a stationary point. Experimental results on the real-world datasets validate the superior of our model over the existing subspace clustering methods.

关键词： Subspace clustering Low-rank Feature extraction Block diagonal representation

来源：评论

学校读者我要写书评

暂无评论

Minutiae Triangle Graphs: A New Fingerprint Representation with Invariance Properties

Minutiae Triangle Graphs: A New Fingerprint Representation w...

引用

International Conference on image and Vision Computing New Zealand, IVCNZ

作者： Akmal-Jahan Mohamed-Abdul-Cader Watcharapong Chaidee Jasmine Banks Vinod Chandran Vision and Signal Processing Lab School of Electrical Engineering and Computer Science Queensland University of Technology Brisbane Australia Signal and Image Processing Laboratory Kasetsart University Bangkok Thailand

A new algorithm for matching finger or palm prints is presented for use where the full hand is considered as a biometric and only parts may be available in images for comparison. The algorithm uses an extended version of the minutiae-based approach treating the pattern as a graph of minutiae-like points. The procedure to identify minutiae-like points uses Gabor filtering, edge detection and thinning and following line patterns. A set of such points is subjected to Delaunay triangulation yielding a starting set of base-triangles for matching. There can be multiple matches of such triangles between the template and test - as similar triangles with a tolerance in the angles. Graphs are then grown to 5 and more nodes as long as a match can be found, until the maximum size matching graph is obtained. If the test matches a significant part of the template, the maximum order of graph matched will be high. The matching process is robust to transformations such as rotation, translation and scale changes. It can be applied to any part of the hand provided minutiae-like points are identifiable prior to the matching steps. The algorithm is tested using 158 fingerprint images from FVC 2002 DB1. 100 genuine and 5048 impostor scores are generated from 46 templates and 112 testing images. It had an EER of about 6%. It proves the principle behind the methodology and demonstrates that the method can be effective with degraded fingerprint images and is robust to similarity transformations present in the data. It can be applied for forensic fingerprint matching from the palm or parts other than the fingertips. By using multiple parts and multiple templates, the accuracy of the method will be improved with fusion in future versions of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of techniques for automated classification and artery quantification of the circle of Willis on TOF-MRA images: The CROWN challenge

引用

Medical image Analysis 2025年 105卷

作者： Iris N. Vos Ynte M. Ruigrok Edwin Bennink Mireille R.E. Velthuis Barbara Paic Maud E.H. Ophelders Myrthe A.D. Buser Bas H.M. van der Velden Chen Geng Matthieu Coupet Félix Dumais Adrian Galdran Junyi Zhang Wei Liu Ting Ma Madhu S. Nair Mathieu Naudin Preena K.P. Keerthi A.S. Pillai Pengcheng Shi Hugo J. Kuijf Image Sciences Institute UMC Utrecht Utrecht The Netherlands Department of Neurology and Neurosurgery University Medical Center Utrecht Utrecht The Netherlands Department of Radiology University Medical Center Utrecht Utrecht The Netherlands Princess Máxima Center for Pediatric Oncology 3584 CS Utrecht The Netherlands Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of Sciences Suzhou China Jinan Guoke Medical Technology Development Co. Ltd Jinan China XLIM Laboratory University of Poitiers UMR CNRS 7252 Poitiers France I3M Common Laboratory CNRS-Siemens University and Hospital of Poitiers Poitiers France Department of Computer Sciences Université de Sherbrooke Sherbrooke Canada Universitat Pompeu Fabra Barcelona Spain School of Electronic & Information Engineering Suzhou University of Science and Technology Suzhou China Electronic & Information Engineering School Harbin Institute of Technology (Shenzhen) Shenzhen China Artificial Intelligence & Computer Vision Lab Department of Computer Science Cochin University of Science and Technology (CUSAT) Kochi 682022 Kerala India University Hospital CHU Poitiers 86000 France DACTIM-MIS/LMA Laboratory University of Poitiers UMR CNRS 7348 Poitiers 86000 France

Assessing risk factors for intracranial aneurysm (IA) development on images is crucial for early detection of high-risk cases. IAs often form at bifurcations within the circle of Willis (CoW), but manual assessment of these arteries is both time-consuming and susceptible to inconsistencies. Previous studies on imaging markers for IA development lack sufficient evidence for clinical implications, highlighting the need for automated methods to assess CoW morphology. No systematic approach currently exists to identify the best methodological strategies. To address this, we organized a scientific challenge to compare various techniques against a clinical reference standard. Participants were tasked with (1) automated classification of CoW anatomical variants and (2) automated prediction of CoW artery diameters and bifurcation angles. We provided 300 TOF-MRA scans for training and another 300 for testing, all manually annotated. Submissions were evaluated using balanced accuracy, mean absolute error, and Pearson correlation coefficient metrics. This paper provides a detailed analysis of the results from six participating teams. The findings show that various methods may be suitable for automated CoW assessment, but that these need further improvement to meet clinical standards. The challenge remains open for future submissions, offering a benchmark for new techniques.

关键词： Classification Quantification MR angiography Circle of Willis

来源：评论

学校读者我要写书评

暂无评论

Two-View Fusion based Convolutional Neural Network for Urban Road Detection

Two-View Fusion based Convolutional Neural Network for Urban...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Shuo Gu Yigong Zhang Jian Yang Jose M. Alvarez Hui Kong PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China NVIDIA Santa Clara CA USA

In this paper, we propose a two-view fusion based convolutional neural network to estimate road areas in urban environments with LiDAR point clouds as input only. The proposed network takes two transformed LiDAR data representations, the LiDAR imageries and the camera-perspective maps, as inputs. It outputs pixel-wise road detection results in both the LiDAR's imagery view and the camera's perspective view simultaneously, in an end-to-end manner. To make better use of the data associations between two representations, we construct a novel mapping layer to transform features from the LiDAR's imagery view to the camera's perspective view in order to strengthen the road detection performance in the camera's perspective view. Experiments on the KITTI-Road dataset show that the proposed network can achieve the state-of-the-art performance among all LiDAR-only methods in real time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object tracking based on hierarchical convolutional features 4th

Object tracking based on hierarchical convolutional features

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Wang, Aili Liu, Haiyang Chen, Yushi Iwahori, Yuji Higher Education Key Lab for Measure and Control Technology and Instrumentations of Heilongjiang Harbin University of Science and Technology Harbin150080 China Institute of Image and Information Technology Harbin Institute of Technology Harbin150001 China Department of Computer Science Chubu University Aichi Japan

ISBN: (纸本)9789811322020

A novel object tracking algorithm based on hierarchical convolutional features was proposed in this paper. Firstly, the tracking algorithm uses the hierarchical networks of VGG-Net-19 to extract the hierarchical convolutional features of image, having a greater improvement than using only one layer to do that. Secondly, the algorithm obtains features by using correlation filtering method with weighted fusion, so as to determine the real position of the target according to the characteristics of different layers. The experimental results show that, compared with the current four popular object tracking algorithms, the proposed algorithm achieves better accuracy and success rate, and the results are consistent in OPE (one-pass evaluation), SRE (spatial robustness evaluation) and TRE (temporal robustness evaluation). © Springer Nature Singapore Pte Ltd. 2018.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Self-supervised linear motion deblurring

arXiv

引用

arXiv 2020年

作者： Liu, Peidong Janai, Joel Pollefeys, Marc Sattler, Torsten Geiger, Andreas Computer Vision and Geometry Group Department of Computer Science ETH Zürich Switzerland Autonomous Vision Group Max Planck Institute for Intelligent Systems Univeristy of Tübingen Tübingen Germany Microsoft Mixed Reality and Artificial Intelligence Lab Zürich Switzerland Computer Vision and Medical Image Analysis Group Chalmers University of Technology Sweden

Motion blurry images challenge many computer vision algorithms, e.g., feature detection, motion estimation, or object recognition. Deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this paper, we present a differentiable reblur model for self-supervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on sharp images for supervision. Our key insight is that motion cues obtained from consecutive images yield sufficient information to inform the deblurring task. We therefore formulate deblurring as an inverse rendering problem, taking into account the physical image formation process: we first predict two deblurred images from which we estimate the corresponding optical flow. Using these predictions, we re-render the blurred images and minimize the difference with respect to the original blurry inputs. We use both synthetic and real dataset for experimental evaluations. Our experiments demonstrate that self-supervised single image deblurring is really feasible and leads to visually compelling results. Both the code and datasets are available at https://***/ethliup/SelfDeblur. Copyright © 2020, The Authors. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2020 Challenge on image and Video Deblurring

arXiv

引用

arXiv 2020年

作者： Seungjun, Nah Sanghyun, Son Radu, Timofte Kyoung Mu, Lee Tseng, Yu Xu, Yu-Syuan Chiang, Cheng-Ming Tsai, Yi-Min Brehm, Stephan Scherer, Sebastian Xu, Dejia Chu, Yihao Sun, Qingyan Jiang, Jiaqin Duan, Lunhao Yao, Jian Purohit, Kuldeep Suin, Maitreya Rajagopalan, A.N. Ito, Yuichi Hrishikesh, P.S. Puthussery, Densen Akhil, K.A. Jiji, C.V. Kim, Guisik Deepa, P.L. Xiong, Zhiwei Huang, Jie Liu, Dong Kim, Sangmin Nam, Hyungjoon Kim, Jisu Jeong, Jechang Huang, Shihua Fan, Yuchen Yu, Jiahui Yu, Haichao Huang, Thomas S. Zhou, Ya Li, Xin Liu, Sen Chen, Zhibo Dutta, Saikat Das, Sourya Dipta Garg, Shivam Sprague, Daniel Patel, Bhrij Huck, Thomas Department of ECE ASRI SNU Korea Republic of Computer Vision Lab ETH Zurich Switzerland MediaTek Inc University of Augsburg Chair for Multimedia Computing and Computer Vision Lab Germany Peking University China Beijing University of Posts and Telecommunications China Beijing Jiaotong University China Wuhan University China Indian Institute of Technology Madras India Vermilion College of Engineering Trivandrum India CVML Chung-Ang University Korea Republic of APJ Abdul Kalam Technological University India University of Science and Technology of China China Image Communication Signal Processing Laboratory Hanyang University Korea Republic of Southern University of Science and Technology China University of Illinois at Urbana-Champaign United States CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China China IIT Madra Jadavpur University India University of Texas Austin United States Duke University Computer Science Department United States

Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on image and Video Deblurring. In this challenge, we present the evaluation results from 3 competition tracks as well as the proposed solutions. Track 1 aims to develop single-image deblurring methods focusing on restoration quality. On Track 2, the image deblurring methods are executed on a mobile platform to find the balance of the running speed and the restoration accuracy. Track 3 targets developing video deblurring methods that exploit the temporal relation between input frames. In each competition, there were 163, 135, and 102 registered participants and in the final testing phase, 9, 4, and 7 teams competed. The winning methods demonstrate the state-of-the-art performance on image and video deblurring tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge

arXiv

引用

arXiv 2020年

作者： Zhuang, Xiahai Xu, Jiahang Luo, Xinzhe Chen, Chen Ouyang, Cheng Rueckert, Daniel Campello, Victor M. Lekadir, Karim Vesal, Sulaiman RaviKumar, Nishant Liu, Yashu Luo, Gongning Chen, Jingkun Li, Hongwei Ly, Buntheng Sermesant, Maxime Roth, Holger Zhu, Wentao Wang, Jiexiang Ding, Xinghao Wang, Xinyue Yang, Sen Li, Lei School of Data Science Fudan University Shanghai China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Biomedical Image Analysis Group Imperial College London London United Kingdom Department Mathematics & Computer Science Universitat de Barcelona Barcelona Spain Friedrich-Alexander-Universität Erlangen-Nürnberg Germany School of Computer Science and Technology Harbin Institute of Technology Harbin China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Informatics Technical University of Munich Germany INRIA Université Côte d’Azur Sophia Antipolis France NVIDIA Bethesda United States School of Informatics Xiamen University Xiamen China College of Electrical Engineering Sichuan University Chengdu China Tencent AI Lab Shenzhen China

Accurate computing, analysis and modeling of the ventricles and myocardium from medical images are important, especially in the diagnosis and treatment management for patients suffering from myocardial infarction (MI). Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) provides an important protocol to visualize MI. However, automated segmentation of LGE CMR is still challenging, due to the indistinguishable boundaries, heterogeneous intensity distribution and complex enhancement patterns of pathological myocardium from LGE CMR. Furthermore, compared with the other sequences LGE CMR images with gold standard labels are particularly limited, which represents another obstacle for developing novel algorithms for automatic segmentation of LGE CMR. This paper presents the selective results from the Multi-Sequence Cardiac MR (MS-CMR) Segmentation challenge, in conjunction with MICCAI 2019. The challenge offered a data set of paired MS-CMR images, including auxiliary CMR sequences as well as LGE CMR, from 45 patients who underwent cardiomyopathy. It was aimed to develop new algorithms, as well as benchmark existing ones for LGE CMR segmentation and compare them objectively. In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR. Nine representative works were selected for evaluation and comparisons, among which three methods are unsupervised methods and the other six are supervised. The results showed that the average performance of the nine methods was comparable to the inter-observer variations. Particularly, the top-ranking algorithms from both the supervised and unsupervised methods could generate reliable and robust segmentation results. The success of these methods was mainly attributed to the inclusion of the auxiliary sequences from the MS-CMR images, which provide important label information for the training of deep neural networks. The challeng

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Improved Local Texture Features for Pedestrian Detection 3

Improved Local Texture Features for Pedestrian Detection

引用

3rd IEEE International Conference on image, Vision and Computing, ICIVC 2018

作者： Ling, Xiao Yongjun, Zhang Qian, Wang Yuewei, Li College of Computer Science and Technology Key Lab. of Intelligent Med. Image Anal. and Precise Diagn. of Guizhou Province Guizhou University Guiyang China

ISBN: (纸本)9781538649916

Pedestrian detection is a hot issue in the field of computer vision and image processing in recent years. It has important application value in the domain of unmanned cars and driver assistance systems and so on, but there are existed many problems that need to be solved. In this paper, we present an improved texture feature MLBP (Mean of Local Binary Pattern) and the CMLBP (Color based on Mean of Local Binary Pattern) feature based on various color spaces. When the uniform LBP feature does not consider the influence of noise, the mutation of central pixel and neighborhood pixel is not taken into account and therefore the extraction processes of MLBP feature improve the calculation method of the uniform LBP, which makes the extracted feature more stable. The MLBP feature is extracted from gray images, yet color images transformed into gray images generally loss a great amount of information. In view of this point, we also propose the CMLBP feature based on multiple color spaces that is a more comprehensive description of the texture feature of images. In the INRIA pedestrian dataset, many experiments have been conducted with SVM and HIKSVM classifier, and the results manifest that the detection rates of MLBP and CMLBP are much better than the uniform LBP and the basic LBP. The combination of MLBP, CMLBP and other features has been applied to pedestrian detection, which also achieves good results. © 2018 IEEE.

关键词： Local binary pattern

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：