检索结果-内蒙古大学图书馆

4th International Conference on computer Vision, Application, and Algorithm, CVAA 2024

作者： Liu, Xinpei Xiong, Hailing Gao, Mingjie Liu, Wei College of Computer and Information Science Squthwest School of Software Southwest University Chongqing400715 China College of Electronic and Information Engineering Southwest University Chongqing China Business School The Taihu Lake University Chongqing China Silkworm Academy Palace Southwest University Chongqing China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

In the field of object detection, deep learning has been used extensively, especially in algorithms like Yolov7, which have achieved significant accuracy improvements. However, traditional convolutional neural networks are computationally intensive and require powerful GPU support, making its deployment on embedded devices difficult. This presents a problem for researchers as the high device requirements hinder their related research work. Consequently, more people opt to use lightweight networks, such as Yolov7-tiny. However, when using Yolov7-tiny for underwater garbage detection, it has been observed that while achieving good accuracy in mAP (mean Average Precision) at IOU (Intersection over Union) of 0.5, the performance is not satisfactory in the mAP range of 0.5 to 0.95. This limitation may be attributed to the trade-off in network performance during the process of model lightweighting. To address these issues, An enhanced Yolov7-tiny method for the detection of underwater trash objects is proposed in this paper. First, the algorithm employs an enhanced Ghost convolutional feature extraction module, which starts with conventional convolutions using a smaller number of channels, then performs grouped convolutions to obtain partial output maps with features. Finally, the maps with features obtained from the first convolutional step are added to the channels obtained from the second grouped convolution step. This design effectively reduces model complexity while extracting richer feature information. Secondly, the algorithm utilizes the CA (Channel Attention) mechanism to weight channels based on their positional information, thereby efficiently extracting features. The network can concentrate more on important feature regions by learning position weights in the feature maps. Lastly, the algorithm combines the Repeated Weighted Bi-directional Feature Pyramid Network (BIFPN) for feature fusion. BIFPN employs multiple down-sampling steps for short skip connections,

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Ownership Verification for Federated Recommendation

引用

ACM Transactions on Information Systems 2025年第3期43卷 1-27页

作者： Yang, Enyue Pan, Weike Fan, Lixin Gu, Hanlin Li, Zhitao Yang, Qiang Ming, Zhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Department WeBank Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Shenzhen Technology University Shenzhen China Shenzhen China

Most federated learning-based recommender systems allow clients to access a well-trained high-quality model locally, which provides adversaries with the opportunity to infringe the legitimate copyright of the model. In response, we study an emerging and important problem, i.e., copyright protection of a federated recommendation model, which has not yet been addressed in the community of federated learning or recommender systems. We propose the first backdoor-based ownership verification scheme for federated recommendation (OVFR), which enables the server to claim its ownership for a given suspicious recommendation model. First, we propose to generate a trigger set tailored to recommendation scenarios. In particular, we generate some fake users and items, and then construct a set of fake users with fake interaction records as a trigger set. Moreover, we ensure that the distribution of the popularity of the fake items follows a long-tailed distribution for the effectiveness of the incorporated watermarking. To provide robustness assurance, we propose two different hybrid strategies to make the embeddings of the fake items similar to those of the real items. Second, we focus on effectively learning from a trigger set for recommendation scenarios. In particular, we design an MSE loss function and a contrastive loss function for incorporating the backdoor-based watermarking into the item embeddings, since the item embeddings are often more valuable and easier to be accessed than other parameters of a federated recommendation model. We then design a contrastive loss function to reduce the risk of the fake items being detected. Extensive experiments on three public datasets show the effectiveness of our OVFR in terms of ownership verification, model performance, and robustness. © 2025 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Potential of Self-Supervised Monocular Depth Estimation via Patch-Based Self-Distillation

引用

IEEE Internet of Things Journal 2025年第11期12卷 18042-18055页

作者： Yu, Ting Pan, Shan Chen, Wei Tian, Zijian Wang, Zehua Yu, F. Richard Leung, Victor C. M. Postdoctoral Research Station China RongTong Academy of Sciences Group Corporation Limited Beijing100022 China China RongTong Artificial Intelligence Research Center Beijing100022 China China University of Mining and Technology School of Artificial Intelligence Beijing100083 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China School of Artificial Intelligence Beijing100083 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

Perceiving scene depth and 3D structure is one of the key tasks for Internet of Video Things (IoVT) devices to understand and interact with the environment. Self-supervised monocular depth estimation has demonstrated significant potential in leveraging large-scale unlabeled datasets to achieve competitive performance, thereby playing an increasingly important role in depth estimation. Despite recent methods providing additional supervisory signals through self-distillation strategies to improve depth estimation, an effective method for generating pseudo-depth labels suitable for addressing occlusion issues among elements far from the camera remains unexplored. To address this limitation, we propose a Patch-based Self-Distillation Learning Framework to exploit the potential of self-supervised monocular depth estimation in recovering fine-grained scene depth. In the proposed framework, elements far from the camera within the input image are enlarged by enlarging and cropping operations in the patch-based self-distillation branch. Guided by photometric consistency, the model learns the detailed occlusion relationships among elements from the enlarged patches, producing patch depth maps with fine structures. In the main branch, which takes full-scale images as input, patch depth maps serve as pseudo-depth labels through self-distillation loss to provide additional supervisory signals for regions where photometric consistency fails to offer effective supervision. This forces the depth estimation network to recover fine structures of elements far from the camera in full-scale input images. Regarding the architecture of the depth estimation network, we introduce a bin-center prediction. In this prediction, a global aggregator based on self-attention provides additional scene structure queries for adaptive scene depth discretization. Finally, to encourage the model to explore more general cues for depth inference beyond road plane cues, we propose a PatchMix data augmentati

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

MVDC : A Multi-view Dental Completion Model Based on Contrastive Learning

MVDC : A Multi-view Dental Completion Model Based on Contras...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xunyu Yang Qingxin Deng Minghan Huang Landu Jiang Dian Zhang College of Computer Science and Software Engineering Shenzhen University Guangdong China College of Future Technology HKUST(GZ) Guangdong China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Restoring the patient’s occlusal function of broken teeth is a challenging task since tooth texture is very complex, a slight deviation may affect the patient’s chewing function and temporomandibular joint function. Therefore, how to efficiently repair the complete shape and real surface of the crown is a critical problem. Traditional technologies are hard to restore complete shape of the dental crown or lack inlay surface details, due to dataset limitations and complexity of missing parts. In this paper, we propose a multi-view crown restoration framework MVDC based on contrastive learning. Specifically, MVDC contains: 1) a multi-view generator with a specially designed loss measurement by using contrastive learning; 2) a multi-scale discriminator mechanism able to consider relation and consistency between teeth from different scales; 3) an occlusal groove extraction network to extract the occlusal details. We conducted extensive experiments on existing public datasets. The results showcase the superior performance of MVDC.

关键词： Correlation Shape Teeth Contrastive learning Signal processing Maintenance engineering Loss measurement Dentistry Surface texture Speech processing

来源：评论

学校读者我要写书评

暂无评论

Toward Drought Modeling in South Asia: Machine Learning Approaches, Challenges, and Opportunities

引用

IEEE Access 2025年 13卷 87654-87671页

作者： Mana Saleh Al Reshan Muhammad Owais Raza Naeem Ahmed Mahoto Adel Rajab Asadullah Shaikh Mohamed A. Elmagzoub Khairan D. Rajab Department of Information Systems College of Computer Science and Information Systems Najran University Najran Saudi Arabia Emerging Technologies Research Laboratory (ETRL) College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Computer Engineering Istanbul Sabahattin Zaim University İstanbul Türkiye Department of Software Engineering Mehran University of Engineering and Technology Jamshoro Sindh Pakistan Department of Computer Science College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Network and Communication Engineering College of Computer Science and Information Systems Najran University Najran Saudi Arabia

Drought is an environmental and economic problem. Sustainable ecosystems, water resources, food security, and ecosystem sustainability. Machine all are severely affected by drought. Due to the increasing frequency and severity of droughts caused by climate change. Effective drought modeling is crucial for early warning systems and risk mitigation. Recent advances in machine learning (ML) and deep learning (DL) techniques have been developed as potential drought modeling tools, which offer accurate and reliable drought detection. This review paper summarizes the drought modeling(Drought Prediction, Drought Detection and Drought Forecasting) approaches. This paper focuses on three main aspect. 1) The selection of the region for this study, for this study South Asia(SA) is selected as region of interest (ROI) that offer accurate drought modeling, providing policymakers and decision-makers with insightful information. The geographical scope of this study is the region of South Asia. This region is selected because of its heavy reliance on agriculture. 2) This paper focuses on the current and future trends, challenges, and advances of and vulnerability to droughts. The review offers a thorough grasp of how drought conditions are evaluated by gathering and analyzing the most important drought indicators and metrics specific to South Asia. The paper explores the current state-of-the-art in ML and DL for drought modeling. 3) This review encapsulates the indicator and metrics (Complex Machine learning and deep learning models) for drought modeling which are most relevant to the SA region. This study sum up as most common challenges in drought modeling are, highlighting current challenges such as incomplete and inconsistent datasets, lack of explainable and interpretable models, and unavailability of data for model uncertainty analysis. This study proposes that these problems can be solved with modern machine learning techniques such as explainable machine learning and federa

关键词： Droughts Machine learning Asia Deep learning Indexes Water resources Remote sensing Predictive models computer science Climate change Environmental monitoring Economics

来源：评论

学校读者我要写书评

暂无评论

Facial Data Minimization: Shallow Model as Your Privacy Filter

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Pu, Yuwen Chen, Jiahao Pan, Jiayu Yan, Diqun Zhang, Xuhong Ji, Shouling College of Computer Science and Technology at Zhejiang University Zhejiang Hangzhou310027 China College of Software Technology at Zhejiang University Zhejiang NingBo315048 China College of Electrical Engineering and Computer Science at Ningbo University Zhejiang NingBo315211 China

Face recognition service has been widely adopted across various domains, offering significant convenience and enhancing efficiency in numerous applications. However, once a user's facial data is transmitted to a service provider, the user will lose control over his/her biometric data. In recent years, there have been various security and privacy issues due to the leakage of facial data. Although many privacy enhancement methods have been proposed, they usually fail when they are not accessible to adversaries' strategies or the complete face recognition model. Therefore, in this work, we propose a Privacy Minimization Transformation (PMT) method, designed to address two common scenarios in practical face recognition systems: the uploading of facial images and facial features. This method can process the private facial data based on the shallow network of the face recognition model to obtain the obfuscated data. The obfuscated data cannot only maintain satisfactory performance on the authorized models (i.e., the models specified by the user) and restrict the performance on other unauthorized models (i.e., the models not specified by the user) but also prevent privacy data from leaking by AI methods and human visual theft. Additionally, since a service provider may execute preprocessing operations on the received data, we propose an enhanced perturbation method to improve the robustness of PMT. Besides, to authorize one facial image to multiple service models simultaneously, a multiple-restriction mechanism is proposed to improve the scalability of PMT. Finally, we conduct extensive experiments and evaluate the effectiveness of the proposed PMT against face reconstruction, function creep, and face attribute estimation attacks. Experimental results demonstrate that PMT performs well in preventing facial function creep and privacy leakage while maintaining high face recognition accuracy © 2004-2012 IEEE.

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Human–object interaction detector with unsupervised domain adaptation

引用

Knowledge-Based Systems 2025年 321卷

作者： Cheng, Yamin Duan, Zhekai Huang, Hualong Wang, Zhi School of Computer and Software Engineering Xihua University Chengdu China Department of Computer Science University College London United Kingdom School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

Human–object interaction (HOI) detection constitutes a foundational challenge in fine-grained visual scene understanding. While mainstream HOI detection frameworks rely on supervised training of deep neural networks with extensive labeled datasets, such data-intensive paradigms face practical limitations due to the high annotation and costs in real-world applications. To tackle this problem, it is a natural idea to leverage data from a well-labeled domain (source domain) to improve the performance for the domain of interest (target domain). However, the domain shift problem renders it non-trivial to transfer knowledge between different domains. In this paper, we propose a novel Domain-Adaptive HOI Detection Framework that effectively bridges domain gaps and achieves robust performance on unlabeled target domains by leveraging knowledge from labeled source domains. Specifically, our method aims to align features on both the map-level and sequence-level to learn domain-invariant features, and minimize the interaction-aware feature discrepancy by learning prototypical patterns of action relationship. To this end, we introduce a new adversarial training schema that uses a CutMix strategy to minimize the domain shift of map-level feature representations from the feature backbone. We then delve into feature distribution alignment and pursue sequence-level domain-invariant features from the transformer encoder by designing a token-based feature alignment. In addition, we design a memory bank to minimizes the distance between each inter-class interaction feature with homogeneous relationship, and maximizes the discrepancy between inter-class interaction features with heterogenous relationship. Extensive experiments on multiple benchmarks demonstrate that our proposed framework significantly outperforms prior supervised learning methods and achieves the superior performance. © 2025 Elsevier B.V.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification

ViT Enhanced Privacy-Preserving Secure Medical Data Sharing ...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Al Amin Kamrul Hasan Sharif Ullah M. Shamim Hossain Department of Electrical & Computer Engineering College of Engineering Tennessee State University TN USA Department of Computer Science & Engineering College of Science and Engineering University of Central Arkansas Conway AR USA Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

Privacy-preserving and secure data sharing are critical for medical image analysis while maintaining accuracy and minimizing computational overhead are also crucial. Applying existing deep neural networks (DNNs) to encrypted medical data is not always easy and often compromises performance and security. To address these limitations, this research introduces a secure framework consisting of a learnable encryption method based on block-pixel operation to encrypt the data and subsequently integrate it with the Vision Transformer (ViT). The proposed framework ensures data privacy and security by creating unique scrambling patterns per key, providing robust performance against leading bit attacks and minimum difference attacks.

关键词： Data privacy computer vision Image analysis Accuracy Artificial neural networks Transformers Robustness Encryption Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

PASTD: Progressive Augmentation and Spatiotemporal Decoupling Contrastive Learning for Skeleton-Based Action Recognition

PASTD: Progressive Augmentation and Spatiotemporal Decouplin...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qian Huang Weiwen Qian Chang Li Gongyou Xu Zhongqi Chen College of Computer Science and Software Engineering Hohai University Nanjing China Faculty of Science and Technology United International College BNU-HKBU Zhuhai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Contrastive learning has achieved significant progress in the field of self-supervised skeleton-based action recognition. However, existing methods often apply strong augmentations directly to skeleton data, which can distort or even lose the semantic of the skeletons. Additionally, most methods focus on unified feature extraction through spatiotemporal modeling, leading to spatiotemporal entanglement that hinders model’s interpretability and degrades performance. To address these issues, we propose a Progressive Augmentation and SpatioTemporal Decoupling contrastive learning model (PASTD). Specifically, we propose progressive augmentation to enhance the model’s generalization capability, which generates multiple distinct positive sample pairs through multiple branches and uses inter-branch constraints to maintain consistent motion patterns. Moreover, we propose spatiotemporal decoupling module to separate the feature’s spatial and temporal information, using a dual-path self-attention module combined with an intra-branch cross-domain learning strategy to facilitate information exchange between domains. Extensive experiments on the four public datasets NTU-RGB+D (60&120) and PKU-MMD (I&II) demonstrate the effectiveness of these components. Moreover, PASTD outperforms state-of-the-art methods across various evaluation metrics.

关键词： Measurement Three-dimensional displays Semantics Contrastive learning Speech recognition Signal processing Skeleton Spatiotemporal phenomena Speech processing Information exchange

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation as Free Lunch: Exploring the Test-Time Augmentation for Sequential Recommendation

arXiv

引用

arXiv 2025年

作者： Dang, Yizhou Liu, Yuting Yang, Enneng Huang, Minhan Guo, Guibing Zhao, Jianzhe Wang, Xingwei Software College Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

Data augmentation has become a promising method of mitigating data sparsity in sequential recommendation. Existing methods generate new yet effective data during model training to improve performance. However, deploying them requires retraining, architecture modification, or introducing additional learnable parameters. These steps are time-consuming and costly for well-trained models, especially when the model scale becomes large. In this work, we explore the test-time augmentation (TTA) for sequential recommendation, which augments the inputs during the model inference and then aggregates the model’s predictions for augmented data to improve final accuracy. It avoids significant time and cost overhead from the previously mentioned steps. We first experimentally disclose the potential of existing augmentation operators for TTA and find that the Mask and Substitute consistently achieve better performance. Further analysis reveals that these two operators are effective because they retain the original sequential pattern while adding appropriate perturbations. Meanwhile, we argue that these two operators still face time-consuming item selection or interference information from mask tokens. Based on the analysis and limitations, we present TNoise and TMask. The former injects uniform noise into the original representation, avoiding the computational overhead of item selection. The latter blocks mask token from participating in model calculations or directly removes interactions that should have been replaced with mask tokens. Comprehensive experiments demonstrate the effectiveness, efficiency, and generalizability of our method. Our codes is available at https://***/KingGugu/TTA4SR. © 2025, CC BY.

关键词：

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：