检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Jiawei Yu College of Computer Science National University of Defense Technology Changsha China State Key Laboratory of Complex & Critical Software Environment Changsha China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

In clinical practice, the cervical structure plays a critical role in predicting preterm birth, thus making accurate segmentation of this structure in ultrasound images of paramount importance. However, the performance of existing deep learning methods is limited by the high cost of labeling ultrasound images. In this context, semi-supervised medical image segmentation techniques have emerged as promising solutions, particularly recent teacher-student frameworks that have demonstrated notable efficacy. Despite their success, these methods are often subject to confirmation bias, which undermines their reliability. To address this issue, we introduce a novel approach, Alternate Diverse Teaching (AD-MT), for the semi-supervised segmentation of cervical ultrasound images. AD-MT enhances model performance by alternately updating two teacher models, offering diverse perspectives during learning. Furthermore, a conftict-combating module is incorporated to ensure that the model learns from the discrepancies between teacher predictions. This methodology effectively harnesses both labeled and unlabeled data for segmentation tasks. Experimental results demonstrate that AD-MT achieves competitive segmentation performance, as evidenced by its strong showing in the ISBI 2025 Fetal Ultrasound Grand Challenge.

关键词： Training Deep learning Image segmentation Ultrasonic imaging Biological system modeling Semisupervised learning Predictive models Reliability Labeling Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Meta Computing-Driven Optimization of AoI in Industrial IoT: A Hybrid Scheme with Self-Organizing Maps and Reinforcement Learning

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Min Wang, Yike Wang, Nuanlai Pang, Shanchen Sun, Xiaobing Li, Ming Yangzhou University School of Information Engineering Yangzhou225127 China College of Computer Science and Technology Qingdao China College of Computer Science and Technology China State Key Laboratory of Chemical Safety Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software China Shandong Inspur Database Technology Co. Ltd Jinan250101 China

In the domain of Industrial Internet of Things (IIoT) applications, methodologies such as meta computing are essential for ensuring timely and efficient data acquisition within intricate environments characterized by multiple edge devices and isolated sensor networks. The Age of Information (AoI), a key metric for evaluating data timeliness and relevance, has emerged as a focal point for improving decision-making and system responsiveness. However, managing these systems in resourcelimited edge environments is challenging, as traditional methods struggle to link sink node selection with data collection path planning, leading to inefficiency and poor AoI performance. This paper develops a collaborative optimization framework based on meta computing, which dynamically coordinates distributed computational resources as a unified virtual system. It combines self-organizing mapping (SOM) with reinforcement learning (RL) to optimize sink node selection and data collection paths using AoI metrics. Experimental results show the method significantly reduces AoI, improves data freshness, and optimizes energy use, highlighting meta computing's potential for scalable, efficient IIoT solutions. © 2014 IEEE.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

DAISY: Dual-Granularity Contrastive Learning for Disease Similarity Prediction

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 757-768页

作者： Zihao Gao Huifang Ma Yike Wang Zhixin Li Liang Chang College of Computer Science and Engineering Northwest Normal University Lanzhou China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

The quantification of similarities among human diseases is crucial for enhancing our understanding of disease biology, which can aid in improving disease diagnosis, prognosis and treatment, and drug development. Recently, efforts have been devoted to quantifying disease similarity by integrating multi-view data sources from disparate biological data. However, disease data are often sparse due to their rarity or privacy, leading to suboptimal representation of disease when biological entity relationships and labeled disease data are not adequately modeled. To address this challenge, we propose DAISY (Dual-grAnularity contrastIve learning for diSease similaritY prediction), an effective deep learning model for disease representation modeling. DAISY leverages a novel dual-granularity contrastive learning mechanism to enhance the representation of diverse biological entities. Its ability to enable the collaborative supervision of diseases represented by both homogeneous and heterogeneous information is of great significance, leading to a high level of disease representation learning. Besides, this contrastive learning mechanism combines two independent and complementary components: a hierarchical biological entity relationship-aware module to capture disease features on other biological entities, and a disease association capturing module based on signed random walk with precious disease data. Experimental results demonstrate that DAISY achieves outstanding performance on the disease similarity prediction problem.

关键词： Diseases Biological information theory Contrastive learning Biological system modeling Biology Semantics Ontologies Bioinformatics Data models Biomedical measurement

来源：评论

学校读者我要写书评

暂无评论

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

A self-supervised graph convolutional model for recommendation with exponential moving average

引用

Neural Computing and Applications 2025年第9期37卷 6777-6793页

作者： Chen, Rui Pang, Kangning Wang, Zonglin Liu, Qingfang Tang, Cundong Chang, Yanshuo Huang, Min College of Software Engineering Zhengzhou University of Light Industry Zhengzhou450001 China Henan Joint International Research Laboratory of Computer Animation Implementation Technologies Zhengzhou450001 China Information Center Shijiazhuang Posts and Telecommunications Technical College Shijiazhuang050021 China School of Information Science and Technology Northwest University Xi’an710127 United States Insititute for Silk Road Research Xi’an University of Finance and Economics Xi’an710100 China

Recommendation algorithms based on graph convolutional networks can integrate user and item node information along with their interaction topology, better capturing the intricate relationships between users and items, thereby enhancing the accuracy of recommender systems. However, existing methods often overlook the impact of noise in user behavior data on recommendation performance. Additionally, when there are too many convolutional layers in the graph, the node representations tend to smoothing, resulting in an inability to accurately distinguish user preferences. To address these issues, we propose a self-supervised graph convolutional model for recommendation with exponential moving average (SGCERec). Specifically, we first employ exponential moving average (EMA) techniques from the field of time-series analysis to denoise the raw user interaction data. Then, by applying layer filtering technique to update the propagation of information and the representation of nodes within the graph convolutional network, we effectively deepen the model hierarchy, enabling the model to gain a deeper understanding of the features and structures of the graph data, thereby improving the performance and effectiveness of the recommender systems. Finally, experimental results on three real datasets show that SGCERec outperforms state-of-the-art recommendation methods across various common evaluation metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Recommender systems

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 Fuzzy C-Means Clustering Algorithm for Real Medical Image Segmentation

A Fuzzy C-Means Clustering Algorithm for Real Medical Image ...

引用

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

作者： Feifei Zhang Fei Shi Dayong Ren Yue Li School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the field of medical image processing, the presence of noise can often result in the obfuscation of crucial details, which in turn can have a detrimental impact on the accuracy of clinical diagnoses. In order to effectively remove noise and improve segmentation performance, this paper proposes a refined Fuzzy C-Means (FCM) algorithm, designated as MKL-FCM. The method commences with Poisson denoising, which enables more effective handling of the noise characteristics inherent to medical images. Subsequently, multi-scale Kullback-Leibler divergence is utilised to analyse local image information across varying scales, facilitating the differentiation between tissues and pathological regions. Furthermore, tight wavelet frames are capable of capturing fine image details, while reverse optimisation of the objective function serves to correct errors in feature reconstruction, thereby enhancing the accuracy of the segmentation process. The experimental results demonstrate that MKL-FCM enhances both image clarity and segmentation accuracy, and outperforms existing methods in terms of efficiency.

关键词： Image segmentation Accuracy Noise reduction Noise Signal processing algorithms Clustering algorithms Linear programming Partitioning algorithms Speech processing Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Visual Acuity Consistent Foveated Rendering towards Retinal Resolution

arXiv

引用

arXiv 2025年

作者： Zhang, Zhi Gai, Meng Li, Sheng School of Software and Microelectronics Peking University China School of Computer Science Peking University China National Key Laboratory of Intelligent Parallel Technology China

Prior foveated rendering methods often suffer from a limitation where the shading load escalates with increasing display resolution, leading to decreased efficiency, particularly when dealing with retinal-level resolutions. To tackle this challenge, we begin with the essence of the human visual system (HVS) perception and present visual acuity-consistent foveated rendering (VaFR), aiming to achieve exceptional rendering performance at retinal-level resolutions. Specifically, we propose a method with a novel log-polar mapping function derived from the human visual acuity model, which accommodates the natural bandwidth of the visual system. This mapping function and its associated shading rate guarantee a consistent output of rendering information, regardless of variations in the display resolution of the VR HMD. Consequently, our VaFR outperforms alternative methods, improving rendering speed while preserving perceptual visual quality, particularly when operating at retinal resolutions. We validate our approach using both the rasterization and ray-casting rendering pipelines. We also validate our approach using different binocular rendering strategies for HMD devices. In diverse testing scenarios, our approach delivers better perceptual visual quality than prior foveated rendering while achieving an impressive speedup of 6.5×-9.29× for deferred rendering of 3D scenarios and an even more powerful speedup of 10.4×-16.4× for ray-casting at retinal resolution. Additionally, our approach significantly enhances the rendering performance of binocular 8K path tracing, achieving smooth frame rates. Copyright © 2025, The Authors. All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Towards an Inclusive Mobile Web: A Dataset and Framework for Focusability in UI Accessibility 34

Towards an Inclusive Mobile Web: A Dataset and Framework for...

引用

34th ACM Web Conference, WWW 2025

作者： Gu, Ming Pei, Lei Zhou, Sheng Shen, Ming Wu, Yuxuan Gao, Zirui Wang, Ziwei Shan, Shuo Jiang, Wei Li, Yong Bu, Jiajun College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou China School of Software Technology Zhejiang University Zhejiang Ningbo China Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems Zhejiang University Zhejiang Hangzhou China Ant Group Zhejiang Hangzhou China

ISBN: (纸本)9798400712746

The rapid growth of mobile web technologies has revolutionized how people manage daily activities, emphasizing the critical need for accessible mobile user interfaces (UIs) that accommodate users with disabilities and situational impairments. Current AI-driven UI understanding methods show promise but primarily target general UI modeling, neglecting nuanced, user-centric accessibility requirements. To bridge this gap, we first conducted a formative study with 12 visually impaired participants. Our study uncovers selective-accessible issues, a new class of accessibility challenges requiring finer granularity and selective focus on UI components, which existing methods largely overlook. Our findings also reveal that the severity of issues varies across interaction stages, with earlier stages posing a more significant impact. Building on these insights, we propose a comprehensive framework of three accessibility stages: focusability, information, and functionality (FIF), encompassing 12 sub-tasks under 3 overarching tasks. Identifying UI element focusability prediction (UFP) as a pivotal yet underexplored task within FIF, hindered by the absence of dedicated datasets, we introduce a new dataset (NOS) with 117,480 annotated components addressing accessibility issues comprehensively. To further enhance UFP, we introduce Graph-based UI Focusability Prediction (GIFT), a method leveraging graph neural networks to model UFP-targeted UI relationships. User studies validate the dataset’s quality, while experiments show GIFT’s effectiveness in improving UFP outcomes. © 2025 Copyright held by the owner/author(s).

关键词： Mobile Web UI Accessibility Web Accessibility Web Inclusivity

来源：评论

学校读者我要写书评

暂无评论

Adversarial Benchmarking of Segment Anything Model on Loss Functions and Multi-Scale Objectives

SSRN

引用

SSRN 2025年

作者： Lv, Huanhuan Jiang, Songru Wan, Tuohang Bai, Yuhao Gou, Chang Chen, Lijun State Key Laboratory for Novel Software Technology Nanjing University Nanjing210036 China School of Computer Science Nanjing University Nanjing210036 China

Segment Anything Model (SAM) and its variants are vulnerable to adversarial examples, which appear benign to humans but can cause the model to make severe mispredictions. This poses critical challenges for their deployment in security-sensitive domains, such as autonomous driving. Existing adversarial benchmarks for SAM and its variants are not comprehensive enough, especially lacking ablations on the loss functions used in adversarial attacks, and analysis on multi-scale objectives. In this paper, we investigate the impact of loss functions employed in adversarial attacks and consideration of various objective scales. First, we benchmark SAM and its variants using 13 loss functions and 3 adversarial attack strategies to evaluate their impact on the mode's robustness. Then, we introduce two novel gradient projection methods, namely tanh and linear, to enhance the efficacy of adversarial attacks. Finally, we examine multi-scale objectives to simulate real-world scenarios, providing insights into SAM's practical applicability. Experiments on the SA-1B dataset demonstrate that the choice of loss functions significantly influences the performance of SAM and its variants. The proposed gradient projection methods further reduce the mIoU and mStep scores. Moreover, the adversarial performance of SAM and its variants exhibits notable differences depending on the multi-scale objectives. Code will be released. © 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

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：