检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiacong Hu Anda Cao Zunlei Feng Shengxuming Zhang Yi Wang Lingxiang Jia Mingli Song College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University College of Computer Science and Technology Zhejiang University School of Software Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security School of Software Technology Zhejiang University College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security

ISBN: (纸本)9798331314385

Mamba, a state-space model with selective mechanisms and hardware-aware architecture, has demonstrated outstanding performance in long sequence modeling tasks, particularly garnering widespread exploration and application in the field of computer vision. While existing works have mixed opinions of its application in visual tasks, the exploration of its internal workings and the optimization of its performance remain urgent and worthy research questions given its status as a novel model. Existing optimizations of the Mamba model, especially when applied in the visual domain, have primarily relied on predefined methods such as improving scanning mechanisms or integrating other architectures, often requiring strong priors and extensive trial and error. In contrast to these approaches, this paper proposes the Vision Mamba Mender, a systematic approach for understanding the workings of Mamba, identifying flaws within, and subsequently optimizing model performance. Specifically, we present methods for predictive correlation analysis of Mamba's hidden states from both internal and external perspectives, along with corresponding definitions of correlation scores, aimed at understanding the workings of Mamba in visual recognition tasks and identifying flaws therein. Additionally, tailored repair methods are proposed for identified external and internal state flaws to eliminate them and optimize model performance. Extensive experiments validate the efficacy of the proposed methods on prevalent Mamba architectures, significantly enhancing Mamba's performance. For more information, please visit https://***/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MM-Tracker: Motion Mamba with Margin Loss for UAV-platform Multiple Object Tracking

arXiv

引用

arXiv 2024年

作者： Yao, Mufeng Peng, Jinlong He, Qingdong Peng, Bo Chen, Hao Chi, Mingmin Liu, Chao Benediktsson, Jon Atli School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China Tencent Youtu Lab China Shanghai Ocean University China University of Iceland Iceland

Multiple object tracking (MOT) from unmanned aerial vehicle (UAV) platforms requires efficient motion modeling. This is because UAV-MOT faces both local object motion and global camera motion. Motion blur also increases the difficulty of detecting large moving objects. Previous UAV motion modeling approaches either focus only on local motion or ignore motion blurring effects, thus limiting their tracking performance and speed. To address these issues, we propose the Motion Mamba Module, which explores both local and global motion features through cross-correlation and bi-directional Mamba Modules for better motion modeling. To address the detection difficulties caused by motion blur, we also design motion margin loss to effectively improve the detection accuracy of motion blurred objects. Based on the Motion Mamba module and motion margin loss, our proposed MM-Tracker surpasses the state-of-the-art in two widely open-source UAV-MOT datasets. Code is available at: https://***/YaoMufeng/MMTracker Copyright © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

PointSFDA: Source-free Domain Adaptation for Point Cloud Completion

arXiv

引用

arXiv 2025年

作者： He, Xing Zhu, Zhe Nan, Liangling Chen, Honghua Qin, Jing Wei, Mingqiang School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Urban Data Science Section Delft University of Technology Delft Netherlands School of Nursing The Hong Kong Polytechnic University Hong Kong

Conventional methods for point cloud completion, typically trained on synthetic datasets, face significant challenges when applied to out-of-distribution real-world scans. In this paper, we propose an effective yet simple source-free domain adaptation framework for point cloud completion, termed PointSFDA. Unlike unsupervised domain adaptation that reduces the domain gap by directly leveraging labeled source data, PointSFDA uses only a pretrained source model and unlabeled target data for adaptation, avoiding the need for inaccessible source data in practical scenarios. Being the first source-free domain adaptation architecture for point cloud completion, our method offers two core contributions. First, we introduce a coarse-to-fine distillation solution to explicitly transfer the global geometry knowledge learned from the source dataset. Second, as noise may be introduced due to domain gaps, we propose a self-supervised partial-mask consistency training strategy to learn local geometry information in the target domain. Extensive experiments have validated that our method significantly improves the performance of state-of-the-art networks in cross-domain shape completion. Our code is available at https://***/Starak-x/PointSFDA. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FreqBlender: enhancing DeepFake detection by blending frequency knowledge 24

FreqBlender: enhancing DeepFake detection by blending freque...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hanzhe Li Jiaran Zhou Yuezun Li Baoyuan Wu Bin Li Junyu Dong School of Computer Science and Technology Ocean University of China School of Data Science The Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (纸本)9798331314385

Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces FreqBlender, a new method that can generate pseudo-fake faces by blending frequency knowledge. Concretely, we investigate the major frequency components and propose a Frequency Parsing Network to adaptively partition frequency components related to forgery traces. Then we blend this frequency knowledge from fake faces into real faces to generate pseudo-fake faces. Since there is no ground truth for frequency components, we describe a dedicated training strategy by leveraging the inner correlations among different frequency knowledge to instruct the learning process. Experimental results demonstrate the effectiveness of our method in enhancing DeepFake detection, making it a potential plug-and-play strategy for other methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

R2V-PPI: Enhancing Prediction of Protein-Protein Interactions Using Word2Vec Embeddings and Deep Neural Networks

R2V-PPI: Enhancing Prediction of Protein-Protein Interaction...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： I. R. Oviya Shanmukha Sravya N Kalpana Raja Department of Computer Science Engineering Amrita School Of Computing Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven Connecticut USA

Proteins play a crucial role in living organisms, and understanding protein-protein interactions is vital for comprehending their functions and aiding drug discovery. In recent years, advanced deep learning models have been developed to predict protein-protein interactions from sequences. However, these large-scale approaches often suffer from deficiencies, resulting in both false positive and false negative predictions. Traditional encoding methods struggle to effectively represent the semantic meaning of individual residues in protein sequences and their impact on neighbouring residues. To overcome these deficiencies, we propose a novel method named R2V-PPI (Residue-to-Vector embeddings based Protein-Protein Interaction Framework) that effectively represents protein sequences and predicts protein-protein interactions. Inspired by Word2Vec, R2V-PPI learns informative representations of individual amino acid residues, capturing the context and relationships between them in raw protein sequences. These representations provide valuable input features for a downstream deep learning model. Our methodology offers a robust and versatile approach for predicting protein-protein interactions, especially when structural information is limited or unavailable. Evaluation on the S. cerevisiae dataset demonstrates that R2V-PPI outperforms existing state-of-the-art machine learning models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When liver disease diagnosis encounters deep learning:Analysis,challenges,and prospects

引用

iLIVER 2023年第1期2卷 73-87页

作者： Yingjie Tian Minghao Liu Yu Sun Saiji Fu School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Research Center on Fictitious Economy and Data Science Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of SciencesBeijing 100190China MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation at UCAS Beijing 100190China Tsinghua University Press Beijing 102611China School of Economics and Management Beijing University of Posts and TelecommunicationsBeijing 100876China

The liver is the second-largest organ in the human body and is essential for digesting food and removing toxic ***,obesity,alcohol use,and other factors can damage the liver and cause liver *** diagnosis of liver disease used to depend on the clinical experience of doctors,which made it subjective,difficult,and *** learning has made breakthroughs in various fields;thus,there is a growing interest in using deep learning methods to solve problems in liver research to assist doctors in diagnosis and *** this paper,we provide an overview of deep learning in liver research using 139 papers from the last 5 *** also show the relationship between data modalities,liver topics,and applications in liver research using Sankey diagrams and summarize the deep learning methods used for each liver topic,in addition to the relations and trends between these ***,we discuss the challenges of and expectations for deep learning in liver research.

关键词： Liver Deep learning data modality Liver topic Application

来源：评论

学校读者我要写书评

暂无评论

Fortifying database Security: Integrating Advanced Honeypot Technology for Resilient SQL Injection Defense

Fortifying Database Security: Integrating Advanced Honeypot ...

引用

Communication, computer sciences and Engineering (IC3SE), International Conference on

作者： Kumaran U Thammisetty Swetha G. S. N. Santhosh Reddy Harini Ala Senthil Murugan Nagarajan B. Umah Department of Computer Science & Engineering Amrita School of Computing Bengaluru India Department of Computer Science & Engineering (Data Science) Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru Karnataka India Department of Mathematics Faculty of Science Technology and Medicine University of Luxembourg Luxembourg Department of Computer Science & Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru Karnataka India

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

The dynamic nature of cyber threats necessitates the development of novel approaches to strengthen database system security. The novel method for fortifying defenses against SQL injection attacks—a pervasive and ongoing danger in the field of cybersecurity—is presented in this study. The suggested methodology creates a strong and adaptable defense mechanism by seamlessly integrating cutting-edge honeypot technology with current SQL injection mitigation techniques. Our approach, which we have named HoneySQLGuard, uses carefully con- structed honeypot tables inside the database system. These tables serve as sly bait, drawing potential attackers’ attention away from genuine data and toward themselves. By utilizing the most recent developments in technology, Honey SQL Guard surpasses the limitations of conventional signature-based detection techniques and is able to adjust to changing attack strategies via anomaly and machine learning. The honeypot tables are cleverly incorporated within the database architecture, making them invisible to an outside observer when compared to real tables. The technology immediately recognizes and isolates unusual behavior suggestive of SQL injection attempts by closely monitoring and analyzing query patterns. Furthermore, HoneySQLGuard has real-time reporting and alerting functions that guarantee an early reaction to any possible intrusions. Extensive testing is conducted to validate the effectiveness of the proposed solution, which shows it can dramatically lower the success rate of SQL injection attacks while keeping false-positive rates low. This study advances the subject by providing a thorough and flexible method for fortifying databases against SQL injection attacks, in line with the industry's increasing demand for robust cybersecurity defenses.

关键词： Protocols Prevention and mitigation Machine learning SQL injection Observers database systems Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Galaxy Morphology Classification with DenseNet 4

Galaxy Morphology Classification with DenseNet

引用

2022 4th International Symposium on Robotics and Intelligent Manufacturing Technology, ISRIMT 2022

作者： Hui, Wuyu Robert Jia, Zheng Li, Hansheng Wang, Zijian School of Electronic and Automation Anhui University Hefei China College of Liberal Arts Computer Science University of Minnesota MN United States Division of Science and Technology Data Science BNU-HKBU United International College Zhuhai China School of Mathematical Sciences Capital Normal University Beijing China

Galaxy classification is crucial in astronomy, as galaxy types reveal information on how the galaxy was formed and evolved. While manually conducting the classification task requires extensive background knowledge and is time-consuming, deep learning algorithms provide a time-efficient and expedient way of accomplishing this task. Hence, this paper utilizes transfer learning from pre-trained CNN models and compares their performances on the Galaxy10 DECals dataset. This paper applies opening operation, data augmentation, class weights, and learning rate decay to further improve the models' performance. In our experiments, DenseNet121 outperforms the other models and achieved approximately 89% test-set accuracy within 30 minutes. The second best-performing model, EfficientNetV2S, takes double the time achieving 2.43% lower test set accuracy. © Published under licence by IOP Publishing Ltd.

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

Predicting Protein-Protein Interactions Using Self-Attention-Based Deep Neural Networks and FastText Embeddings

Predicting Protein-Protein Interactions Using Self-Attention...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： I. R. Oviya N Shanmukha Sravya Kalpana Raja Department of Computer Science Engineering Amrita School Of Computing Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven Connecticut USA

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Predicting Protein-protein interactions are central to understanding the intricate mechanisms governing cellular functions, as proteins seldom act in isolation. While current machine learning and deep learning models focus on encoding protein sequences based on residue composition or physicochemical properties, they often overlook the complex relationships between amino acid segments within lengthy sequences. To address these limitations, we propose a novel hybrid model that combines a self-attention to enhance Deep neural network feature extraction with an with FastText Protein embeddings for predicting PPI. Utilizing transfer learning via the unsupervised FastText embedding technique to derive statistical representations of protein sequences, offers advantages over traditional protein encoding techniques in the context of analysing k-Mer sequences. Our model’s performance is assessed through $\mathbf{5 - f o l d}$ cross-validation on datasets of *** and Human-Bacillus Anthracis protein interactions, resulting in accuracies of $\mathbf{9 2. 2 8 \%}$ and $\mathbf{9 4. 0 8 \%}$, respectively. Compared to existing machine learning models, our model demonstrates superior performance on both datasets.

关键词： Proteins Accuracy Transfer learning Pathogenesis Artificial neural networks Organizations Predictive models Feature extraction Encoding Vectors

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Unconstrained Head Pose Estimation in the Wild

arXiv

引用

arXiv 2024年

作者： Zhou, Huayi Jiang, Fei Yuan, Jin Rui, Yong Lu, Hongtao Jia, Kui School of Data Science The Chinese University of Hong Kong Shenzhen China Academy of Science and Technology China Lenovo Research and Technology China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Existing research on unconstrained in-the-wild head pose estimation suffers from the flaws of its datasets, which consist of either numerous samples by non-realistic synthesis or constrained collection, or small-scale natural images yet with plausible manual annotations. This makes fully-supervised solutions compromised due to the reliance on generous labels. To alleviate it, we propose the first semi-supervised unconstrained head pose estimation method SemiUHPE, which can leverage abundant easily available unlabeled head images. Technically, we choose semi-supervised rotation regression and adapt it to the error-sensitive and label-scarce problem of unconstrained head pose. Our method is based on the observation that the aspect-ratio invariant cropping of wild heads is superior to previous landmark-based affine alignment given that landmarks of unconstrained human heads are usually unavailable, especially for underexplored non-frontal heads. Instead of using a pre-fixed threshold to filter out pseudo labeled heads, we propose dynamic entropy based filtering to adaptively remove unlabeled outliers as training progresses by updating the threshold in multiple stages. We then revisit the design of weak-strong augmentations and improve it by devising two novel head-oriented strong augmentations, termed pose-irrelevant cut-occlusion and pose-altering rotation consistency respectively. Extensive experiments and ablation studies show that SemiUHPE outperforms its counterparts greatly on public benchmarks under both the front-range and full-range settings. Furthermore, our proposed method is also beneficial for solving other closely related problems, including generic object rotation regression and 3D head reconstruction, demonstrating good versatility and extensibility. Code is in https://***/hnuzhy/SemiUHPE. Copyright © 2024, The Authors. All rights reserved.

关键词： Semi-supervised learning

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：