检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Haoran Deng, Junkai Chen, Xuhui Hou, Fei Wang, Wencheng Qin, Hong Qian, Chen He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science Stony Brook University United States SenseTime Research

Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces α-NeuS—an extension of NeuS—that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https://***/728388808/alpha-NeuS. © 2024, CC BY.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

A Multi-Domain Coupled Spatio-temporal Feature Interaction Model for EEG Emotion Recognition

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Xu, Liyun Xing, Xiaofang Chang, Jiang Lin, Pan Shanxi University Institute of Big Data Science and Industry The School of Computer and Information Technology Taiyuan030006 China Hunan Normal University Center for Mind & Brain Sciences Institute of Interdisciplinary Studies Hunan Changsha410081 China

Electroencephalogram (EEG) is a powerful tool for monitoring the brain’s electrical activity, providing valuable insights into an individual’s emotional state. The task of emotion recognition from EEG signals has gained significant attention, particularly with the advent of deep learning techniques. However, challenges such as the inherent instability of EEG signals and insufficient feature extraction methods can hinder effective recognition. In this study, we propose a novel approach for EEG emotion recognition—the Multi-Domain Coupled Spatio-Temporal Feature Interaction Model (MCSFIM). First, leveraging the energy aggregation characteristics of the Fractional Fourier Transform (FrFT), we extract the features of the EEG signal fractional power spectral density (FrPSD) from multi-domain to address the non-stationarity of EEG signals and construct a more comprehensive feature set. Then, by integrating Graph Convolutional Networks (GCN) and Bidirectional Long-Short-Term Memory (BiLSTM) networks, we capture the spatial topology and temporal dependencies of EEG signals for feature interaction and classification. To further enhance classification accuracy, we propose a Dynamically Weighted Loss (DWL) function to reduce inter-class imbalance and achieve more precise emotion recognition. Extensive experimental results on the DEAP and SEED datasets demonstrate that the proposed method outperforms other state-of-the-art methods. © 1963-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Structure injected weight normalization for training deep networks

Structure injected weight normalization for training deep ne...

引用

作者： Yuan, Xu Shen, Xiangjun Mehta, Sumet Li, Teng Ge, Shiming Zha, Zhengjun School of Computer Science and Telecommunication Engineering Jiangsu University Jiangsu Zhenjiang212013 China School of electrical engineering and Automation Anhui University Jiangsu Anhui Hefei230039 China Institute of information engineering CAS Chinese academy of sciences Beijing100086 China School of data science University of science and technology of china Anhui Hefei230026 China

Weight normalization (WN) can help to stabilize the distribution of activations over layers, which boost the performance of DNNs in generalization. In this paper, we further propose deep structural weight normalization (DSWN) methods to inject the network structure measurements into the WN to fully acknowledge the data propagation through the neural network. In DSWN, two novel structural measurements are developed to impose regularity on each network weight using different penalty matrices. One is sparsity measurement (DSWN-SM). In this measurement, L1,2 weight regularization is applied in our proposed model to promote competition for features between network weights to obtain a sparsity network and finally prune the network. The other is neuron measurement (DSWN-NM). It uses L2 norm of column weight to scale up or down the importance of each intermediate neuron, which leads to accelerating the speed of network convergence. Extensive experiments on several benchmark image datasets using fully connected network and convolution neural network are performed, and the proposed DSWN-SM and DSWN-NM methods are compared with state-of-the-art sparsity and weight normalization methods. The results show that DSWN-SM can reduce the number of trainable parameters while guaranteeing high accuracy, whereas DSWN-NM can accelerate the convergence while improving the performance of deep networks. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation

arXiv

引用

arXiv 2023年

作者： Gu, Yunqi Zhou, Tao Zhang, Yizhe Zhou, Yi He, Kelei Gong, Chen Fu, Huazhu PCA Laboratory The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The School of Computer Science and Engineering Southeast University Nanjing211189 China The Medical School Nanjing University Nanjing210023 China The National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The Institute of High Performance Computing A*STAR Singapore

Medical image segmentation plays a crucial role in computer-aided diagnosis. However, existing methods heavily rely on fully supervised training, which requires a large amount of labeled data with time-consuming pixel-wise annotations. Moreover, accurately segmenting lesions poses challenges due to variations in shape, size, and location. To address these issues, we propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image Segmentation (DEC-Seg). First, we propose a Cross-level Feature Aggregation (CFA) module that integrates cross-level adjacent layers to enhance the feature representation ability across different resolutions. To address scale variation, we present a scale-enhanced consistency constraint, which ensures consistency in the segmentation maps generated from the same input image at different scales. This constraint helps handle variations in lesion sizes and improves the robustness of the model. Furthermore, we propose a cross-generative consistency scheme, in which the original and perturbed images can be reconstructed using cross-segmentation maps. This consistency constraint allows us to mine effective feature representations and boost the segmentation performance. To further exploit the scale information, we propose a Dual-scale Complementary Fusion (DCF) module that integrates features from two scale-specific decoders operating at different scales to help produce more accurate segmentation maps. Extensive experimental results on multiple medical segmentation tasks (polyp, skin lesion, and brain glioma) demonstrate the effectiveness of our DECSeg against other state-of-the-art semi-supervised segmentation approaches. The implementation code will be released at https://***/taozh2017/DECSeg. Copyright © 2023, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Ur-Sam: Enhancing the Reliability of Segment Anything Model For Auto-Prompting Medical Image Segmentation with Uncertainty Rectification

SSRN

引用

SSRN 2024年

作者： Zhang, Yichi Hu, Shiyao Ren, Sijie Pan, Tan Jiang, Chen Cheng, Yuan Qi, Yuan Artificial Intelligence Innovation and Incubation Institute Fudan University Shanghai China Shanghai Academy of Artificial Intelligence for Science Shanghai China School of Data Science Fudan University Shanghai China School of Computer Science and Technology Xi’an Jiaotong University Xi’an China

Recent advancements in prompt-driven image segmentation exemplified by the Segment Anything Model (SAM) have shown remarkable potential for universal medical image segmentation. However, their reliance on manual prompting each target structure from testing images poses a significant challenge due to the need for domain-specific knowledge from medical experts and directly increases the burden for applications. Auto-prompting methods have been introduced to enable automatic segmentation but often lack reliability, while low-quality prompts induced by noisy annotation can significantly compromise the accuracy of segmentation. In this paper, we propose UR-SAM, an uncertainty rectified SAM framework to enhance the reliability of auto-prompting medical image segmentation. Building upon a localization framework for automatic prompt generation, we incorporates a prompt augmentation module to obtain a series of input prompts for uncertainty estimation. Subsequently, we adapt an uncertainty-based rectification strategy to leverage the distribution of estimated uncertainty and further improve the segmentation performance without the need of supplementary training or fine-tuning. We conduct extensive experiments on two representative medical datasets covering the segmentation of 22 head-and-neck organs and 13 abdominal organs. Experimental results demonstrate significant improvements in dice similarity coefficient with up to 10.7 % and 13.8 %, demonstrating efficiency and broad capabilities for medical image segmentation without manual prompting. © 2024, The Authors. All rights reserved.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

How Well Do CMIP6 and CMIP5 Models Simulate the Climatological Seasonal Variations in Ocean Salinity?

引用

Advances in Atmospheric sciences 2022年第10期39卷 1650-1672,I0005-I0015页

作者： Yuanxin LIU Lijing CHENG Yuying PAN Zhetao TAN John ABRAHAM Bin ZHANG Jiang ZHU Junqiang SONG College of Meteorology and Oceanography College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China Institute of Atmospheric Physics Chinese Academy of SciencesBeijing 100029China Center for Ocean Mega-Science Chinese Academy of SciencesQingdao 266071China University of Chinese Academy of Sciences Beijing 100049China School of Engineering University of St.Thomas2115 Summit Ave.St PaulMN 55105USA Marine Science Data Center Institute of OceanologyChinese Academy of SciencesQingdao 266071China

This paper includes a comprehensive assessment of 40 models from the Coupled Model Intercomparison Project phase 5(CMIP5)and 33 models from the CMIP phase 6(CMIP6)to determine the climatological and seasonal variation of ocean salinity from the surface to 2000 *** general pattern of the ocean salinity climatology can be simulated by both the CMIP5 and CMIP6 models from the surface to 2000-m ***,this study shows an increased fresh bias in the surface and subsurface salinity in the CMIP6 multimodel mean,with a global average of−0.44 g kg^(−1) for the sea surface salinity(SSS)and−0.26 g kg^(−1) for the 0-1000-m averaged salinity(S1000)compared with the CMIP5 multimodel mean(−0.25 g kg^(−1) for the SSS and−0.07 g kg^(−1) for the S1000).In terms of the seasonal variation,both CMIP6 and CMIP5 models show positive(negative)anomalies in the first(second)half of the year in the global average SSS and *** model-simulated variation in SSS is consistent with the observations,but not for S1000,suggesting a substantial uncertainty in simulating and understanding the seasonal variation in subsurface *** CMIP5 and CMIP6 models overestimate the magnitude of the seasonal variation of the SSS in the tropics in the region 20°S-20°N but underestimate the magnitude of the seasonal change in S1000 in the Atlantic and Indian *** assessments show new features of the model errors in simulating ocean salinity and support further studies of the global hydrological cycle.

关键词： salinity climatology seasonal cycle CMIP5 CMIP6 upper ocean

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Legal Case Analysis through Advanced Event Extraction

Revolutionizing Legal Case Analysis through Advanced Event E...

引用

Recent Advances in science and Engineering Technology (ICRASET), International Conference on

作者： S Shivananda Lincy Meera Mathews Sanvi Nikkam Prashanth Kambli Rajashree D Ingale Prashant Koparde Information Science and Engineering M S Ramaiah Institute of Technology Bangalore India K S School of Engineering and Management Artificial Intelligence & Data Science Bangalore India K S School of Engineering and Management Computer Science & Business Systems Bangalore India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

In India manually evaluating court records was time-consuming and prone to errors, leading to delays in justice administration. Legal Sarathi, an automated event extraction tool was proposed to address this issue, it utilized Large Language Models coupled with other cutting-edge Natural Language Processing (NLP) techniques. Legal Sarathi analyzes unstructured legal case documents to extract time frames, significant participants and major events to improve speed and accuracy. It featured state-of-the-art Natural Language Processing (NLP) capabilities for prompt and precise case analysis whose aims included speeding up the analysis of court proceedings and real-time information retrieval, while simultaneously providing critical data for informed decision-making. The tools deliverables comprised an automated event extraction system, a highly preprocessed data corpus, a sophisticated NLP model, a user-friendly interface and thorough validation results. Ultimately, this established an improved and equitable legal system in India to ensure that all parties received quick and fair access to the courts and fostered public trust.

关键词： Productivity Visualization Text analysis Law Feature extraction Transformers Solids Natural language processing Libraries User experience

来源：评论

学校读者我要写书评

暂无评论

TOPOGRAPH: AN EFFICIENT GRAPH-BASED FRAMEWORK FOR STRICTLY TOPOLOGY PRESERVING IMAGE SEGMENTATION

arXiv

引用

arXiv 2024年

作者： Lux, Laurin Berger, Alexander H. Weers, Alexander Stucki, Nico Rueckert, Daniel Bauer, Ulrich Paetzold, Johannes C. School of Computation Information and Technology Technical University of Munich Germany Department of Computing Imperial College London United Kingdom Munich Center for Machine Learning Germany Munich Data Science Institute Technical University of Munich Munich Germany

Topological correctness plays a critical role in many image segmentation tasks, yet most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy. Existing topology-aware methods often lack robust topological guarantees, are limited to specific use cases, or impose high computational costs. In this work, we propose a novel, graph-based framework for topologically accurate image segmentation that is both computationally efficient and generally applicable. Our method constructs a component graph that fully encodes the topological information of both the prediction and ground truth, allowing us to efficiently identify topologically critical regions and aggregate a loss based on local neighborhood information. Furthermore, we introduce a strict topological metric capturing the homotopy equivalence between the union and intersection of prediction-label pairs. We formally prove the topological guarantees of our approach and empirically validate its effectiveness on binary and multi-class datasets. Our loss demonstrates state-of-the-art performance with up to fivefold faster loss computation compared to persistent homology methods. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

External Validation of an AI mHealth Tool for Gingivitis Detection among Older Adults at Daycare Centers: A Pilot Study

引用

International Dental Journal 2025年第3期75卷 1970-1978页

作者： Chau, Reinhard Chun Wang Cheng, Andrew Chi Chung Mao, Kaijing Thu, Khaing Myat Ling, Zhaoting Tew, In Meei Chang, Tien Hsin Tan, Hong Jin McGrath, Colman Lo, Wai-Lun Hsung, Richard Tai-Chiu Lam, Walter Yu Hang Faculty of Dentistry The University of Hong Kong Hong Kong Special Administrative Region China Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong Special Administrative Region China Department of Computer Science Hong Kong Chu Hai College Hong Kong Special Administrative Region China Faculty of Dentistry The National University of Malaysia Kuala Lumpur Malaysia School of Dental Medicine University of Pennsylvania Philadelphia PA United States Eastman Dental Institute University College London London United Kingdom

Objectives: Periodontal disease is a significant public health concern among older adults due to its relationship with tooth loss and systemic health disease. However, there are numerous barriers that prevent older adults from receiving routine dental care, highlighting the need for innovative screening tools at the community level. This pilot study aimed first, to evaluate the accuracy of GumAI, a new mHealth tool that uses AI and smartphones to detect gingivitis, and the user acceptance of personalized oral hygiene instructions provided through the new tool, among older adults in day-care community centers. Methods: Participants were invited from 3 day-care community centers. Intraoral photographs were captured and assessed by both GumAI (test) and a panel consisting of 2 calibrated periodontists and a dentist (benchmark). Mean sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and F1 score were calculated to determine GumAI's diagnostic performance in comparison to the benchmark. User acceptance with this tool was assessed using 2 Rasch Theory-based 5-point Likert-type questions. Results: 44 participants were recruited out of 80 invited older adults. GumAI demonstrated a sensitivity of 0.93 and specificity of 0.50 compared to the panel‘s assessments, with a PPV of 0.90 and NPV of 0.56. The accuracy and F1 scores were 0.85 and 0.91, respectively. All participants expressed high acceptance of the process. Conclusion: GumAI demonstrates high sensitivity, PPV, accuracy, and F1 score compared to the panel's assessments but falls relatively short in specificity and NPV. Despite this, the tool was highly accepted by older adults, indicating its potential to enhance gingivitis detection and oral hygiene management in community settings. Further refinements are necessary to improve specificity and validate usability measures. Clinical Relevance: This study may pave the way for broader applications of mHealth systems in co

关键词： Community dentistry Gingivitis Machine learning Mobile health Periodontal diseases Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Recursion and Student Preparedness of Functional Programming

Journal of Computing Sciences in Colleges

引用

Journal of computing sciences in Colleges 2025年第8期40卷

作者： Sunjae Park Frank Kreimendahl School of Computing and Data Science Wentworth Institute of Technology Boston MA

Functional programming languages conduct computation through expressions and compositions of values [6], unlike traditional imperative programming languages (like Java or Python) where the basic means of computation are through statements and the modification of variables. Many functional programming languages such as Scala have started to gain ground in various programming language rankings [1], and even traditional imperative programming languages have introduced functional programming paradigms, such as Java [7] and Rust [3]. Use of a functional programming language is a core knowledge unit in the CS 2023 curricula as well [5].

关键词：

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：