检索结果-内蒙古大学图书馆

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350374889

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable (Sa S) bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all Sa S probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed L2 regularizers on all the test cases. Soft diamond regularizers also outperformed L1 lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization. © 2024 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Learning group interaction for sports video understanding from a perspective of athlete

引用

Frontiers of computer science 2024年第4期18卷 175-188页

作者： Rui HE Zehua FU Qingjie LIU Yunhong WANG Xunxun CHEN Intelligent Recognition and Image Processing(IRIP)Lab School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Hangzhou Innovation Institute Behang UniversityHangzhou 310051China National Computer Network Emergency Response Technical Team/Coordination Center of China(CNCERT or CNCERT/CC) Beijing 100029China

Learning activities interactions between small groups is a key step in understanding team sports *** research focusing on team sports videos can be strictly regarded from the perspective of the audience rather than the *** team sports videos such as volleyball and basketball videos,there are plenty of intra-team and inter-team *** this paper,a new task named Group Scene Graph Generation is introduced to better understand intra-team relations and inter-team relations in sports *** tackle this problem,a novel Hierarchical Relation Network is *** all players in a video are finely divided into two teams,the feature of the two teams’activities and interactions will be enhanced by Graph Convolutional Networks,which are finally recognized to generate Group Scene *** evaluation,built on Volleyball dataset with additional 9660 team activity labels,a Volleyball+dataset is proposed.A baseline is set for better comparison and our experimental results demonstrate the effectiveness of our ***,the idea of our method can be directly utilized in another video-based task,Group Activity *** show the priority of our method and display the link between the two ***,from the athlete’s view,we elaborately present an interpretation that shows how to utilize Group Scene Graph to analyze teams’activities and provide professional gaming suggestions.

关键词： group scene graph group activity recognition scene graph generation graph convolutional network sports video understanding

来源：评论

学校读者我要写书评

暂无评论

Analysis of multimodal fusion strategies in deep learning for ischemic stroke lesion segmentation on computed tomography perfusion data

引用

Multimedia Tools and Applications 2025年第10期84卷 7493-7518页

作者： Raju, Chintha Sri Pothu Neelapu, Bala Chakravarthy Laskar, Rabul Hussain Muhammad, Ghulam Speech and Image Processing Lab Department of ECE National Institute of Technology Silchar Assam Silchar788010 India Department of Biotechnology and Medical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia

Stroke poses a significant risk to human life. Segmenting and immediately treating the stroke core stops its further development, therefore, enhancing the likelihood of survival. Convolutional neural networks (CNN) have been very successful in medical image segmentation, namely in the field of deep learning, and have produced the most advanced outcomes. Multi-modal images provide superior outcomes in the segmentation of stroke lesions compared to single-modal images. The integration of input from several modalities at various levels is crucial in determining performance and producing diverse outcomes in deep learning models that use multimodalities. Further investigation is required to explore the optimal methods for processing multimodal data in CNNs, the influence of fusion on CNN learning, and the effect of fusion strategies on lesions of varying sizes. To examine the impact of a multi-modal fusion method on lesion segmentation, we assessed four models using distinct fusion techniques, including early, late, bottleneck, and hierarchical fusions. This study discusses the various fusion procedures used in segmenting the lesion using computed tomography perfusion data. In addition, both quantitative and qualitative assessments, including deep feature analysis and feature similarity, were conducted to assess the impact of the fusion technique on the model’s performance. Furthermore, we examined the influence of fusion techniques on the size of the lesion. In addition, we analyzed the advantages and disadvantages of several multi-modal fusion systems. Our findings demonstrate that the bottleneck fusion technique got the highest dice score, 0.582, on the Ischemic Stroke Lesion Segmentation 2018 validation data as a result of its capacity to construct complex relationships across several modalities. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deepdive:a learning-based approach for virtual camera in immersive contents

引用

Virtual Reality & Intelligent Hardware 2022年第3期4卷 247-262页

作者： Muhammad IRFAN Muhammad MUNSIF Department of Computer Science Oakland UniversityMichiganUSA Digital Image Processing Laboratory Islamia CollegePeshawarPakistan

A 360°video stream provide users a choice of viewing one's own point of interest inside the immersive *** head or hand manipulations to view the interesting scene in a 360°video is very tedious and the user may view the interested frame during his head/hand movement or even lose *** automatically extracting user's point of interest(UPI)in a 360°video is very challenging because of subjectivity and difference of *** handle these challenges and provide user's the best and visually pleasant view,we propose an automatic approach by utilizing two CNN models:object detector and aesthetic score of the *** proposed framework is three folded:pre-processing,Deepdive architecture,and view selection *** first fold,an input 360°video-frame is divided into three sub frames,each one with 120°*** second fold,each sub-frame is passed through CNN models to extract visual features in the sub-frames and calculate aesthetic ***,decision pipeline selects the sub frame with salient object based on the detected object and calculated aesthetic *** compared to other state-of-the-art techniques which are domain specific approaches i.e.,support sports 360°video,our syste m support most of the 360°videos *** evaluation of proposed framework on our own collected data from various websites indicate performance for different categories of 360°videos.

关键词： Virtual reality Immersive contents Deep learning Aesthetic Saliency

来源：评论

学校读者我要写书评

暂无评论

GAN-DIRNet:A Novel Deformable image Registration Approach for Multimodal Histological images

引用

computers, Materials & Continua 2024年第7期80卷 487-506页

作者： Haiyue Li Jing Xie Jing Ke Ye Yuan Xiaoyong Pan Hongyi Xin Hongbin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai200240China Department of Pathology Ruijin HospitalShanghai Jiao Tong UniversitySchool of MedicineShanghai200025China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai200240China Global Institute of Future Technology Shanghai Jiao Tong UniversityShanghai200240China

Multi-modal histological image registration tasks pose significant challenges due to tissue staining operations causing partial loss and folding of *** neural network(CNN)and generative adversarial network(GAN)are pivotal inmedical image ***,existing methods often struggle with severe interference and deformation,as seen in histological images of conditions like Cushing’s *** argue that the failure of current approaches lies in underutilizing the feature extraction capability of the discriminator *** this study,we propose a novel multi-modal registration approach GAN-DIRNet based on GAN for deformable histological image *** begin with,the discriminators of two GANs are embedded as a new dual parallel feature extraction module into the unsupervised registration networks,characterized by implicitly extracting feature descriptors of specific ***,modal feature description layers and registration layers collaborate in unsupervised optimization,facilitating faster convergence and more precise ***,experiments and evaluations were conducted on the registration of the Mixed National institute of Standards and Technology database(MNIST),eight publicly available datasets of histological sections and the Clustering-Registration-Classification-Segmentation(CRCS)dataset on the Cushing’s *** results demonstrate that our proposed GAN-DIRNet method surpasses existing approaches like DIRNet in terms of both registration accuracy and time efficiency,while also exhibiting robustness across different image types.

关键词： Histological images registration deformable registration generative adversarial network cushing’s disease machine learning computer vision

来源：评论

学校读者我要写书评

暂无评论

From spatial data warehouse into NoSQL document-oriented database: case study Forest fire risk management. 7

From spatial data warehouse into NoSQL document-oriented dat...

引用

7th International Conference on computer science and Artificial Intelligence, CSAI 2023

作者： Belaroussi, Asma Derbal, Khalissa Lounis, Mohamed Fazil Mensouri, Adel Belhadj-Aissa, Mostefa ENS-Kouba Image Processing and Radiation Laboratory Ltir Usthb Algeria Lsi Laboratory Usthb Algeria Computer Science Department Usthb Algeria Image Processing and Radiation Laboratory Ltir Usthb Algeria

ISBN: (纸本)9798400708688

Spatial Data Warehouses are commonly used for decision making systems, but they require a costing time and considerable resources to analyze all stored information. The traditional approach uses relational databases with Spatial R-OLAP, which can't handle the large amount of data that SDWs contain. As an alternative, Spatial Big Data and NoSQL systems are better suited. This study proposes transformation rules, allowing a direct translation of the spatial-multidimensional schema components as the spatial facts and measures and spatial dimensions and hierarchies from the conceptual level to the target spatial NoSQL model. We then developed a geo-decisional tool powered by the NoSQL spatial data warehouse to manage the risk of the Forest Fire phenomenon in Algeria. © 2023 ACM.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

A Novel Split Learning-Based Consumer Electronics Network Traffic Anomaly Detection Framework for Smart City Environment

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 4197-4204页

作者： Kim, Dong-Jo Amma, N. G. Bhuvaneswari Sarveshwaran, Velliangiri Sunchon National University Department of Image Design Sunchon57922 Korea Republic of Vellore Institute of Technology School of Computer Science and Engineering Chennai600 127 India Srm Institute of Science and Technology Department of Computational Intelligence Chennai603 203 India National Chung Cheng University Department of Computer Science and Information Engineering Chiayi621301 Taiwan

Due to technology advancement, connectivity and intelligence have revolutionized the consumer electronics (CE) world and IoT systems pose a new cybersecurity threat because smart devices are constantly connected to sensors, which are connected directly to enormous cloud servers. To address the cybersecurity vulnerabilities associated with IoT in smart cities, we provide a Software Defined Network (SDN) orchestrated anomaly detection system based on Split Learning (SL). The traffic generated by the CE is pre-processed and the relevant traffic features are selected. Then the model is split into at least two sub-models using SL to detach model training from the necessity for direct access to raw data. Client-side sub-models are trained on local training data on client devices, whereas server-side sub-models are trained on servers. Experiments show that the proposed SL-based CE network anomaly detection framework decreases computation needs on the client side by just computing a sub-model rather than the complete computationally costly model. The proposed solution has the potential to detect compromised CE network traffic in smart city environments. As evidenced by our results, the proposed framework performed significantly better than the existing state-of-the-art anomaly detection system in terms of accuracy. © 1975-2011 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Backpropagation Autoencoding Networks for image Compression and Denoising 22

Bidirectional Backpropagation Autoencoding Networks for Imag...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350345346

A bidirectional autoencoder learns or approximates an identity mapping as it trains a single network with a version of the new bidirectional backpropagation algorithm. Ordinary unidirectional autoencoders find many uses in image processing and in large language models. But they use separate networks for encoding and decoding. Bidirectional auto encoders use the same synaptic weights for encoding and decoding. The forward pass encodes while the backward pass decodes. Bidirectional auto encoders improved network performance and significantly reduced memory usage and used fewer parameters. Simulations compared unidirectional with bidirectional autoencoders for image compression and de noising. The models trained on the MNIST handwritten-digit and CIFAR-IO image datasets. The performance measures were the peak signal-to-noise ratio and the index of structural similarity. Bidirectional autoencoders outperformed unidirectional autoencoders and still reduced the number of trainable synaptic parameters by about 50%. © 2023 IEEE.

关键词： autoencoders bidirectional au-toencoders Bidirectional backpropagation bidirectional networks large language models variational autoencoders

来源：评论

学校读者我要写书评

暂无评论

Attention-stacking adaptive fuzzy neural networks for autism diagnosis

Attention-stacking adaptive fuzzy neural networks for autism...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Shuzhan Xiao, Lei Huang, Hui Hu, Zhongyi Wenzhou University Institute of Intelligent Information System Wenzhou University Key Laboratory of Intelligent Image Processing and Analysis College of Computer Science and Artificial Intelligence Wenzhou China

ISBN: (纸本)9798350386226

The current diagnostic methods for Autism Spectrum Disorder (ASD) based on Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) face two significant challenges. Firstly, the functional connectivity networks (FCNs) of the brain are subject to uncertainty due to noise interference during the rs-fMRI acquisition process. Secondly, variations in equipment parameters across different imaging sites lead to diverse distributions of collected features. To address these issues, this paper introduces a novel Multi-Task Stacked Adaptive Fuzzy Neural Network (AT-STTSK) specifically designed for Autism Spectrum Disorder (ASD) classification. The proposed network seamlessly integrates a Multi-Output TSK (MO-TSK) fuzzy system, a Stacked Autoencoder (SAE), and a Transformer. This integration aims to reduce the impact of uncertainty factors, enhance the model's interpretability, and leverage the multi-head attention mechanisms to capture both local and global information, thus strengthening feature learning. Additionally, we explore the utilization of a Contrastive Learning (CL) strategy to further optimize the model. By incorporating these advancements, our AT-STTSK network offers a promising approach for improving the accuracy and reliability of ASD diagnosis based on rs-fMRI data. The validity of the method in this paper is verified on ABIDE dataset, and the result shows that the accuracy rate can reach 85.7% at most. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Language-Guided Semantic Alignment for Point Cloud-Based 3D Scene Graph Generation

Language-Guided Semantic Alignment for Point Cloud-Based 3D ...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Lee, Suhyeon Jeong, Jinwoo Jeong, Taehyun Kim, Sungjei Intelligent Image Processing Research Center Korea Electronics Technology Institute Seongnam Korea Republic of School of Computer Science and Engineering Korea University of Technology and Education Cheonan Korea Republic of

ISBN: (纸本)9798331510756

In this paper, we propose a novel model called LAP, Language-guided semantic Alignment for Point cloud-based 3D semantic scene graph generation. Point cloud-based 3D scene graph generation is the task of predicting the category of each instance present in a 3D point cloud scene and the relationships between them. Our model leverages text embeddings for objects, predicates, and triplets during network training, enabling the network to generate reliable semantic scene graphs. To this end, we introduce three loss functions that leverage text embed dings to semantically align the features for scene graph prediction. Comparative experiments with previous methods on the 3DSSG dataset demonstrate the effectiveness of the LAP model. © 2025 IEEE.

关键词： Cloud platforms

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：