检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Haochen Song Junlin Ouyang Yebo Gu Jian Song Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

In accomplishing the task of semantic segmentation of RGB-T remote sensing images, there is a great challenge due to severe occlusion, long-tailed data distribution, and insufficient pixel representation of certain objects. The effective use of high-level semantic contexts among various ground object categories is crucial, yet presents considerable diffi-culties. Traditional RGB-T remote sensing image semantic segmentation methods often fail to capture and utilize complex relationships and interdependencies among these categories, leading to reduced semantic segmentation accuracy. This paper proposes a novel, knowledge-enhancement module, empowering the model to utilize human-like commonsense knowledge. Specifically, we firstly employ the self-attention and cross-attention mechanisms to fuse RGB and Thermal features. Subsequently, we collect the weights of the classification layer to get a high-level semantic pool based on all the categories. Alongside this, a prior knowledge graph is developed to enable information propagation among all categories. We applied this knowledge-enhancement module to enhance the Mask R-CNN, named KEMask R-CNN. Experiments results on the RS RGB-T dataset demonstrate the progressiveness of the proposed method.

关键词： Measurement Knowledge engineering Deep learning Accuracy Fuses Semantic segmentation Semantics

来源：评论

学校读者我要写书评

暂无评论

Source Camera Identification Algorithm Based on Multi-Scale Feature Fusion

引用

computers, Materials & Continua 2024年第8期80卷 3047-3065页

作者： Jianfeng Lu Caijin Li Xiangye Huang Chen Cui Mahmoud Emam School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Shangyu Institute of Science and Engineering Hangzhou Dianzi UniversityShaoxing312300China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310000China Faculty of Artificial Intelligence Menoufia UniversityShebin El-Koom32511Egypt

The widespread availability of digital multimedia data has led to a new challenge in digital *** source camera identification algorithms usually rely on various traces in the capturing ***,these traces have become increasingly difficult to extract due to wide availability of various image processing *** Neural Networks(CNN)-based algorithms have demonstrated good discriminative capabilities for different brands and even different models of camera ***,their performances is not ideal in case of distinguishing between individual devices of the same model,because cameras of the same model typically use the same optical lens,image sensor,and image processing algorithms,that result in minimal overall *** this paper,we propose a camera forensics algorithm based on multi-scale feature fusion to address these *** proposed algorithm extracts different local features from feature maps of different scales and then fuses them to obtain a comprehensive feature *** representation is then fed into a subsequent camera fingerprint classification *** upon the Swin-T network,we utilize Transformer Blocks and Graph Convolutional Network(GCN)modules to fuse multi-scale features from different stages of the backbone ***,we conduct experiments on established datasets to demonstrate the feasibility and effectiveness of the proposed approach.

关键词： Source camera identification camera forensics convolutional neural network feature fusion transformer block graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Adaptive Feature Exchange Network with Complementary Advantages for Cooperative Classification of Hyperspectral and Multispectral Imagery

Adaptive Feature Exchange Network with Complementary Advanta...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Xingxing Fan Jiangbo Huang Yuanqin Meng Chengbiao Fu Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

With the development of remote sensing technology for earth observation, the collaborative utilization of Hyperspectral images (HSI) and multispectral images (MSI) has received increasing attention in terrestrial observation. HSI and MSI represent two typical types of optical remote sensing data and can provide rich complementary information. However, the paradoxical problem of high spatial resolution and high spectral resolution leads to difficulties in extracting complementary information. In this paper, we propose an Adaptive Feature Exchange network with Complementary Advantages (AFECAnet). Specifically, we enhance the discriminative feature extraction of HSI-MSI by introducing a spectral-spatial feature enhancement module based on a dual attention mechanism. Subsequently, in order to reduce redundant information, we design an adaptive feature interaction strategy based on batch normalization privatization factors. This strategy helps to accurately replace redundant information and reduces the computational burden on the network. Experimental results demonstrate that the proposed AFECAnet has a significant improvement in HSI-MSI collaborative classification.

关键词： Earth Adaptive systems Privatization Redundancy Collaboration Feature extraction Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Network with Local Topology and Spectral Feature Representation for Multispectral Point Cloud Classification

Graph Convolutional Network with Local Topology and Spectral...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Xueqian Chen Mingye Wang Chengbiao Fu Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Multispectral LiDAR contributes to the rapid acquisition of 3D spatial and spectral information of land covers, providing more comprehensive features for classification. Despite the impressive performance of existing Graph Neural Networks (GNNs) in point cloud classification, extracting local features with discriminative ability remains challenging in multispectral LiDAR scenes due to the uneven distribution of geometric and spectral information. To enhance the local representation of spectral features, we propose a novel Graph Convolutional Network with Local Topology and Spectral Feature Representation (GCN-LTSFR). The network constructs optimal local topological graphs of corresponding scales based on the feature distribution density of the point cloud to enhance local spectral features. Experimental results demonstrate that the proposed GCN-LTSFR outperforms several state-of-the-art methods on a real multispectral point cloud.

关键词： Point cloud compression Laser radar Three-dimensional displays Network topology Graph convolutional networks Land surface Geoscience and remote sensing

来源：评论

学校读者我要写书评

暂无评论

Differential Feature-Enhanced Fusion Network for Hyperspectral Image Classification

Differential Feature-Enhanced Fusion Network for Hyperspectr...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qingwang Wang Jiangbo Huang Pengcheng Jin Yebo Gu Tao Shen Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Recently, some hybrid networks, combining graph convolutional network (GCN) and convolutional neural network (CNN) into a unified framework, have drawn increasing attention in hyperspectral image (HSI) classification. Compared with the single CNN or GCN architecture, hybrid networks can simultaneously perform feature learning on pixel-level and superpixel-level regions and generate complementary spectral-spatial features. However, existing methods primarily employ simple fusion strategies such as linear combination or concatenation, resulting in the extracted complementary features not being fully exploited and utilized. In this work, we propose a differential feature-enhanced fusion network (DFEFN) for HSI classification. Specifically, DFEFN consists of two different convolutional network architectures, (i.e. GCN and CNN), and a differential feature enhancement fusion (DFEF) module. The features extracted by CNN and GCN can be enhanced and fused through the DFEF module. Experiments results on two benchmark HSI datasets demonstrate that DFEFN achieves better classification performance compared with state-of-the-art methods.

关键词： Representation learning Graph convolutional networks Neural networks Geoscience and remote sensing Benchmark testing Feature extraction Hybrid power systems

来源：评论

学校读者我要写书评

暂无评论

Optical polarized orthogonal matrix

引用

Photonics Research 2025年第2期13卷 373-381页

作者： SHUJUN ZHENG JIAREN TAN XIANMIAO XU HONGJIE LIU YI YANG XIAO LIN XIAODI TAN Information Photonics Research Center College of Photonic and Electronic EngineeringFujian Normal University Department of Electrical and Computer Engineering Duke University College of Photonic and Electronic Engineering Key Laboratory of Opto-Electronic Science and for Medicine of Ministry of EducationFujian Provincial Key Laboratory of Photonics TechnologyFujian Provincial Engineering Technology Research Center of Photoelectric Sensing ApplicationFujian Normal University

Multiplexing technology serves as an effective approach to increase both information storage and transmission capability. However, when exploring multiplexing methods across various dimensions, the polarization dimension encounters limitations stemming from the finite orthogonal combinations. Given that only two mutually orthogonal polarizations are identifiable on the basic Poincaré sphere, this poses a hindrance to polarization modulation. To overcome this challenge, we propose a construction method for the optical polarized orthogonal matrix(OPOM), which is not constrained by the number of orthogonal combinations. Furthermore, we experimentally validate its application in high-dimensional multiplexing of polarization holography. We explore polarization holography technology, capable of recording amplitude, phase, and polarization, for the purpose of recording and selective reconstruction of polarization multi-channels. Our research reveals that, despite identical polarization states, multiple images can be independently manipulated within distinct polarization channels through orthogonal polarization combinations, owing to the orthogonal selectivity among information.

关键词： Multiplex holography Optical data storage Optical encryption Orbital angular momentum multiplexing Signal transmission Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Leveraging Interactive Paths for Sequential Recommendation 28th

Leveraging Interactive Paths for Sequential Recommendation

引用

28th International Conference on Database Systems for Advanced applications, DASFAA 2023

作者： Li, Aoran Zang, Yalei Wang, Yani Li, Bohan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Key Laboratory of Safety-Critical Software Ministry of Industry and Information Technology Beijing China National Engineering Laboratory for Integrated Aero-Space-Ground Ocean Big Data Application Technology Xi’an China

ISBN: (纸本)9783031306716

Sequential recommendation systems dynamically predict the users’ next behaviors from chronological historical records to provide more accurate recommendations. However, in many real-world scenarios, recommenders find it difficult to make recommendations for cold-start users who have limited interactions with items. To address this issue, existing methods utilize auxiliary information to capture user preferences, which have achieved performance improvement to some extent. But with the gradual awareness of personal privacy, external information becomes difficult to obtain. Therefore, we develop a novel model called Path-based sequential Recommender for cold-start users (PathRec). PathRec exploits the rich sequential dependencies within the interactive paths to give reasonable recommendations for cold-start users without additional external information. Specifically, (i) PathRec constructs the global graph to learn the representations of the items. (ii) Then, PathRec elaborately selects the sampled paths to derive the underlying dependencies of the cold-start sequence. (iii) Finally, PathRec provides rich and complementary information to user-item interactions by strongly coupling the paths to give suitable recommendations. Extensive experiments on three datasets demonstrate the effectiveness of PathRec. In particular, our model can adapt to the cold-start users and has potential interpretability for recommendations. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network with Self-attentions 20th

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network w...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Pei, Songwen Huang, Junjie School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education East China Normal University Shanghai200062 China

ISBN: (纸本)9789819970247

computer-aided skin lesion segmentation with high precision is crucial to diagnose skin cancers in the early stage. However, the lack of pixel-level labels makes the skin lesion segmentation tasks challenging. To tackle this problem, a new weakly-supervised skin lesion segmentation network with self-attentions named SLSNet is proposed. SLSNet contains two modules and uses image-level labels as supervision information. One module named Intra-image Self-attention Seed Expansion (ISE) digs intra-image self-attentions with an expansion loss and a confidence loss to expand seed areas. The other module named Inter-image Affinity-based Noise Suppression (IAS) suppresses the noise pixels in attention maps via inter-image correlations. Extensive experiments conducted on ISIC-2017 dataset show that SLSNet achieves relatively high performance while reducing human labeling efforts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Expansion

来源：评论

学校读者我要写书评

暂无评论

Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm 24

Towards the Identifiability and Explainability for Personali...

引用

33rd ACM Web Conference, WWW 2024

作者： Li, Jiatong Liu, Qi Wang, Fei Liu, Jiayu Huang, Zhenya Yao, Fangzhou Zhu, Linbo Su, Yu University of Science and Technology of China Anhui Province Key Laboratory of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence Hefei China University of Science and Technology of China School of Computer Science and Technology Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China Hefei Normal University Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China

ISBN: (纸本)9798400701719

Personalized learner modeling using cognitive diagnosis (CD), which aims to model learners' cognitive states by diagnosing learner traits from behavioral data, is a fundamental yet significant task in many web learning services. Existing cognitive diagnosis models (CDMs) follow theproficiency-response paradigm that views learner traits and question parameters as trainable embeddings and learns them through learner performance prediction. However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners' cognitive states and the quality of web learning services. To address these problems, we propose an identifiable cognitive diagnosis framework (ID-CDF) based on a novelresponse-proficiency-response paradigm inspired by encoder-decoder models. Specifically, we first devise the diagnostic module of ID-CDF, which leverages inductive learning to eliminate randomness in optimization to guarantee identifiability and captures the monotonicity between overall response data distribution and cognitive states to prevent explainability overfitting. Next, we propose a flexible predictive module for ID-CDF to ensure diagnosis preciseness. We further present an implementation of ID-CDF, i.e., ID-CDM, to illustrate its usability. Extensive experiments on four real-world datasets with different characteristics demonstrate that ID-CDF can effectively address the problems without loss of diagnosis preciseness. Our code is available at https://***/CSLiJT/ID-CDF. © 2024 ACM.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

An alert-situation text data augmentation method based on MLM

引用

High technology Letters 2024年第4期30卷 389-396页

作者： DING Weijie MAO Tingyun CHEN Lili ZHOU Mingwei YUAN Ying HU Wentao Department of Computer and Information Security Zhejiang Police CollegeHangzhou 310053P.R.China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityHangzhou 310053P.R.China Zhejiang Dahua Technology Co. LtdHangzhou 310053P.R.China

The performance of deep learning models is heavily reliant on the quality and quantity of train-ing *** training data will lead to ***,in the task of alert-situation text classification,it is usually difficult to obtain a large amount of training *** paper proposes a text data augmentation method based on masked language model(MLM),aiming to enhance the generalization capability of deep learning models by expanding the training *** method em-ploys a Mask strategy to randomly conceal words in the text,effectively leveraging contextual infor-mation to predict and replace masked words based on MLM,thereby generating new training *** Mask strategies of character level,word level and N-gram are designed,and the performance of each Mask strategy under different Mask ratios is analyzed and *** experimental results show that the performance of the word-level Mask strategy is better than the traditional data augmen-tation method.

关键词： deep learning text data augmentation masked language model(MLM) alert-sit-uation text classification

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：