检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Đurašinović, Srećko Azzi, Perla Lasserre, Jean-Bernard Magron, Victor Mula, Olga Zhao, Jun CNRS@CREATE LTD Singapore College of Computing and Data Science Nanyang Technological University Singapore LAAS-CNRS France Toulouse School of Economics France Institute of Mathematics from Toulouse France Eindhoven University of Technology Department of Mathematics and Computer Science Netherlands

The classical Moment-Sum Of Squares hierarchy allows to approximate a global minimum of a polynomial optimization problem through semidefinite relaxations of increasing size. However, for many optimization instances, solving higher order relaxations becomes impractical or even impossible due to the substantial computational demands they impose. To address this, existing methods often exploit intrinsic problem properties, such as symmetries or sparsity. Here, we present a complementary approach, which enhances the accuracy of computationally more efficient low-order relaxations by leveraging Christoffel-Darboux kernels. Such strengthened relaxations often yield significantly improved bounds or even facilitate minimizer extraction. We illustrate the efficiency of our approach on several classes of important quadratically constrained quadratic programs. Copyright © 2025, The Authors. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation

arXiv

引用

arXiv 2022年

作者： Singhania, Dipika Rahaman, Rahul Yao, Angela School of Computing National Univeristy of Singapore Singapore Department of Statistics and Data Science National University of Singapore Singapore

Temporal action segmentation tags action labels for every frame in an input untrimmed video containing multiple actions in a sequence. For the task of temporal action segmentation, we propose an encoder-decoder style architecture named C2F-TCN featuring a "coarse-to-fine" ensemble of decoder outputs. The C2F-TCN framework is enhanced with a novel model agnostic temporal feature augmentation strategy formed by the computationally inexpensive strategy of the stochastic max-pooling of segments. It produces more accurate and well-calibrated supervised results on three benchmark action segmentation datasets. We show that the architecture is flexible for both supervised and representation learning. In line with this, we present a novel unsupervised way to learn frame-wise representation from C2F-TCN. Our unsupervised learning approach hinges on the clustering capabilities of the input features and the formation of multi-resolution features from the decoder’s implicit structure. Further, we provide first semi-supervised temporal action segmentation results by merging representation learning with conventional supervised learning. Our semi-supervised learning scheme, called "Iterative-Contrastive-Classify (ICC)", progressively improves in performance with more labeled data. The ICC semi-supervised learning in C2F-TCN, with 40% labeled videos, performs similar to fully supervised counterparts. © 2022, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Virtual Palette: An Efficient Object Tracking Tool

Virtual Palette: An Efficient Object Tracking Tool

引用

Sustainable computing and Smart Systems (ICSCSS), International Conference on

作者： R. Madhura S. Nikkath Bushra Devi P. P Sasigresa P Department of Computing Technologies SRM Institute of Science and Technology Kattangulathur Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering (Data Science) Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

Virtual Palette is a cutting-edge tool designed to enhance audience participation by providing an alternative to conventional jamboards for educators. Leveraging object tracking, a fundamental component of computer vision, it facilitates seamless and intuitive interactions with the audience. The video analysis process comprises three primary steps: object detection, object tracking across frames, and object behavior analysis. This sophisticated approach necessitates meticulous consideration of elements such as accurate object representation, feature selection for tracking, object recognition, and object tracking. One of the primary advantages of Virtual Palette over traditional mouse or touchpad devices is its ability to support clear and legible drawing and effective interaction in virtual environments. This feature is particularly beneficial for individuals with hearing impairments, aiding in the identification of patterns and drawings. The development of Virtual Palette involves overcoming challenges such as precise three-dimensional finger movement tracking and optimizing the technology for virtual backgrounds. Overall, Virtual Palette offers a dynamic and interactive teaching experience, akin to the advantages provided by screen recording for creating tutorials and virtual documentation.

关键词： Fingers Virtual environments Tutorials Transforms Object detection Green computing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MOAC: Multi-Objective Adaptive Clustering Optimization Algorithm Based on Cluster Adaptation

MOAC: Multi-Objective Adaptive Clustering Optimization Algor...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hossam M. J. Mustafa Dheeb Albashish Ahmad Khasawneh Department of Data Science and Artificial Intelligence Faculty of Information Technology University of Petra Amman Jordan Computer Science Department Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Salt Jordan School of Computing Skyline University College Sharjah UAE

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This paper presents a novel Multi-Objective Adaptive Clustering (MOAC) algorithm that addresses current limitations in existing multi-objective optimization methods. While current algorithms often struggle with premature convergence and diversity preservation, the MOAC algorithm proposes a novel clustering-based approach to search space by partitioning. The algorithm combines cluster evolution with an adaptive parameter control mechanism to achieve significant improvements in balancing exploration-exploitation and diversity maintenance. MOAC employs k-means clustering for population partitioning, combined with cluster-based genetic operators, and an efficient diversity preservation scheme. Extensive experiments across different ZDT, MMF, and UF test suites demonstrate that MOAC's performance is superior, which achieves outstanding hypervolume and IGD values in complex multi-modal problems. The algorithm shows strength in handling complex Pareto fronts, and comprehensive statistical analysis through the Friedman rankings test with a 2.21 rank. Moreover. The results reveal that MOAC is a robust approach for complex multi-objective optimization problems, particularly maintaining solution diversity and achieving consistent convergence across different problems.

关键词： Ranking (statistics) Statistical analysis Metaheuristics Clustering algorithms Optimization methods Evolutionary computation Partitioning algorithms Maintenance Convergence Genetic operators

来源：评论

学校读者我要写书评

暂无评论

RVPD: An Automated System for Calculating the Tortuosity and Bifurcation Angles of Retinal Vessels to Predict Diseases 22

RVPD: An Automated System for Calculating the Tortuosity and...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Yang, Guangzhengao Luo, Xingyu Zhao, Jie Fan, Fangfang Li, Haoshen Dong, Bin Zhang, Li Zhang, Yan Center for Data Science Peking University China Peking University First Hospital Department of Cardiology China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Peking University Changsha Institute for Computing and Digital Economy China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China National Biomedical Imaging Center Peking University China

ISBN: (纸本)9798331520526

Hypertension and diabetes are known to potentially cause morphological changes in the retinal capillary system, yet quantifying these changes presents significant challenges. This research addresses this issue by designing and developing an automated system capable of analyzing retinal images to detect and measure these changes. Our system automatically segments vessels and the optic disc, calculates tortuosity and bifurcation angles, and performs disease prediction based on these measurements along with clinical features. For tortuosity calculation, we adopted a novel curve fitting method, which provides more stable convergence compared to traditional discrete numerical methods. The system integrates clinical data and conducts prediction experiments on hypertensive and diabetic patients with varying sample sizes. Our results demonstrate the system's strong performance and scalability: in the hypertension group, the AUC reached a maximum of 0.814 ± 0.023, with an ACC of 0.735 ± 0.033, while in the diabetes group, the AUC reached a maximum of 0.710 ± 0.043, with an ACC of 0.641 ± 0.052. These findings suggest that our automated system could serve as a valuable tool for early detection and risk assessment of hypertension and diabetes, potentially improving patient outcomes through timely intervention. © 2025 IEEE.

关键词： Bifurcation (mathematics)

来源：评论

学校读者我要写书评

暂无评论

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Pan, Jiazhen Liu, Che Wu, Junde Liu, Fenglin Zhu, Jiayuan Li, Hongwei Bran Chen, Chen Ouyang, Cheng Rueckert, Daniel TUM University Hospital Germany Department of Engineering Science University of Oxford United Kingdom Data Science Institute Imperial College London United Kingdom Massachusetts General Hospital Harvard Medical School United States School of Computer Science University of Sheffield United Kingdom Department of Computing Imperial College London United Kingdom

Reasoning is a critical frontier for advancing medical image analysis, where transparency and trustworthiness play a central role in both clinician trust and regulatory approval. Although Medical Visual Language Models (VLMs) show promise for radiological tasks, most existing VLMs merely produce final answers without revealing the underlying reasoning. To address this gap, we introduce MedVLM-R1, a medical VLM that explicitly generates natural language reasoning to enhance transparency and trustworthiness. Instead of relying on supervised fine-tuning (SFT), which often suffers from overfitting to training distributions and fails to foster genuine reasoning, MedVLM-R1 employs a reinforcement learning framework that incentivizes the model to discover human-interpretable reasoning paths without using any reasoning references. Despite limited training data (600 visual question answering samples) and model parameters (2B), MedVLM-R1 boosts accuracy from 55.11% to 78.22% across MRI, CT, and X-ray benchmarks, outperforming larger models trained on over a million samples. It also demonstrates robust domain generalization under out-of-distribution tasks. By unifying medical image analysis with explicit reasoning, MedVLM-R1 marks a pivotal step toward trustworthy and interpretable AI in clinical practice. Inference model is available at: https://***/JZPeterPan/ MedVLM-R1. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

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

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

A New Federated Learning Framework Against Gradient Inversion Attacks 39

A New Federated Learning Framework Against Gradient Inversio...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Pengxin Zeng, Shuang Chen, Wenhao Zhang, Xiaodan Ren, Weihong Zhou, Yuyin Qu, Liangqiong School of Computing and Data Science The University of Hong Kong Hong Kong Department of Mathematics The University of Hong Kong Hong Kong College of Computer Science Beijing University of Technology China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering UC Santa Cruz United States

ISBN: (纸本)157735897X

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively "breaks the direct connection" between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Batch Verification and Privacy-Preserving data Aggregation Scheme in V2G Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Congcong Wang, Chen Shen, Jian Vasilakos, Athanasios V. Wang, Bin Wang, Weizheng Department of Software Engineering Nanjing University of Information Science and Technology Nanjing210044 China the Zhejiang Key Laboratory of Digital Fashion and Data Governance the Zhejiang Provincial International Cooperation Base for Science and Technology on Cloud Computing Security and Data Aggregation Zhejiang Sci-Tech University Hangzhou310018 China Zhejiang Provincial Innovation Center of Advanced Textile Technology Shaoxing312000 China College of Computer Science and Information Technology IAU Saudi Arabia Grimstad4879 Norway Network and Data Security Hangzhou310053 China Computer Science Department City University of Hong Kong Hong Kong the Division of Computer Science University of Aizu Fukushima965–8580 Japan

In recent years, against the backdrop of smart grids, vehicle-to-grid (V2G) interaction has become a hot topic. With the increasing number of new energy vehicles, handling massive amounts of electricity transaction data has become an urgent problem in need of resolution. Ensuring the security of the vast quantities of electricity transaction data has emerged as a significant challenge. Therefore, two data aggregation schemes are proposed in this paper, both supporting batch verification and privacy protection in centralized and distributed scenarios, respectively. Firstly, an improved Paillier cryptosystem is utilized to achieve lightweight encryption in the proposed schemes. In addition, a novel distributed data aggregation structure that combines a large number of geographically distributed fog nodes with centralized cloud servers is introduced. This structure not only meets the requirements of lightweight encryption and resistance against single point failures but also reduces the communication complexity of distributed data aggregation to O(n). According to the security proofs and experimental analysis, it can be demonstrated that both proposed schemes are effective and secure, meeting the lightweight requirements of modern smart grid systems. © 2025 IEEE. All rights reserved,

关键词： data aggregation

来源：评论

学校读者我要写书评

暂无评论

Identification of Landslides From Remote Sensing Satellite Imagery Using YOLOv7

Identification of Landslides From Remote Sensing Satellite I...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： R Prasanna Kumar G Bharathi Mohan Rohith N D Mukesh K Harish B Yamani Kakarla Department of Computer Science – Artificial Intelligence Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Business Data Scientist Kinaxis Halifax Nova Scotia Canada

One of the most catastrophic natural catastrophes is landslides since they typically follow other major disasters, further harming already damaged systems. In order to mitigate the impact of landslides, it is crucial to be able to quickly and accurately identify potential landslide locations. One way to achieve this is by using high-spatial-resolution remote-sensing image technology, which allows emergency rescue teams to quickly scan large areas and identify potential landslide locations. This research focuses on landslide detection from high-resolution optical satellite images using the YOLOv7, a single-stage object detection algorithm which is known for its fast and accurate object detection capabilities. The dataset from Bijie landslide is utilised to train and evaluate the model. In addition, an Efficient Channel Attention (ECA) module is introduced in YOLOv7, which increases the model’s capacity to focus on relevant features in the image. The findings demonstrate that the attention mechanism improved YOLOv7 performed better than other state-of-the-art models with an F1-score of 96.7% and a mAP score of 97.3%.

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：