检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Junjie Ge, Meng Pan, Zexu Cao, Rui Wang, Longbiao Dang, Jianwu Zhang, Shiliang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore Shenzhen Research Institute of Big Data Shenzhen China

The Audio-Visual Speaker Extraction (AVSE) algorithm employs parallel video recording to leverage two visual cues, namely speaker identity and synchronization, to enhance performance compared to audio-only algorithms. However, the visual front-end in AVSE is often derived from a pre-trained model or end-to-end trained, making it unclear which visual cue contributes more to the speaker extraction performance. This raises the question of how to better utilize visual cues. To address this issue, we propose two training strategies that decouple the learning of the two visual cues. Our experimental results demonstrate that both visual cues are useful, with the synchronization cue having a higher impact. We introduce a more explainable model, the Decoupled Audio-Visual Speaker Extraction (DAVSE) model, which leverages both visual cues. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Web-Based Optimization and Expansion of Multimodal High School Entrance Examination data Visualization

Web-Based Optimization and Expansion of Multimodal High Scho...

引用

Information and Communication Technology (ICTech), International Conference of

作者： Wei Zhang Duan Jian HongLiang Wang YongHong Zhang Shengyang Institute of Computing Technology University of Chinese Academy of Sciences Beijing China Big Data Technology and Cognitive Intelligence Laboratory Shandong University Beijing China

The reform of the new college entrance examination system makes students and their parents pay more attention to the feasibility and accuracy of the college entrance examination. The college entrance examination informatization can help the local admissions departments to mine and analyze the data rules from the massive college entrance examination data, and provide help and guidance for each link of volunteer application. Therefore, this paper, in order to comply with the development trend of the new college entrance examination information construction, proposes the optimization method of data visualization chart rendering and innovative combination of ideas to improve the Web rendering performance in order to enhance the interactive experience of users and the platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Technologies in data Fabric

Research on Technologies in Data Fabric

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Qingyuan Hu Zheng Yin Tao Tao Jibin Wang Zhuo Chen Bohuan Ai Yu Liu Chongzhou Liu China Mobile Information Technology Center Beijing China Cloud Computing and Big Data Research Institute China Academy of Information and Communications Technology Beijing China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

With the continuous advancement of technologies like big data, artificial intelligence, and cloud computing, enterprises are increasingly encountering challenges related to the heterogeneity of data from various sources, difficulties in querying data assets, and understanding business insights. To address these issues, data fabric emerges as a solution that leverages distributed data management. By harnessing metadata and facilitating its activation, data fabric enables organizations to efficiently and accurately manage and locate data assets. However, it is important to note that this concept is still under development and faces obstacles such as establishing connections with additional data sources and unifying semantics. Nonetheless, overall, the concept of data fabric exhibits remarkable potential in assisting enterprises in transitioning towards becoming data-driven organizations.

关键词： Industries Cloud computing Technological innovation Soft sensors Standards organizations Distributed databases Collaboration

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Activity in Untrimmed Videos Using Dense Optical Flow and Deep Neural Network 5

Early Detection of Activity in Untrimmed Videos Using Dense ...

引用

5th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2021

作者： Poonkodi, M. Vadivu, G. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India Big Data Analytics School of Computing SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9781665435246

Computer Vision is playing aremarkable role right from essentials to entertainment and thus trying to turn computer as a 'seeing' machine. Having widespread applications in most of the real world domain like healthcare, surveillance., space and social media, yet it is still challenging to match human intelligence in understanding the underlying context. Recognition of a task performed by human is important to learn the happenings, but predicting it, from the activities' initial subset becomes an aid to overcome adversities in near future. Numerous algorithms and techniques are present, yet a gap exists due to the environment in which it is recorded, illumination condition,overlapping of men and materials on captured scenes *** lead to the requirement of high power computing devices for recognition, which is considerably *** this work, Dense OPnet (Dense optical flow and Convolution neural Net) is proposed which takes in the RGB input video, converted to dense optical flow frames and then fed to three layered CNN for recognition and early detection of an activity using N/2 frames of the total input video. This method is evaluated on two benchmark datasetlike J-HMDB21 and UCF50 giving an accuracy of 93.4% and 74.3% on recognition, 68.2% and 50.24% on early action detection respectively. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

CAAVM-TransUNet: Integrating Context Anchor Attention with Transformer U-Net for Single Image Dehazing

CAAVM-TransUNet: Integrating Context Anchor Attention with T...

引用

International Conference on Computer and Communications (ICCC)

作者： Hongwei Zeng Lijun Fu Jin Li Xu Li Xiangdong He Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China Laboratory of Big Data and Artificial Intelligence Technolgy Shandong University Jinan China Institute of Future Artificial Intelligence Technology and Innovative Applications Beijing China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Image dehazing has always been a challenging visual task. Most of the existing image dehazing algorithms are constructed based on convolutional neural networks, which perform very well in capturing local features and detail information, but fall short of the ability to capture remote contextual information. In this paper, we introduce a novel method called CAAVM-TransUNet. The method integrates Transformer into the traditional U -shaped architecture. Unlike earlier Transformer-based U-Net, CAA VM-TransUNet introduces the State Space Sequence Model (SSM) to enhance the ability of capturing remote dependencies, and adds Context Anchor Attention (CAA) to filter redundant features in the hopping connectivity layer prior to the encoder and decoder, so that the model can better focus on the key feature information and reduce the interference of irrelevant information, thus improving the effect of image dehazing. The results show that the dehazing effect of CAAVM-TransUNet on RESIDE dataset is better than the existing methods, especially the PSNR in the SOTS-outdoor dataset reaches 36.13 dB, which provides a new idea to solve the complex image dehazing problem.

关键词： Visualization PSNR Interference Drives Transformers Information filters Decoding Environmental monitoring Convolutional neural networks Context modeling

来源：评论

学校读者我要写书评

暂无评论

Diabetic retinopathy identification based on multi-sourcefree domain adaptation

引用

International Journal of Ophthalmology(English edition) 2024年第7期17卷 1193-1204页

作者： Guang-Hua Zhang Guang-Ping Zhuo Zhao-Xia Zhang Bin Sun Wei-Hua Yang Shao-Chong Zhang School of Big Data Intelligent Diagnosis&Treatment Industry Taiyuan UniversityTaiyuan 030032Shanxi ProvinceChina Shanxi Key Laboratory of Intelligent Optimization Computing and Blockchain Technology Taiyuan Normal UniversityTaiyuan 030619Shanxi ProvinceChina Shanxi Eye Hospital Taiyuan 030002Shanxi ProvinceChina College of Computer Science and Technology Taiyuan Normal UniversityTaiyuan 030619Shanxi ProvinceChina Shenzhen Eye Institute Shenzhen Eye HospitalJinan UniversityShenzhen 518040Guangdong ProvinceChina

AIM:To address the challenges of data labeling difficulties,data privacy,and necessary large amount of labeled data for deep learning methods in diabetic retinopathy(DR)identification,the aim of this study is to develop a source-free domain adaptation(SFDA)method for efficient and effective DR identification from unlabeled ***:A multi-SFDA method was proposed for DR *** method integrates multiple source models,which are trained from the same source domain,to generate synthetic pseudo labels for the unlabeled target ***,a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class *** is performed using three color fundus photograph datasets(APTOS2019,DDR,and EyePACS).RESULTS:The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification *** demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target ***:The multi-SFDA method provides an effective approach to overcome the challenges in DR *** method not only addresses difficulties in data labeling and privacy issues,but also reduces the need for large amounts of labeled data required by deep learning methods,making it a practical tool for early detection and preservation of vision in diabetic patients.

关键词： diabetic retinopathy multisource-free domain adaptation pseudo-label generation softmaxconsistence minimization

来源：评论

学校读者我要写书评

暂无评论

Multi User Offloading Strategy for Edge computing in Charging Load Forecasting Scenario

Multi User Offloading Strategy for Edge Computing in Chargin...

引用

2023 China Automation Congress, CAC 2023

作者： Long, Hongyu Huang, Zhaocheng Liu, Chao Xu, Daolin Li, Tao Ye, Fan School of Automation/School of Industrial Internet Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China School of Automation/School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing China Institute of State Grid Chongqing Electric Power Company Economic and Technical Research Chongqing China

ISBN: (纸本)9798350303759

In order to mitigate the impact of large-scale new energy vehicle charging access to the grid, edge computing technology is widely used in smart charging perception scenarios. By deploying various edge terminal devices or application software at the perception sites, it can collect and predict the power load in various regions, so as to effectively guide and control the charging amount of new energy vehicles. However, with the increase of computing demand brought by the increase of edge device nodes, the edge server may face the problem of insufficient computing resources, which will affect the low latency characteristics. To alleviate this problem, this paper abstracts each edge terminal device as an independent user with task computing needs, establishes a multi-user edge computing system, and proposes a multi-level resource allocation strategy for edge computing, Decompose and allocate communication channel resources and server resources in multiple rounds. This method can reduce task latency by optimizing the task offloading ratio and resource allocation method of users while meeting their basic needs. The simulation results show that this method can effectively reduce the latency of task computation in multi user scenarios. © 2023 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Refining COVID-19 Biomarker Classification through Automated LASSO-PCA Feature Selection

Refining COVID-19 Biomarker Classification through Automated...

引用

Student Conference on Research and Development (SCOReD)

作者： Hafiza Zoya Mojahid Jasni Mohamad Zain Marina Yusoff Abdul Basit Abdul Kadir Jumaat Mushtaq Ali College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam Selangor Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI)Universiti Teknologi MARA Shah Alam Selangor Malaysia Faculty of Computing Riphah International University Islamabad Pakistan

ISBN: (数字)9798331510077

ISBN: (纸本)9798331510084

Machine learning, through predictive analytics, offers valuable insights into COVID-19 progression. Building high-performing models requires an effective feature selection process to identify key features that enhance accuracy while removing irrelevant ones. Methods like LASSO show promise but also have limitations. The present research investigates the efficacy of integrating LASSO (Least Absolute Shrinkage and Selection Operator) guided Principal Component Analysis (PCA) for dimensionality reduction and feature selection in predictive modeling of COVID-19 outcomes. Using a dataset that includes blood biomarker information, RT-PCR results, blood test values, and patient demographics, our goal was to identify critical features that enhance model performance. After preprocessing, LASSO-guided PCA selected significant components based on Bayesian (BIC) and Akaike (AIC) Information Criteria. These components were used to train and evaluate three classifiers: XGBoost, Logistic Regression, and Support Vector Machine (SVM). Results show that the LASSOguided PCA approach based on AIC enhances model performance, with SVM and Logistic Regression achieving AUROC scores of $\mathbf{\sim} 0.85$ and $\mathbf{0. 8 4}$, and accuracy scores around $\mathbf{7 8 \%}$. The seven most important features are ‘Age’, ‘WBC’, ‘Platelets’, ‘Neutrophils’, ‘Basophils’, ‘AST’ and ‘ALP’. This study highlights the potential of machine learning models in improving COVID-19 diagnostic accuracy and emphasizes the value of automated, data-driven feature selection.

关键词： Support vector machines COVID-19 Measurement Logistic regression Accuracy Biological system modeling Feature extraction Blood Research and development Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Robust Real-World Image Super-Resolution against Adversarial Attacks

arXiv

引用

arXiv 2022年

作者： Yue, Jiutao Li, Haofeng Wei, Pengxu Li, Guanbin Lin, Liang Sun Yat-Sen University China Shenzhen Research Institute of Big Data Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen China

Recently deep neural networks (DNNs) have achieved significant success in real-world image super-resolution (SR). However, adversarial image samples with quasi-imperceptible noises could threaten deep learning SR models. In this paper, we propose a robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features. The rationale is that on the SR task clean images or features have a different pattern from the attacked ones in the frequency domain. Observing that existing adversarial attacks usually add high-frequency noises to input images, we introduce a novel random frequency mask module that blocks out high-frequency components possibly containing the harmful perturbations in a stochastic manner. Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module. Based on the above ideas, we devise a novel real-world image SR framework that combines the proposed frequency mask modules and the proposed adversarial classifier with an existing super-resolution backbone network. Experiments show that our proposed method is more insensitive to adversarial attacks and presents more stable SR results than existing models and defenses. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

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：