检索结果-内蒙古大学图书馆

CAT: a coarse-to-fine attention tree for semantic change detection

Visual Intelligence 2023年第1期1卷 1-12页

作者： Wei, Xiu-Shen Xu, Yu-Yan Zhang, Chen-Lin Xia, Gui-Song Peng, Yu-Xin School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory of Integrated Services Networks Xidian University Xi’an China Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing China 4Paradigm Inc Beijing China School of Computer Science and Institute of Artificial Intelligence Wuhan University Wuhan China Wangxuan Institute of Computer Technology Peking University Beijing China

Semantic change detection (SCD) and land cover mapping (LCM) are always treated as a dual task in the field of remote sensing. However, due to diverse real-world scenarios, many SCD categories are not easy to be clearly recognized, such as “water-vegetation” and “water-tree”, which can be regarded as fine-grained differences. In addition, even a single LCM category is usually difficult to define. For instance, some “vegetation” categories with litter vegetation coverage are easily confused with the general “ground” category. SCD/LCM becomes challenging under both challenges of its fine-grained nature and label ambiguity. In this paper, we tackle the SCD and LCM tasks simultaneously by proposing a coarse-to-fine attention tree (CAT) model. Specifically, it consists of an encoder, a decoder and a coarse-to-fine attention tree module. The encoder-decoder structure extracts the high-level features from input multi-temporal images first and then reconstructs them to return SCD and LCM predictions. Our coarse-to-fine attention tree, on the one hand, utilizes the tree structure to better model a hierarchy of categories by predicting the coarse-grained labels first and then predicting the fine-grained labels later. On the other hand, it applies the attention mechanism to capture discriminative pixel regions. Furthermore, to address label ambiguity in SCD/LCM, we also equip a label distribution learning loss upon our model. Experiments on the large-scale SECOND dataset justify that the proposed CAT model outperforms state-of-the-art models. Moreover, various ablation studies have demonstrated the effectiveness of tailored designs in the CAT model for solving semantic change detection problems. © The Author(s) 2023.

关键词： Attention tree Coarse-to-fine Fine-grained recognition Label ambiguity Semantic change detection

来源：评论

学校读者我要写书评

暂无评论

A Multi-Channel Composite Recommendation Method in Federated Learning

A Multi-Channel Composite Recommendation Method in Federated...

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber Science and technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Chen, Shi Li, Qianmu Wang, Qi Zhao, Xinjian Ge, Hao Li, Nianzhe State Grid Jiangsu Information & Telecommunication Company Nanjing China School of Computer Science Ana Engineering Nanjing University of Science and Technology Nanjing China State Grid Smart Grid Research Institute Co. Ltd. State Grid Key Laboratory of Information & Network Security Nanjing China

ISBN: (纸本)9798350304602

There are various data security risks in power grid systems, and recommendation systems are a good solution to the selection of security strategies. Federated learning is a machine learning framework that can protect the data privacy of each participant and can effectively solve the data security external collaborative training modeling challenges. This paper proposed a flexible implantable recommendation algorithm based on knowledge graph and multi-channel composite to enhance federated learning on demand. The algorithm designs three different feature extraction modules to learn to construct multi-dimensional features on multi-attribute collaborative knowledge graphs. Among them, the distance translation module utilizes the Trans R recommendation algorithm to learn the internal semantic structure information in knowledge graph triples and terminal-security policy selection history;the random walk module uses the Node2Vec algorithm to learn the homogeneous and Structured information in the multi-attribute collaborative knowledge graph;the graph convolutional network module learns the high-order neighborhood multi-attribute collaborative information of terminal/security policy nodes through multi-layer feature propagation and aggregation. The composite network module adopts a convolutional neural network-like operation to first locally optimize the three modules, and then extracts the highly informative elements to obtain the final feature representation of the terminal/security policy. Finally, the algorithm merges the vectors of terminal-security policy pairs into the multi-layer perceptron to learn and calculate the prediction score for recommendation. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based activity recognition and fine motor identification using 2D skeletons of cynomolgus monkeys

引用

Zoological Research 2023年第5期44卷 967-980页

作者： Chuxi Li Zifan Xiao Yerong Li Zhinan Chen Xun Ji Yiqun Liu Shufei Feng Zhen Zhang Kaiming Zhang Jianfeng Feng Trevor W.Robbins Shisheng Xiong Yongchang Chen Xiao Xiao School of Information Science and Technology Micro Nano System Center Fudan UniversityShanghai 200433China Department of Anesthesiology Huashan HospitalKey Laboratory of Computational Neuroscience and Brain-Inspired IntelligenceMinistry of EducationBehavioral and Cognitive Neuroscience CenterInstitute of Science and Technology for Brain-Inspired IntelligenceMOE Frontiers Center for Brain ScienceFudan UniversityShanghai 200433China Kuang Yaming Honors School Nanjing UniversityNanjingJiangsu 210023China Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China State Key Laboratory of Primate Biomedical Research Institute of Primate Translational MedicineKunming University of Science and TechnologyKunmingYunnan 650500China New Vision World LLC. Aliso ViejoCalifornia 92656USA Behavioural and Clinical Neuroscience Institute University of CambridgeCambridgeCB21TNUK

Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and ***,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized *** this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton ***,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in *** the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual *** Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.

关键词： Action recognition Fine motor identification Two-stream deep model 2D skeleton Non-human primates Rett syndrome

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Interest-Aware Message-Passing GCN for Recommendation

A Dynamic Interest-Aware Message-Passing GCN for Recommendat...

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Weichao He Yi Zhu Mei Song Zixin Wu Guosheng Hao School of Computer Science and Technology Jiangsu Normal University Xuzhou Jiangsu China Jiangsu Engineering Technology Research Center of ICT in Education Xuzhou Jiangsu China Key Laboratory of Safety-Critical Software (Nanjing University of Aeronautics and Astronautics) Ministry of Industry and Information Technology Nanjing Jiangsu China

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

Over the past few years, Graph Convolutional Networks (GCN) have emerged as a promising tool in the field of recommendation. They have the ability to effectively learn user and item embeddings by leveraging collaborative signals from higher-order neighbors. Nevertheless, the recommendation models based on GCN also face a common issue. As more layers are added, the node embeddings start to become increasingly similar and eventually become indistin-guishable, leading to a decline in performance. To address the issues at hand, we present a recommendation model called DIMP-GCN. This model utilizes a Dynamic Interest-aware Message-Passing approach, where users and interacted items are organized into distinct subgraphs based on their interests. Within each subgraph, single-layer graph convolution operations are performed. As a result, the users who have been updated are divided based on their interests once again, leading to dynamic changes in subgraph partitioning as the network layers stack. Nodes are able to acquire more accurate representations through this process. We conduct extensive experiments on three established datasets, showcasing the superior performance of our DIMP-GCN compared to other state-of-the-art GCN-based recommendation models.

关键词： Accuracy Convolution Graph convolutional networks Collaboration Software quality Software reliability Security Faces

来源：评论

学校读者我要写书评

暂无评论

A Privacy Leakage Detection Method for Personalized Course Recommendation Based on Pi-Calculus

A Privacy Leakage Detection Method for Personalized Course R...

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Zixin Wu Xiaoyun Zhou Yi Zhu Chenyu Wang Guosheng Hao School of Computer Science and Technology Jiangsu Normal University Xuzhou Jiangsu China Jiangsu Engineering Technology Research Center of ICT in Education Xuzhou Jiangsu China Key Laboratory of Safety-Critical Software (Nanjing University of Aeronautics and Astronautics) Ministry of Industry and Information Technology Nanjing Jiangsu China

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

Privacy protection is one of the main approaches to improve the security and reliability of personalized course recommendation systems. However, the current privacy protection methods for personalized course recommendation mainly focus on data protection, but ignore the potential privacy leakage that may be caused by the system behavior. In addition, privacy protection is not fully considered in the initial phases of system development and design. To address this issue, this paper presents a methodology for detecting privacy leakage in personalized course recommendation systems using the process algebra Pi-Calculus. Firstly, the basic semantics and evolution rules of Pi-Calculuss as well as the definition of mutual simulation techniques are introduced. Then the personalized course recommendation system is mapped to a process algebra Pi-Calculus, a formal description and analysis of the interaction behavior of the components of the personalized course recommendation system is given, and finally a framework for privacy leakage detection is introduced and applied to a case study to detect whether there is privacy leakage behavior in the recommendation system by the inter-simulation technique. Experiments demonstrate that the method can effectively detect potential privacy leakage problems in the early stages of system development.

关键词： Privacy Algebra Semantics Data protection Software quality Systems modeling Data transfer Software reliability Protection Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Knowledge Distillation for Improved Event Extraction in QA Models

Leveraging Knowledge Distillation for Improved Event Extract...

引用

Frontiers technology of information and computer (ICFTIC), IEEE International Conference on

作者： Peiyao Zhou Zhikui Hu Kangli Zi Dawei Zhang School of Computer Science Jiangsu University of Science and Technology Zhenjiang China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Event extraction is an important task in natural language processing, and it is widely utilized in intelligence domains such as business and military for information extraction. Recently, many works have successfully transformed document-level event extraction into Question-answering (QA) tasks with remarkable results. This approach embeds event argument information within the questions, introducing prior knowledge into the process. Jin et al. highlighted the importance of high-quality QA pairs for practical QA tasks, emphasizing that constructing these pairs remains a key challenge[1]. In this study, we propose a Prompt-based question generation method to automatically generate questions containing event arguments, which converts event extraction into a QA task. We introduce an event ontology-based information retrieval module to enhance answer accuracy and select the most relevant document segments as input text. Additionally, we employ knowledge distillation to build the QA model, transferring knowledge from a large pre-trained model to a more compact and efficient one, improving the student model's performance. Experiments show that our model performs strongly in mainstream benchmarks, with 4.8 improvements on WikiEvents.

关键词： Accuracy Benchmark testing information retrieval Question generation Question answering (information retrieval) Data mining Business

来源：评论

学校读者我要写书评

暂无评论

An Efficient Image Encryption Scheme Based on Variable Row-Columns Scrambling and Selective Block Diffusion 14

An Efficient Image Encryption Scheme Based on Variable Row-C...

引用

14th International Conference on Digital Image processing, ICDIP 2022

作者： Huang, Weiye Lyu, Xin Zhang, Chao Li, Xin Su, Yifei Zeng, Tao Wang, Xinyuan Xu, Zhennan Huang, Yucong College of Computer and Information Hohai University Jiangsu Province Nanjing211100 China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Jiangsu Province Nanjing211100 China Information Center Ministry of Water Resources Beijing100053 China

ISBN: (纸本)9781510657564

With the continuous development of multimedia technology and shooting hardware, more and more high-quality images appear in life and production. At present, there are many image encryption methods to ensure image security, but most of them cannot meet the real-time requirements of large-size image encryption, which causes great obstacles to the application and popularization of image encryption. In this paper, an efficient image encryption method based on variable row-columns scrambling and dynamic threshold selective block diffusion is designed. The pixels are operated in batches row by column and block, and the length of chaotic sequence required is reduced without reducing the security, thus reducing the time consuming of the encryption system. In addition, the modified five-point sampling is adopted to select chaotic sequence, which improves the utilization rate of chaotic sequence and further improves the encryption efficiency. Experimental results show that the proposed method has a higher encryption efficiency than the existing methods with similar security, and has strong practicability. © 2022 SPIE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space

arXiv

引用

arXiv 2025年

作者： Liang, Yuheng Liu, Feng Liu, Mingzhou Yao, Yu Wang, Zheyu Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology China Nanjing University of Science and Technology ZiJin College School of Computer and Artificial Intelligence China

Continuous Emotion Recognition (CER) plays a crucial role in intelligent human-computer interaction, mental health monitoring, and autonomous driving. Emotion modeling based on the Valence-Arousal (VA) space enables a more nuanced representation of emotional states. However, existing methods still face challenges in handling long-term dependencies and capturing complex temporal dynamics. To address these issues, this paper proposes a novel emotion recognition model, Mamba-VA, which leverages the Mamba architecture to efficiently model sequential emotional variations in video frames. First, the model employs a Masked Autoencoder (MAE) to extract deep visual features from video frames, enhancing the robustness of temporal information. Then, a Temporal Convolutional Network (TCN) is utilized for temporal modeling to capture local temporal dependencies. Subsequently, Mamba is applied for long-sequence modeling, enabling the learning of global emotional trends. Finally, a fully connected (FC) layer performs regression analysis to predict continuous valence and arousal values. Experimental results on the Valence-Arousal (VA) Estimation task of the 8th competition on Affective Behavior Analysis in-the-wild (ABAW) demonstrate that the proposed model achieves valence and arousal scores of 0.5362 (0.5036) and 0.4310 (0.4119) on the validation (test) set, respectively, outperforming the baseline. The source code is available on GitHub: https://***/FreedomPuppy77/Charon. Copyright © 2025, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Jiangsu Nanjing210094 China JD Explore Academy Beijing100000 China Anhui University School of Computer Science and Technology Anhui Heifei230601 China Yunnan University FIST LAB School of Information Science and Engineering Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this article, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice"in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also provide a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the potential of extending our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. © 1999-2012 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Improved Res2Net Based on Multi-scale Attention Mechanism for Breast Cancer Image Classification 12th

Improved Res2Net Based on Multi-scale Attention Mechanism fo...

引用

12th International Conference on computer Engineering and Networks, CENet 2022

作者： Lei, Suqin Deng, Xing Shao, Haijian Xia, Wang Department of Computer Jiangsu University of Science and Technology Jiangsu Zhenjiang212003 China College of Automation Key Laboratory of Ministry of Education of Complex Engineering System Measurement and Control Southeast University Jiangsu Nanjing210009 China School of Information Science and Technology Nantong University Nantong Jiangsu226019 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

ISBN: (纸本)9789811969003

Breast cancer is one of the most common cancers among female diseases. Since the classification accuracy of pathological images is crucial to the diagnosis of breast cancer, in order to reduce the error of manual diagnosis and improve the automatic classification accuracy of pathological images, this paper proposes a high-accuracy breast cancer classification method based on multi-scale attention mechanism enhanced Res2Net. By constructing a multi-channel residual connection in the residual block, and introducing a convolutional attention mechanism to enhance the feature extraction ability of Res2Net, and using group convolution to replace part of the ordinary convolution. In addition, since the channel information interaction across groups cannot be realized in the group convolution, which reduces the feature extraction ability. In this paper, the channel shuffling operation is used to reorganize the feature maps after the group convolution to achieve the information interaction between different groups. The evaluation results on the BreaKHis dataset show that, the accuracy and precision of the method in this paper have reached 98.5% and 98.9% respectively, in binary classification of histopathological images compared with the benchmark method, and the advantages of recall rate and F1 value are also more obvious. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image 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：