检索结果-内蒙古大学图书馆

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

作者： Shihao Gao Xiaoyan Yu Yu Cai Xulong Zhang Jianzong Wang Taisong Jin Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Ping An Technology Co. Ltd. Shenzhen China School of Computer Science and Technology Beijing Institute of Technology China School of Informatics Xiamen University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Heterogeneous Graph Neural Networks (HGNNs) aim to embed rich structural and semantic information of heterogeneous graphs into low-dimensional node representations. While HGNNs extend the foundational work of homogeneous Graph Neural Networks, the methodology for effectively transforming heterogeneous graphs into homogeneous graphs and then learning node representations remains under-explored. In this paper, we propose a novel heterogeneous graph embedding method via the Homogeneous Graph Extraction strategy, termed HGE. Specifically, the proposed method ingeniously harnesses information clusters and metapaths to extract tailored homogeneous graphs from the complex heterogeneous graph. Subsequently, these distilled homogeneous graphs are fed into a weight-shared homogeneous graph encoder to obtain embeddings with diverse semantic information. Finally, we employ an attention mechanism, which adeptly fuses embeddings derived from distinct homogeneous graphs, resulting in the more expressive capability of the nodes. The effectiveness of the proposed architecture was demonstrated through experiments on three real heterogeneous graph datasets.

关键词： Representation learning Attention mechanisms Fuses Semantics Signal processing Graph neural networks Acoustics Data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

Learning to Deblur Polarized Images

引用

International Journal of Computer Vision 2025年 1-16页

作者： Zhou, Chu Teng, Minggui Zhou, Xinyu Xu, Chao Sato, Imari Shi, Boxin National Institute of Informatics Tokyo Japan National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China National Key Laboratory of General AI School of Intelligence Science and Technology Peking University Beijing China

A polarization camera can capture four linear polarized images with different polarizer angles in a single shot, which is useful in polarization-based vision applications since the degree of linear polarization (DoLP) and the angle of linear polarization (AoLP) can be directly computed from the captured polarized images. However, since the on-chip micro-polarizers block part of the light so that the sensor often requires a longer exposure time, the captured polarized images are prone to motion blur caused by camera shakes, leading to noticeable degradation in the computed DoLP and AoLP. Deblurring methods for conventional images often show degraded performance when handling the polarized images since they only focus on deblurring without considering the polarization constraints. In this paper, we propose a polarized image deblurring pipeline to solve the problem in a polarization-aware manner by adopting a divide-and-conquer strategy to explicitly decompose the problem into two less ill-posed sub-problems, and design a two-stage neural network to handle the two sub-problems respectively. Experimental results show that our method achieves state-of-the-art performance on both synthetic and real-world images, and can improve the performance of polarization-based vision applications such as image dehazing and reflection removal.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Decoupled Augmentation

Graph Contrastive Learning with Decoupled Augmentation

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Gao, Shihao Li, Caoshuo Mao, Cunli Zhang, Xulong Qu, Xiaoyang Jin, Taisong Wang, Jianzong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China Ping An Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9798350368741

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph's semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches. © 2025 IEEE.

关键词： Contrastive learning Graph representation Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Mind the Gap: Confidence Discrepancy Can Guide Federated Semi-Supervised Learning Across Pseudo-Mismatch

arXiv

引用

arXiv 2025年

作者： Liu, Yijie Shang, Xinyi Zhang, Yiqun Lu, Yang Gong, Chen Xue, Jing-Hao Wang, Hanzi Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China Department of Statistical Science University College London United Kingdom School of Computer Science and Technology Guangdong University of Technology Guangzhou China Department of Automation Shanghai Jiao Tong University China

Federated Semi-Supervised Learning (FSSL) aims to leverage unlabeled data across clients with limited labeled data to train a global model with strong generalization ability. Most FSSL methods rely on consistency regularization with pseudo-labels, converting predictions from local or global models into hard pseudo-labels as supervisory signals. However, we discover that the quality of pseudo-label is largely deteriorated by data heterogeneity, an intrinsic facet of federated learning. In this paper, we study the problem of FSSL in-depth and show that (1) heterogeneity exacerbates pseudo-label mismatches, further degrading model performance and convergence, and (2) local and global models’ predictive tendencies diverge as heterogeneity increases. Motivated by these findings, we propose a simple and effective method called Semi-supervised Aggregation for Globally-Enhanced Ensemble (SAGE), that can flexibly correct pseudo-labels based on confidence discrepancies. This strategy effectively mitigates performance degradation caused by incorrect pseudo-labels and enhances consensus between local and global models. Experimental results demonstrate that SAGE outperforms existing FSSL methods in both performance and convergence. Our code is available at https://***/Jay-Codeman/SAGE. Copyright © 2025, The Authors. 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

Learning Diffusion High-Quality Priors for Pan-Sharpening: A Two-Stage Approach With Time-Aware Adapter Fine-Tuning

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Wang, Yingying Lin, Yunlong He, Xuanhua Zheng, Hui Yan, Keyu Fan, Linyu Huang, Yue Ding, Xinghao Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen361005 China Institute of Artificial Intelligence Xiamen University Xiamen361102 China Xiamen University School of Informatics Xiamen361102 China University of Science and Technology of China Science Island Branch Graduate School Hefei230026 China Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230031 China

Pan-sharpening aims to enhance the spatial resolution of the low-resolution multispectral (LRMS) image by incorporating high-frequency details from the panchromatic (PAN) image, while maintaining the spectral qualities of the LRMS image. Recent advancements in diffusion models have shown remarkable capabilities in image restoration and generation. However, simply applying diffusion models in pan-sharpening yields suboptimal outcomes in terms of fine-grained details and spectral fidelity. To this end, we introduce TA-DiffHQP, a two-stage approach that integrates the diffusion high-quality priors model (DiffHQP) and the time-aware adapter (TA-Adapter). Initially, we perform self-reconstruction pretraining DiffHQP with a fixed sampling strategy on approximately 24K high-resolution remote sensing datasets to explicitly model the high-quality texture details and spectral fidelity, after which we freeze most of DiffHQP's parameters. In stage two, we integrate time-aware fusion adapters with the DiffHQP, enabling rapid adaptation to the pan-sharpening task. The TA-Adapters prioritize low-frequency main scenes during the early phases of the denoising process and refine high-frequency details in the later phases, achieving cross-modal information fusion from coarse to fine. Extensive experiments conducted on three satellite datasets demonstrate that our approach attains state-of-the-art (SOTA) performance over existing methods, revealing superior fusion outcomes in pan-sharpening. © 2025 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Decoupled Augmentation

Graph Contrastive Learning with Decoupled Augmentation

引用

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

作者： Shihao Gao Caoshuo Li Cunli Mao Xulong Zhang Xiaoyang Qu Taisong Jin Jianzong Wang Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Ping An Technology Co. Ltd. Shenzhen China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph’s semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches.

关键词： Acoustic distortion Semantics Contrastive learning Interference Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery

arXiv

引用

arXiv 2025年

作者： Li, Bo Zhang, Bob Zhang, Chengyang Zhou, Minghao Huang, Weiliang Wang, Shihang Wang, Qing Li, Mengran Zhang, Yong Song, Qianqian PAMI Research Group Department of Computer and Information Science University of Macau Taipa China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida Florida United States Faculty of Applied Sciences Macao Polytechnic University Taipa China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong China Department of Cancer Biology Wake Forest School of Medicine Winston SalemNC United States

In the field of image-based drug discovery, capturing the phenotypic response of cells to various drug treatments and perturbations is a crucial step. This process involves transforming high-throughput cellular images into quantitative representations for downstream analysis. However, existing methods require computationally extensive and complex multi-step procedures, which can introduce inefficiencies, limit generalizability, and increase potential errors. To address these challenges, we present PhenoProfiler, an innovative model designed to efficiently and effectively extract morphological representations, enabling the elucidation of phenotypic changes induced by treatments. PhenoProfiler is designed as an end-to-end tool that processes whole-slide multi-channel images directly into low-dimensional quantitative representations, eliminating the extensive computational steps required by existing methods. It also includes a multi-objective learning module to enhance robustness, accuracy, and generalization in morphological representation learning. PhenoProfiler is rigorously evaluated on large-scale publicly available datasets, including over 230,000 whole-slide multi-channel images in end-to-end scenarios and more than 8.42 million single-cell images in non-end-to-end settings. Across these benchmarks, PhenoProfiler consistently outperforms state-of-the-art methods by up to 20%, demonstrating substantial improvements in both accuracy and robustness. Furthermore, PhenoProfiler uses a tailored phenotype correction strategy to emphasize relative phenotypic changes under treatments, facilitating the detection of biologically meaningful signals. UMAP visualizations of treatment profiles demonstrate PhenoProfiler’s ability to effectively cluster treatments with similar biological annotations, thereby enhancing interpretability. These findings establish PhenoProfiler as a scalable, generalizable, and robust tool for phenotypic learning, offering transformative advancement

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Smart application-aware IoT data collection

引用

Journal of Reliable Intelligent Environments 2019年第1期5卷 17-28页

作者： Siris, Vasilios A. Fotiou, Nikos Mertzianis, Alexandros Polyzos, George C. Mobile Multimedia Laboratory Department of Informatics School of Information Sciences and Technology Athens University of Economics and Business Athens Greece

We present and experimentally evaluate procedures for efficient IoT data collection while achieving target requirements in terms of data accuracy, response time, energy, and privacy protection. Different strategies are considered because different IoT applications can have different requirements. Specifically, the accuracy-driven strategy adjusts the time period between consecutive measurements following an additive increase and multiplicative decrease (AIMD) scheme based on a target data accuracy, while the time-driven strategy adjusts the time period between measurement requests to achieve delay less than a given maximum delay between consecutive measurements. The energy-driven strategy considers both the data accuracy and the energy costs for the corresponding measurements. Finally, the privacy-driven strategy adds noise to measurements using differential privacy techniques. The experimental evaluation involves real temperature, humidity, and ozone (O3) measurements obtained from three testbeds through the FIESTA-IoT platform. Our results show that the AIMD adaptation of the measurement period is robust to different types of measurements from different testbeds, without having any tuning parameters. Also, the experimental results show the trade-offs between the target data accuracy and the number of measurements and between the target data accuracy and the corresponding energy costs. For the privacy-driven strategy, the results show that the addition of noise to the sensor measurements using differential privacy has a negligible effect on the aggregate statistics. © 2019, Springer Nature Switzerland AG.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of XML Query Processing in Centralized and Distributed Environment 2

Performance Evaluation of XML Query Processing in Centralize...

引用

2nd International Conference on Computational Intelligence and Intelligent Systems, CIIS 2019

作者： Subramaniam, Samini Haw, Su-Cheng Soon, Lay-Ki Faculty of Computing Informatics Multimedia University Persiaran Multimedia Cyberjaya63100 Malaysia School of Information Technology Monash University Malaysia

ISBN: (纸本)9781450372596

eXtensible Markup Language (XML) has been used to transfer data among a wide variety of systems. The increasing usage of XML data and increase in query workloads makes XML unrealisable for centralized storage. Therefore, a distributed query evaluation strategy is well-suited to access these types of collections without having to ship large volumes of irrelevant data across the network. A centralized planning and distributed execution strategy can be used in processing XML queries in distributed manner. In this paper, a technique that processes query in distributed environment is presented, with a pruning technique in local distributed servers and the central server federates the results sent by the distributed servers. A series of evaluations were that compares the performance of centralized and distributed techniques using same set of queries on two different datasets. The results show that the proposed technique, D-DGReLab+ outperformed other centralized techniques, TwigStack and QTwig. © 2019 ACM.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

IODBCON: A integrted object-oriented database system for integrating information about architecture design and construction processes 3

IODBCON: A integrted object-oriented database system for int...

引用

3rd International Conference on Enterprise Information Systems, ICEIS 2001

作者： Marir, Farhi Yip, Yau Jim School of Informatics and Multimedia Technology North London University Holloway Road London United Kingdom

ISBN: (纸本)9729805024

This paper presents IODBCON (Integrated Object Database for Construction), an interactive system for integrating CAD and construction related applications to address the problems of design fragmentation and the gap that exists between construction and design processes. It provides a vehicle for storing architectural design information in an integrated construction object-oriented database that can be shared by a range of construction applications. The IODBCON model uses the object-oriented modelling approach to establish standard models for architectural design that comply with Industry Foundation Classes (IFC) for common interpretation of construction design objects and with CORBA (Common Object Request Broker Architecture) for distribution of the objects amongst the construction applications.

关键词： Object-oriented databases

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：