检索结果-内蒙古大学图书馆

FilterGNN:Image feature matching with cascaded outlier filters and linearattention

Computational Visual Media 2024年第5期10卷 873-884页

作者： Jun-Xiong Cai Tai-Jiang Mu Yu-Kun Lai Key Laboratory of Pervasive Computing Ministry of EducationDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China School of Computer Science and Informatics Cardiff UniversityWales CF244AGUK

The cross-view matching of local image features is a fundamental task in visual localization and 3D *** study proposes FilterGNN,a transformer-based graph neural network(GNN),aiming to improve the matching efficiency and accuracy of visual *** on high matching sparseness and coarse-to-fine covisible area detection,FilterGNN utilizes cascaded optimal graph-matching filter modules to dynamically reject outlier ***,we successfully adapted linear attention in FilterGNN with post-instance normalization support,which significantly reduces the complexity of complete graph learning from O(N2)to O(N).Experiments show that FilterGNN requires only 6%of the time cost and 33.3%of the memory cost compared with SuperGlue under a large-scale input size and achieves a competitive performance in various tasks,such as pose estimation,visual localization,and sparse 3D reconstruction.

关键词： image matching transformer linear attention visual localization sparse reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fake News Detection through the Fusion of Deep Learning and Repeat Vector Representations 2

Enhanced Fake News Detection through the Fusion of Deep Lear...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Mahmud, Tanjim Hasan, Imran Aziz, Mohammad Tarek Rahman, Taohidur Hossain, Mohammad Shahadat Andersson, Karl Rangamati Science and Technology University Department of Computer Science and Engineering Rangamati4500 Bangladesh University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh Pervasive and Mobile Computing Laboratory Luleå University of Technology Luleå97187 Sweden

ISBN: (纸本)9798350327533

The rapid dissemination of information across social networks, online news portals, and digital platforms has given rise to a pervasive issue - fake news. This misinformation, deliberately propagated by groups with ulterior motives, has the potential to divert societies in alarming directions. In a digital landscape inundated with millions of daily stories, distinguishing fact from fabrication has become a formidable challenge, casting a dark cloud of uncertainty over the information age. In response to this critical issue, this paper presents an innovative approach for enhanced fake news detection through the fusion of deep learning and Repeat Vector representations. In an era where individuals of all ages increasingly rely on online news sources, the dissemination of misinformation has become an alarming norm. It is a challenge to discern deceptive narratives that aim to sow discord and create undue *** confront this challenge head-on, we propose a deep neural network model that combines Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architectures using the Repeat Vector method. This hybrid model excels in deciphering complex patterns within 1D data, effectively tackling the menace of fake news. Our rigorous evaluation demonstrates that our proposed model outperforms contemporary methods, achieving an impressive validation accuracy of up to 98.94% on our *** a world increasingly plagued by misinformation, our approach represents a significant stride toward safeguarding the integrity of information in the digital age. © 2024 IEEE.

关键词： Autoencoder Technique Convolutional Neural Network Deep Learning Long Short-Term Memory

来源：评论

学校读者我要写书评

暂无评论

FedTG: Text-guided Federated Domain Generalization

FedTG: Text-guided Federated Domain Generalization

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Chen, Yiming He, Nan Sun, Lifeng Department of Computer Science and Technology Tsinghua University China Key Laboratory of Pervasive Computing Ministry of Education China

ISBN: (纸本)9798350368741

Federated Domain Generalization is aimed at learning a global model that generalizes well to new clients with domain shift in a privacy-preserving manner. Inspired by the powerful generation capability of Large language models (LLMs), we propose a novel method for this problem, named Text-guided Federated Domain Generalization (FedTG), which utilizes text generated by LLMs to guide the training of visual models. In the client, we align the image embeddings to the text embeddings, which provides strong generalization knowledge. In the server, we generate abundant textual descriptions about different classes, subsequently converting them into embeddings for fine-tuning the global classifier, which helps the global classifier not overfit to a particular domain. Moreover, we utilize the powerful image generation capabilities of LLMs to generate a cross-domain validation dataset to help select the most generalized model. We conduct experiments on several datasets, and the results prove that FedTG outperforms relevant baselines. © 2025 IEEE.

关键词： Data Heterogeneity Domain Shift Federated Domain Generalization Federated Learning

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection in Precision Agriculture: Deep Learning Approaches 2

Plant Disease Detection in Precision Agriculture: Deep Learn...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Dey, Puja Mahmud, Tanjim Nahar, Sultana Rokeya Hossain, Mohammad Shahadat Andersson, Karl University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh Rangamati Science and Technology University Department of Computer Science and Engineering Rangamati4500 Bangladesh Department of Computer Science and Engineering Dhaka1212 Bangladesh Luleå University of Technology Pervasive and Mobile Computing Laboratory Luleå97187 Sweden

ISBN: (纸本)9798350327533

Plants affect economy, agriculture industry and climate of any country. Therefore it is very important to take care of plants. Like human being, plants are also infected by various disease that are resulted from virus, bacteria, and fungi. It is necessary to identify these diseases in time and cure them immediately to counteract the destruction of whole plant. In recent times, deep learning networks have attained tremendous improvement in classifying image and detecting object. Therefore, in our research, some pre-Trained Convolution Neural Networks (AlexNet, VGG16, VGG19) have been utilised along with transfer learning for detecting plant diseases. First of all, pre-processing technique has been applied to improve image quality and increase the accuracy. After the training process, testing has been done for validating the results. To train these models, PlantVillage dataset has been used which contains both diseased and healthy leaves. 80% data has been utilised in training step and other 20% has been used in testing. In this research, precision, recall and f1-score are also computed besides the accuracy. Using AlexNet, VGG16, and VGG19 96.63%, 95.05%, and 95.22% testing accuracy have been achieved respectively. As we can see that among all models the modified AlexNet performed best and got 96.63% as accuracy, 92 % as precision, 91 % as recall, and 91 % as f1-score. © 2024 IEEE.

关键词： Deep Learning Fully Connected Histogram equalization Pooling RELU

来源：评论

学校读者我要写书评

暂无评论

VTSIM: Attention-Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation

VTSIM: Attention-Based Recurrent Neural Network for Intersec...

引用

作者： Liu, Jingyao Mao, Tianlu Wang, Zhaoqi Beijing Key Lab of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of Computer Science University of Chinese Academy of Sciences Beijing China

Simulating vehicle trajectories at intersections is one of the challenging tasks in traffic simulation. Existing methods are often ineffective due to the complexity and diversity of lane topologies at intersections, as well as the numerous interactions affecting vehicle motion. To address this issue, we propose a deep learning based vehicle trajectory simulation method. First, we employ a vectorized representation to uniformly extract features from traffic elements such as pedestrians, vehicles, and lanes. By fusing all factors that influence vehicle motion, this representation makes our method suitable for a variety of intersections. Second, we propose a deep learning model, which has an attention network to dynamically extract features from the surrounding environment of the vehicles. To address the issue of vehicles continuously entering and exiting the simulation scene, we employ an asynchronous recurrent neural network for the extraction of temporal features. Comparative evaluations against existing rule-based and deep learning-based methods demonstrate our model's superior simulation accuracy. Furthermore, experimental validation on public datasets demonstrates that our model can simulate vehicle trajectories among the urban intersections with different topologies including those not present in the training dataset. © 2024 John Wiley & Sons Ltd.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

SV-HaRF: a scene representation method for sparse image view synthesis

SV-HaRF: a scene representation method for sparse image view...

引用

2023 International Conference on computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2023

作者： Liu, Wei Zhang, Yu Zou, Xuechao Ma, Rui Tao, Pin Department of Computer Technology and Applications Qinghai University China Department of Computer Science and Technology Tsinghua University China Key Laboratory of Pervasive Computing Ministry of Education China

ISBN: (纸本)9781510677685

Existing view synthesis algorithms often require dozens or even hundreds of photographs taken from different angles to capture more intricate details in the resulting 3D model. While increasing the number of angles can yield better model parameters, it also significantly increases the training cost. Therefore, there is a need to reduce the quantity of input images with different angles while maintaining comparable results. In this paper, we propose SV-HaRF, which aims to reconstruct scenes by using a sparse set of angles (typically less than 100 but not less than 10) to ensure scene model integrity, as the original training sets often consist of over 100 angles. To address this issue, SV-HaRF employs hash encoding on the input sparse image resolutions to enhance the spatial constraint of these viewpoint positions during the scene reconstruction process, thereby improving the ability to restore scene information. SV-HaRF not only demonstrates outstanding performance in synthesizing sparse viewpoints for reducing model angles but also exhibits superior enhancement, compared to existing NeRF and its related variants, when the input image viewpoints remain unchanged. We conducted experiments on the NeRF Blender Synthetic dataset, showcasing significant improvements in scene synthesis achieved by SV-HaRF. © 2024 SPIE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

An Approach of Analyzing Classroom Student Engagement in Multimodal Environment by Using Deep Learning 9

An Approach of Analyzing Classroom Student Engagement in Mul...

引用

9th IEEE International Women in Engineering (WIE) Conference on Electrical and computer Engineering, WIECON-ECE 2023

作者： Nuha, Nishat Sultana Mahmud, Tanjim Rezaoana, Noortaz Hossain, Mohammad Shahadat Andersson, Karl University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh Rangamati Science and Technology University Department of Computer Science and Engineering Rangamati4500 Bangladesh Luleå University of Technology Pervasive and Mobile Computing Laboratory Sweden

ISBN: (纸本)9798350319651

Student engagement refers to the level of involve-ment, interest, attention, and active participation that students demonstrate during their learning experiences. As the engage-ment rate increases the learning rate, teachers always try to mea-sure the engagement rate in the classroom in various ways. This paper introduces a multimodal approach for detecting student engagement, a vital aspect of effective learning. Leveraging Convolutional Neural Networks (CNNs), video and audio data are integrated to capture comprehensive insights into engagement levels. The objective is to classify student engagement into three categories: highly engaged, engaged, and not engaged. Separate unimodal models are employed for speech and video data., achieving notable accuracies of 92.87 % and 94.77 %, respectively, in recognizing engagement levels. The combined model, achieved through feature-level fusion, yields a competitive accuracy of 69.36%, benefiting from the strengths of both modalities. Al-though the combined model exhibits slightly lower test accuracy compared to the individual speech and video models, its enhanced interpretability and comprehensive insights make it a promising avenue for future research. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Skinned Motion Retargeting with Dense Geometric Interaction Perception 38

Skinned Motion Retargeting with Dense Geometric Interaction ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ye, Zijie Liu, Jia-Wei Jia, Jia Sun, Shikun Shou, Mike Zheng Department of Computer Science and Technology BNRist Tsinghua University China Key Laboratory of Pervasive Computing Ministry of Education China Show Lab National University of Singapore Singapore

Capturing and maintaining geometric interactions among different body parts is crucial for successful motion retargeting in skinned characters. Existing approaches often overlook body geometries or add a geometry correction stage after skeletal motion retargeting. This results in conflicts between skeleton interaction and geometry correction, leading to issues such as jittery, interpenetration, and contact mismatches. To address these challenges, we introduce a new retargeting framework, MeshRet, which directly models the dense geometric interactions in motion retargeting. Initially, we establish dense mesh correspondences between characters using semantically consistent sensors (SCS), effective across diverse mesh topologies. Subsequently, we develop a novel spatio-temporal representation called the dense mesh interaction (DMI) field. This field, a collection of interacting SCS feature vectors, skillfully captures both contact and non-contact interactions between body geometries. By aligning the DMI field during retargeting, MeshRet not only preserves motion semantics but also prevents self-interpenetration and ensures contact preservation. Extensive experiments on the public Mixamo dataset and our newly-collected ScanRet dataset demonstrate that MeshRet achieves state-of-the-art performance. Code available at https://***/abcyzj/MeshRet. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CDGNet: A Cross-Time Dynamic Graph-Based Deep Learning Model for Vehicle-Based Traffic Speed Forecasting

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-14页

作者： Fang, Yuchen Luo, Haiyong Zhao, Fang Sun, Poly Z.H. Qin, Yanjun Zeng, Liang Hui, Bo Wang, Chenxing School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of Industrial Engineering School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Tsinghua University Beijing China University of Tulsa Tulsa USA

Vehicle-based traffic speed forecasting aims to predict the average speed of vehicles on the road in the future, which is an essential side information in intelligent vehicles and beneficial to safe autonomous driving, yet is very challenging due to the complex and dynamic spatio-temporal dependencies in real-world vehicle-based traffic. To extract intricate correlations among multiple vehicle-based speed time series, previous methods have used graph convolution networks. However, the conventional static and dynamic graphs fail to reflect the traffic evolution and the hysteresis spatial influence caused by vehicle movement. To address this issue, we propose a novel cross-time dynamic graph-based deep learning model, named CDGNet, for vehicle-based traffic speed forecasting. The model is able to effectively capture hysteresis spatial dependencies between each time slice and its historical time slices through the cross-time dynamic graph-based GCN. Meanwhile, a gating mechanism is integrated into our cross-time dynamic graph, which conforms to the sparse correlation in the real world. Besides, GCNs are incorporated into a novel encoder-decoder architecture to forecast multi-step speed. Experimental results on three real-world vehicle-based traffic speed datasets demonstrate the superiority of our CDGNet over various state-of-the-art spatio-temporal forecasting methods and the effectiveness of each component. We additionally provide a visualization of our cross-time dynamic graph to show the capability of assisting intelligent vehicles to avoid congestion. IEEE

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Belief Rule Based Expert System to Diagnose Schizophrenia Using Whole Blood DNA Methylation Data 1st

A Belief Rule Based Expert System to Diagnose Schizophrenia...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Hossain, Mohammad Shahadat Ahmed, Mumtahina Raihan, S. M. Shafkat Sharma, Angel Islam, Raihan Ul Andersson, Karl Department of Computer Science and Engineering University of Chittagong Chittagong4331 Bangladesh Port City International University Dhaka Bangladesh Pervasive and Mobile Computing Laboratory Lulea University of Technology Lulea Sweden

ISBN: (纸本)9783031346217

Schizophrenia is a severe neurological disease where a patient’s perceptions of reality are disrupted. Its symptoms include hallucinations, delusions, and profoundly strange thinking and behavior, which make the patient’s daily functions difficult. Despite identifying genetic variations linked to Schizophrenia, causative genes involved in pathogenesis and expression regulations remain unknown. There is no particular way in life sciences for diagnosing Schizophrenia. Commonly used machine learning and deep learning are data-oriented. They lack the ability to deal with uncertainty in data. Belief Rule Based Expert System (BRBES) methodology addresses various categories of uncertainty in data with evidential reasoning. Previous researches showed the association of DNA methylation (DNAm) with risk of Schizophrenia. Whole blood DNAm data, hence, is useful for smart diagnosis of Scizophrenia. However, to our knowledge, no previous studies have investigated the performance of BRBES to diagnose Schizophrenia. Therefore, in this study, we explore BRBES’ performance in diagnosing Schizophrenia using whole blood DNAm data. BRBES was optimized by gradient-free algorithms due to the limitations of gradient-based optimization. Classification thresholds were optimized to yield better results. Finally, we compared performance to two machine learning models after 5-fold cross-validation where our model achieved the highest average sensitivity (76.8%) among the three. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Diagnosis

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：