检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Qian, Bo Chen, Hao Wang, Xiangning Che, Haoxuan Kwon, Gitaek Kim, Jaeyoung Choi, Sungjin Shin, Seoyoung Krause, Felix Unterdechler, Markus Hou, Junlin Feng, Rui Li, Yihao Daho, Mostafa El Habib Wu, Qiang Zhang, Ping Yang, Xiaokang Cai, Yiyu Li, Huating Jia, Weiping Sheng, Bin Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong Department of Ophthalmology Shanghai Jiao Tong University Affiliated Sixth People’s Hospital Shanghai China VUNO Inc. Seoul Korea Republic of AI/DX Convergence Business Group KT Korea Republic of Johannes Kepler University Linz Linz Austria School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Academy for Engineering and Technology Fudan University China LaTIM UMR 1101 Inserm Brest France University of Western Brittany Brest France Department of Computer Science and Engineering The Ohio State University Ohio United States Department of Biomedical Informatics The Ohio State University Ohio United States Translational Data Analytics Institute The Ohio State University Ohio United States MoE Key Lab of Artificial Intelligence Artificial Intelligence Institute Shanghai Jiao Tong University Shanghai China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore Department of Endocrinology and Metabolism Shanghai Jiao Tong University Affiliated Sixth People’s Hospital Shanghai China Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes Shanghai China

computer-assisted automatic analysis of diabetic retinopathy (DR) is of great importance in reducing the risks of vision loss and even blindness. Ultra-wide optical coherence tomography angiography (UW-OCTA) is a non-invasive and safe imaging modality in DR diagnosis system, but there is a lack of publicly available benchmarks for model development and evaluation. To promote further research and scientific benchmarking for diabetic retinopathy analysis using UW-OCTA images, we organized a challenge named "DRAC - Diabetic Retinopathy Analysis Challenge" in conjunction with the 25th International Conference on Medical Image Computing and computer Assisted Intervention (MICCAI 2022). The challenge consists of three tasks: segmentation of DR lesions, image quality assessment and DR grading. The scientific community responded positively to the challenge, with 11, 12, and 13 teams from geographically diverse institutes submitting different solutions in these three tasks, respectively. This paper presents a summary and analysis of the top-performing solutions and results for each task of the challenge. The obtained results from top algorithms indicate the importance of data augmentation, model architecture and ensemble of networks in improving the performance of deep learning models. These findings have the potential to enable new developments in diabetic retinopathy analysis. The challenge remains open for post-challenge registrations and submissions for benchmarking future methodology developments. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Network Parameter Generation for One-Shot Object Detection

Network Parameter Generation for One-Shot Object Detection

引用

2019 IEEE International Conference on Unmanned Systems, ICUS 2019

作者： Wang, Kang Zhao, Jiajia Wang, Yang Zhou, Shuigeng Fudan University Shanghai Key Lab of Intelligent Information Processing School of Computer Science Shanghai200433 China Beijing Electro-Mechanical Engineer Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Nanchang University School of Information Engineering 330031 China

ISBN: (纸本)9781728137926

Recent object detection models have achieved satisfactory performance by deep learning with large-scale annotated datasets. However, these models often perform poorly when the training examples are not sufficient enough, especially for one-shot object detection where there is only one training example of each target class. In this paper, we propose a network parameter generation framework for effective one-shot object detection. By leveraging the semantic relationship between the source-domain and the target-domain (new classes), our framework can generate network parameters for the new classes directly. Furthermore, we develop two implementation schemes for this framework: weighting-based parameter generation and regression-based parameter generation. These two schemes use different information to construct the relationship and transfer knowledge from the source-domain to the target-domain. Experiments on the PASCAL-OSCD benchmark show that our methods can significantly boost the performance of one-shot object detection. © 2019 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Chinese Lexical Based Sentiment Analysis Framework in Meteorology

Chinese Lexical Based Sentiment Analysis Framework in Meteor...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yinan Li Fuquan Zhang Yifan Zhu Sifan Zhang Yu Mao Zhendong Niu School of Computer Science and Technology Beijing Institute of Technology Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China School of Computing and Information University of Pittsburgh Pittsburgh PA USA

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Evaluating the performance of meteorological service not only relies on physical measurements but also requires public feedback. As a significant part of the evaluation, assessing the sentiment of these feedbacks gives an insightful view which can help to establish reliable decision support in policy making and emergency responding. However, climate and weather are always accompanying phenomena in the evolutionary process of human beings, making the climate and weather-related words themselves contain a large number of extend meanings in people's daily expression. These polysemy phenomena have led to a decline in the performance of traditional general sentiment calculations in the vertical field of meteorology. As far as we know, there is no Chinese sentiment calculation tool in the meteorological field, due to the different expressions between different languages. Facing with the above problems and issues, this paper proposes and establishes a sentiment analysis based on lexicon-based framework of Chinese text in the meteorological field. The framework fuses two major sentiment assessment method consists of two approaches, namely machine learning-based and knowledge based one. First, word embedding similarity and word co-occurrence methods are utilized to construct the domain sentiment dictionary which includes 8,796 negative words and 4,751 positive words. Then, by using the extend sentiment dictionary to select theme words from original text as feature, machine learning models are introduced to assess the sentiment tendency. Experiment showed that the performance of the proposed framework was improved up to 85.79% in terms of overall accuracy compared with traditional methods.

关键词： Dictionaries Meteorology Sentiment analysis Feature extraction Machine learning Vocabulary Semantics

来源：评论

学校读者我要写书评

暂无评论

Supervised hashing with recurrent scaling 3rd

Supervised hashing with recurrent scaling

引用

3rd APWeb and WAIM Joint Conference on Web and Big Data, APWeb-WAIM 2019

作者： Fu, Xiyao Bin, Yi Wang, Zheng Wei, Qin Chen, Si Guizhou Provincial Key Laboratory of Public Big Data Guizhou University GuiyangGuizhou550025 China School of Computer Science and Engineering University of Electronic Science and Technology of China ChengduSichuan611731 China Information Science Academy China Electronics Technology Group Corporation Beijing China

ISBN: (纸本)9783030260743

Learning to hash is a method that can deal with content-based information retrieval efficiently. Traditional learning to hash methods, however, lack the ability to map the generated hash codes to the high-level semantic space. Attributes, as a kind of higher level of visual data representation compared to features, have the potential ability in deep learning to boost the performance. Utilizing attributes from visual data in deep learning to hash can link every bit of the hash codes and a certain type of attributes, therefore giving the hash code an explicit explanation. This paper presents a novel framework, named Deep Recurrent Scaling Hashing (DRSH), to solve the traditional image retrieval problem. The hash codes generated from DRSH are a combination of the outputs of each step of an enhanced LSTM and features generated from convolutional neural nets and are learned through images' attributes. This RNN is reformed to adjust the decorrelation of data flowing between each cell step, which not only makes the learning phase benefit from the ability of recurrent neural nets to learn with recurrent memory but also enable the availability of each hash bit to preserve distinct information. Experiments show that this framework can achieve appreciable performance on major datasets, and also have the ability to explain the meaning of hash codes based on attributes. © 2019, Springer Nature Switzerland AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multi-level graph convolutional network with automatic graph learning for hyperspectral image classification

arXiv

引用

arXiv 2020年

作者： Wan, Sheng Gong, Chen Pan, Shirui Yang, Jie Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Detecting Interest-Factor Influenced Abnormal Evaluation of Teaching via Multimodal Embedding and Priori Knowledge Based Neural Network

Detecting Interest-Factor Influenced Abnormal Evaluation of ...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yu Mao Yifan Zhu Sifan Zhang Dexiu Zhang Fuquan Zhang Xiaozhong Fan School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Computer Science Minnan Normal University Zhangzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Student evaluations of teaching (SET) helps to quantitatively measure the teaching performance of classes. However, concerns arouse when the result of SET and students' final grades are highly positively correlated, which means the students may make the evaluation based on the final grades they take. For the purpose of avoiding retaliation and mutual reward rating, some methods based on statistics or rules are used to detect the presence of anomaly evaluation. Whereas, the problem is still challenging since the characteristics of this abnormal evaluation are implicit and multimodal. Besides, additional information such as the domain of subject, instructors' teaching style, and the reputation spread by students also requires corresponding prior knowledge to supplement the abnormal evaluation detection model. Therefore, in this paper, we proposed a multimodal embedding and prior knowledge based neural network to detect potential so called Interest Factor Influenced Abnormal Evaluation (IFAE). The method proposed in this paper uses SDNE and PV-DM to embed the evaluation network between students and teachers and the comment text of students. Taking into account the continuity of mutual evaluation between students and teachers during the teaching cycles and the different emphasis of students' comment texts on teachers, the features of students and teachers are comprehensively constructed. Then, the attention mechanism is used in the comment text to perform final prediction jointly with above features. The experiment result shows that our proposed model outperforms other state-of-art models which based on single type of features on F1 score by 9.25%.

关键词： Education Feature extraction Neural networks Data mining Knowledge based systems computer science Quality control

来源：评论

学校读者我要写书评

暂无评论

BASSET: Bandpass-Adaptive Single-pulse SEarch Toolkit – Optimized Sub-Band Pulse Search Strategies for Faint Narrow-Band FRBs

arXiv

引用

arXiv 2025年

作者： Cao, J.H. Wang, P. Li, D. Pan, Q.H. Mao, K. Niu, C.H. Zhang, Y.K. Qu, Q.Y. Lu, W.J. Zhang, J.S. Zhu, Y.H. Wang, Y.D. Chen, H.X. Chen, X.L. Gügercinoğlu, E. Fang, J.H. Feng, Y. Gao, H. Huang, Y.F. Li, J. Miao, C.C. Tsai, C.W. Yao, J.M. You, S.P. Zhao, R.S. Liu, Q.Z. Weng, S.M. Yew, S.H. Zhang, J. Zhang, L. Zhou, D.K. Zhu, W.W. National Astronomical Observatories Chinese Academy of Sciences 20A Datun Road Chaoyang District Beijing100101 China University of Chinese Academy of Sciences Beijing100049 China Institute for Frontiers in Astronomy and Astrophysics Beijing Normal University Beijing102206 China Department of Astronomy Tsinghua University Beijing100084 China Zhejiang Lab Zhejiang Hangzhou311121 China Central China Normal University Wuhan430079 China Institute for Astronomy School of Physics Zhejiang University Hangzhou310027 China Department of Astronomy Beijing Normal University Beijing100875 China School of Astronomy and Space Science Nanjing University Nanjing210023 China Ministry of Education Nanjing210023 China Department of Astronomy School of Physical Sciences University of Science and Technology of China Hefei230026 China Xinjiang Astronomical Observatory Chinese Academy of Sciences Urumqi830011 China Key Laboratory of Information and Computing Science Guizhou Province Guizhou Normal University Guiyang550001 China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal University Guiyang550001 China Purple Mountain Observatory Chinese Academy of Sciences Nanjing210023 China College of Physics and Electronic Engineering Qilu Normal University Jinan250200 China School of Physics and Astronomy Shanghai Jiao Tong University Shanghai200240 China Centre for Astrophysics and Supercomputing Swinburne University of Technology P.O. Box 218 HawthornVIC3122 Australia

The existing single-pulse search algorithms for fast radio bursts (FRBs) do not adequately consider the frequency bandpass pattern of the pulse, rendering them incomplete for the relatively narrow-spectrum detection of pulses. We present a new search algorithm for narrow-band pulses to update the existing standard pipeline, Bandpass-Adaptive Single-pulse SEarch Toolkit (BASSET). The BASSET employs a time-frequency correlation analysis to identify and remove the noise involved by the zero-detection frequency band, thereby enhancing the signal-to-noise ratio (SNR) of the pulses. The BASSET algorithm was implemented on the FAST real dataset of FRB 20190520B, resulting in the discovery of additional 79 pulses through reprocessing. The new detection doubles the number of pulses compared to the previously known 75 pulses, bringing the total number of pulses to 154. In conjunction with the pulse calibration and the Markov Chain Monte Carlo (MCMC) simulated injection experiments, this work updates the quantified parameter space of the detection rate. Moreover, a parallel-accelerated version of the BASSET code was provided and evaluated through simulation. BASSET has the capacity of enhancing the detection sensitivity and the SNR of the narrow-band pulses from the existing pipeline, offering high performance and flexible applicability. BASSET not only enhances the completeness of the low-energy narrow-band pulse detection in a more robust mode, but also has the potential to further elucidate the FRB luminosity function at a wider energy scale. Copyright © 2025, The Authors. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

3D-EPI Blip-Up/Down Acquisition (BUDA) with CAIPI and Joint Hankel Structured Low-Rank Reconstruction for Rapid Distortion-Free High-Resolution T2* Mapping

arXiv

引用

arXiv 2022年

作者： Chen, Zhifeng Liao, Congyu Cao, Xiaozhi Poser, Benedikt A. Xu, Zhongbiao Lo, Wei-Ching Wen, Manyi Cho, Jaejin Tian, Qiyuan Wang, Yaohui Feng, Yanqiu Xia, Ling Chen, Wufan Liu, Feng Bilgic, Berkin School of Biomedical Engineering Guangdong Provincial Key Laboratory of Medical Image Processing Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology Southern Medical University Guangzhou China Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Department of Radiology Harvard Medical School CharlestownMA United States Department of Data Science and AI Faculty of IT Monash University ClaytonVIC Australia Department of Radiology Stanford University Stanford CA United States Maastricht Brain Imaging Center Faculty of Psychology and Neuroscience University of Maastricht Netherlands Department of Radiotherapy Cancer Center Guangdong Provincial People's Hospital Guangdong Academy of Medical Science Guangzhou China Siemens Medical Solutions BostonMA United States Department of Chemical Pathology The Chinese University of Hong Kong Hong Kong Division of Superconducting Magnet Science and Technology Institute of Electrical Engineering Chinese Academy of Sciences Beijing China Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence Key Laboratory of Mental Health of the Ministry of Education Southern Medical University Guangzhou China Department of Biomedical Engineering Zhejiang University Hangzhou China Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China School of Information Technology and Electrical Engineering The University of Queensland BrisbaneQLD Australia Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States

Purpose: This work aims to develop a novel distortion-free 3D-EPI acquisition and image reconstruction technique for fast and robust, high-resolution, whole-brain imaging as well as quantitative T2* mapping. Methods: 3D-Blip-Up and -Down Acquisition (3D-BUDA) sequence is designed for both single- and multi-echo 3D GRE-EPI imaging using multiple shots with blip-up and -down readouts to encode B0 field map information. Complementary k-space coverage is achieved using controlled aliasing in parallel imaging (CAIPI) sampling across the shots. For image reconstruction, an iterative hard-thresholding algorithm is employed to minimize the cost function that combines field map information informed parallel imaging with the structured low-rank constraint for multi-shot 3D-BUDA data. Extending 3D-BUDA to multi-echo imaging permits T2* mapping. For this, we propose constructing a joint Hankel matrix along both echo and shot dimensions to improve the reconstruction. Results: Experimental results on in vivo multi-echo data demonstrate that, by performing joint reconstruction along with both echo and shot dimensions, reconstruction accuracy is improved compared to standard 3D-BUDA reconstruction. CAIPI sampling is further shown to enhance the image quality. For T2* mapping, T2* values from 3D-Joint-CAIPI-BUDA and reference multi-echo GRE are within limits of agreement as quantified by Bland-Altman analysis. Conclusions: The proposed technique enables rapid 3D distortion-free high-resolution imaging and T2* mapping. Specifically, 3D-BUDA enables 1-mm isotropic whole-brain imaging in 22 s at 3 T and 9 s on a 7 T scanner. The combination of multi-echo 3D-BUDA with CAIPI acquisition and joint reconstruction enables distortion-free whole-brain T2* mapping in 47 s at 1.1×1.1×1.0 mm3 resolution. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Cross-lingual implicit discourse relation recognition with co-training

引用

Frontiers of information technology & Electronic Engineering 2018年第5期19卷 651-661页

作者： Yao-jie LU Mu XU Chang-xing WU De-yi XIONG Hong-ji WANG Jin-song SU School of Software Xiamen University State Key Laboratory for Novel Software Technology Nanjing University Institute of Software Chinese Academy of Sciences Provincial Key Laboratory for Computer Information Processing Technology Soochow University

A lack of labeled corpora obstructs the research progress on implicit discourse relation recognition （DRR） for Chinese, while there are some available discourse corpora in other languages, such as English. In this paper, we propose a cross-lingual implicit DRR framework that exploits an available English corpus for the Chinese DRR task. We use machine translation to generate Chinese instances from a labeled English discourse corpus. In this way, each instance has two independent views： Chinese and English views. Then we train two classifiers in Chinese and English in a co-training way, which exploits unlabeled Chinese data to implement better implicit DRR for Chinese. Experimental results demonstrate the effectiveness of our method.

关键词： Cross-lingual Implicit discourse relation recognition Co-training

来源：评论

学校读者我要写书评

暂无评论

Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Yang, Yehui Zhang, Huixin Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Computer Science and Technology University of Cambridge United Kingdom

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：