检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Jianfei Bai, Jun Lin, Chenghua Wang, Yanmeng Rong, Wenge State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

Variational autoencoders (VAEs) are one of the most powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound (ELBo), which consists of a conditional likelihood for generation and a negative Kullback-Leibler (KL) divergence for regularization. In practice, optimizing ELBo often leads the posterior distribution of all samples converging to the same degenerated local optimum, namely posterior collapse or KL vanishing. There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and the hole problem, i.e., the mismatch between the aggregated posterior distribution and the prior distribution. To this end, we introduce new training objectives to tackle both problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution. Through experiments on language modeling, latent space visualization, and interpolation, we show that our proposed method can solve both problems effectively and thus outperforms the existing methods in latent-directed generation. To the best of our knowledge, we are the first to jointly solve the hole problem and posterior collapse. Copyright © 2022, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Discernible image mosaic with edge-aware adaptive tiles

引用

Computational Visual Media 2019年第1期5卷 45-58页

作者： Pengfei Xu Jianqiang Ding Hao Zhang Hui Huang College of Computer Science and Software Engineering Shenzhen University School of Computing Science Simon Fraser University

We present a novel method to produce discernible image mosaics, with relatively large image tiles replaced by images drawn from a database, to resemble a target image. Compared to existing works on image mosaics, the novelty of our method is ***, believing that the presence of visual edges in the final image mosaic strongly supports image perception,we develop an edge-aware photo retrieval scheme which emphasizes the preservation of visual edges in the target image. Secondly, unlike most previous works which apply a pre-determined partition to an input image, our image mosaics are composed of adaptive tiles, whose sizes are determined based on the available images in the database and the objective of maximizing resemblance to the target image. We show discernible image mosaics obtained by our method, using image collections of only moderate size. To evaluate our method, we conducted a user study to validate that the image mosaics generated present both globally and locally appropriate visual impressions to the human observers. Visual comparisons with existing techniques demonstrate the superiority of our method in terms of mosaic quality and perceptibility.

关键词： image mosaic image retrieval image synthesis

来源：评论

学校读者我要写书评

暂无评论

Progressive Glass Segmentation

arXiv

引用

arXiv 2022年

作者： Yu, Letian Mei, Haiyang Dong, Wen Wei, Ziqi Zhu, Li Wang, Yuxin Yang, Xin The School of Computer Science and Technology Dalian University of Technology Dalian116024 China The School of Software Tsinghua University Beijing100084 China The School of Control Science and Engineering Dalian University of Technology Dalian116024 China

Glass is very common in the real world. Influenced by the uncertainty about the glass region and the varying complex scenes behind the glass, the existence of glass poses severe challenges to many computer vision tasks, making glass segmentation as an important computer vision task. Glass does not have its own visual appearances but only transmit/reflect the appearances of its surroundings, making it fundamentally different from other common objects. To address such a challenging task, existing methods typically explore and combine useful cues from different levels of features in the deep network. As there exists a characteristic gap between level-different features, i.e., deep layer features embed more high-level semantics and are better at locating the target objects while shallow layer features have larger spatial sizes and keep richer and more detailed low-level information, fusing these features naively thus would lead to a sub-optimal solution. In this paper, we approach the effective features fusion towards accurate glass segmentation in two steps. First, we attempt to bridge the characteristic gap between different levels of features by developing a Discriminability Enhancement (DE) module which enables level-specific features to be a more discriminative representation, alleviating the features incompatibility for fusion. Second, we design a Focus-and-Exploration Based Fusion (FEBF) module to richly excavate useful information in the fusion process by highlighting the common and exploring the difference between level-different features. Combining these two steps, we construct a Progressive Glass Segmentation Network (PGSNet) which uses multiple DE and FEBF modules to progressively aggregate features from high-level to low-level, implementing a coarse-to-fine glass segmentation. In addition, we build the first home-scene-oriented glass segmentation dataset for advancing household robot applications and in-depth research on this topic. Extensive experiments de

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An n-MOSFET Layout with Multi-Finger Z Gate for Radiation Tolerance 5

An n-MOSFET Layout with Multi-Finger Z Gate for Radiation To...

引用

5th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2022

作者： Shan, Chan Liu, Ying Chen, Huan Huo, Dong-Yang Xu, Tian-Rong Jimei University College of Ocean Information Engineering Xiamen China Xiamen Institute of Software Technology Department of Software Technology Xiamen China Minjiang University School of Journalism and Communication Fuzhou China Universiti Malaya Faculty of Computer Science and Information Technology Department of Information Systems Kuala Lumpur Malaysia Universiti Malaya Planning Faculty of Built Environment Department of Urban and Regional Kuala Lumpur Malaysia

ISBN: (数字)9781665479295

ISBN: (纸本)9781665479295

In this paper, a new n-MOSFET layout with multi-finger Z gate is proposed to reduce the total ionizing dose (TID) effect. In addition to the proposed layout, multi-finger single gate layout is also simulated using Sentaurus TCAD in 3D. Firstly, drain current - gate voltage curves of both layouts are compared in order to verify the radiation hardening ability of the proposed layout. Secondly, we compare TID responses by extracting threshold voltages and leakage currents from both layouts. Thirdly, the finger number is investigated for both layouts because it is an important factor for multi-finger layout. The results have indicated that the finger number significantly affects the multi-finger single gate layout, whereas the proposed multi-finger Z gate layout is relatively little affected by the finger number in radiation environment. © 2022 IEEE.

关键词： Drain current

来源：评论

学校读者我要写书评

暂无评论

Nam-Cr: Noise-Aware Multisensor Cloud Removal for Optical Remote Sensing Imagery by Fusing Sar Data

SSRN

引用

SSRN 2024年

作者： Xu, Meng Zhang, Ruihua Liu, Shuyi Jia, Xiuping Li, Qingquan Jia, Sen College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Engineering and Information Technology University of New South Wales CanberraACT2612 Australia Guangdong Key Laboratory of Urban Informatics Shenzhen University Shenzhen518060 China College of Civil and Transportation Engineering Shenzhen University Shenzhen518060 China

Optical remote sensing images frequently suffer from extensive cloud coverage, resulting in the loss of valuable raw data and severely hindering their Earth observation capacity. Cloud removal methods employing auxiliary synthetic aperture radar (SAR) data have been explored in recent years instead of using optical cloud-free reference images from the same area on a different date, where uncertainties arise due to surface changes and unavailability of cloud-free images is often encountered. However, the inherent speckle noise in SAR data brings challenges in interpreting texture information from SARs into optical images for cloud removal. In this study, we propose a data-driven noise-aware multisensor cloud removal (NAM-CR) method for multispectral images by fusing SAR data. The network is composed of a self-attention multimodal aggregator (SMMA) and deep-shallow feature cross-fusion (DSFF) modules for better integration of the texture information from SAR data and spectral information from optical images. To further reduce speckle noise effects, the proposed method is equipped with a novel cloud-guided noise optimization loss function. We trained and tested our method on 100,000 patch triplets from the SEN12MS-CR dataset containing global all-season Sentinel optical and SAR images. The experimental results demonstrate that NAM-CR outperforms the other five state-of-the-art cloud removal methods and achieves outstanding performance with the highest PSNR of 34.22 dB and minimal parameter usage. The source code is accessible to the public at http://***/. © 2024, The Authors. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Service Migration for Delay-Sensitive IoT Applications in Edge Networks

引用

IEEE Transactions on Services Computing 2025年

作者： Li, Xiaocui Zhou, Zhangbing Wang, Yasha Deng, Shuiguang Hung, Patrick C. K. School of Information Engineering Beijing100083 China Peking University National Research & Engineering Center of Software Engineering Beijing100871 China Peking University New Generation Information Technology Research Institute Tianjin300380 China School of Information Engineering Frontiers Science Center for Deep-Time Digital Earth Beijing100083 China Institut Polytechnique de Paris Télécom SudParis Palaiseau91120 France Zhejiang University College of Computer Science and Technology Hangzhou310012 China Ontario Tech University Faculty of Business and Information Technology Oshawa Canada

The proliferation of Internet of Things (IoT) applications prompts extraordinary demands for the collaboration of large amounts of computational resources provided by IoT devices in edge networks, and these applications are mostly delay-sensitive. Generally, these resources are encapsulated as IoT services. Thereafter, IoT applications can be performed, such that the collaboration of their sub-tasks is achieved through the composition of functionally complementary and geographically contiguous IoT services. The status of computational resources in IoT devices may change continuously along with their occupancy and release by IoT services. Considering the resource-scarceness of IoT devices, when the workload of IoT devices increases due to more services to be processed, certain IoT devices may hardly have enough remaining resources to co-host more instances of certain IoT services prescribed by forthcoming IoT applications with strict constraints. As a result, the delay satisfaction of both on-running and forthcoming IoT applications may be negatively impacted, or even hardly be satisfied any longer. To solve this issue, this paper proposes a rEsource-Efficient service Configuration (E2rC) mechanism, which aims to optimize the configuration of computational resources provided by IoT devices with respect to complex requirements prescribed by IoT applications, through service migration techniques. This service migration problem is formulated as markov multi-phases decisions, which is solved through our enhanced Deep Reinforcement Learning (DRL) approach with a two-layer Q-network. Extensive experiments have been conducted upon the dataset of our testbed system. Evaluation results show that our E2rC is more efficient than the state-of-art counterparts in satisfying delay constraints of IoT applications, while reducing the energy consumption and improving the resource utilization efficiency of IoT devices. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Improving variational autoencoders with density gap-based regularization 22

Improving variational autoencoders with density gap-based re...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jianfei Zhang Jun Bai Chenghua Lin Yanmeng Wang Wenge Rong State Key Laboratory of Software Development Environment Beihang University China and School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

ISBN: (纸本)9781713871088

关键词：

来源：评论

学校读者我要写书评

暂无评论

UniUIR: Considering Underwater Image Restoration as An All-in-One Learner

arXiv

引用

arXiv 2025年

作者： Zhang, Xu Zhang, Huan Wang, Guoli Zhang, Qian Zhang, Lefei Du, Bo The Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan430072 China The Hubei Luojia Laboratory Wuhan China The National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China The School of Information Engineering Guangdong University of Technology Guangzhou510006 China The Horizon Robotics Beijing100083 China

Existing underwater image restoration (UIR) methods generally only handle color distortion or jointly address color and haze issues, but they often overlook the more complex degradations that can occur in underwater scenes. To address this limitation, we propose a Universal Underwater Image Restoration method, termed as UniUIR, considering the complex scenario of real-world underwater mixed distortions as an all-in-one manner. To decouple degradation-specific issues and explore the inter-correlations among various degradations in UIR task, we designed the Mamba Mixture-of-Experts module. This module enables each expert to identify distinct types of degradation and collaboratively extract task-specific priors while maintaining global feature representation based on linear complexity. Building upon this foundation, to enhance degradation representation and address the task conflicts that arise when handling multiple types of degradation, we introduce the spatial-frequency prior generator. This module extracts degradation prior information in both spatial and frequency domains, and adaptively selects the most appropriate task-specific prompts based on image content, thereby improving the accuracy of image restoration. Finally, to more effectively address complex, region-dependent distortions in UIR task, we incorporate depth information derived from a large-scale pre-trained depth prediction model, thereby enabling the network to perceive and leverage depth variations across different image regions to handle localized degradation. Extensive experiments demonstrate that UniUIR can produce more attractive results across qualitative and quantitative comparisons, and shows strong generalization than state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

BcIIS: Blockchain-Based Intelligent Identification Scheme of Massive IoT Devices

BcIIS: Blockchain-Based Intelligent Identification Scheme of...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Yi Sun Tong Xu Ali Kashif Bashir Jie Liu Marwan Omar School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Department of Computing and Mathematics Manchester United Kingdom Woxsen School of Business Woxsen University India Information Technology and Management Illinois Institute of Technology USA

With the rapid development of loT technology, various loT devices enter our daily life. The continuously increasing scale of the massive loT devices in both of numbers and types further bring heavy pressure on loT network management and security. Therefore, how to accurately identify and efficiently manage so massive loT devices has become a challenge. In this paper, we propose BcllS, Blockchain-based Intelligent Identification Scheme of Massive loT Devices. It applies a decentralized identification architecture and realizes learning sustainably as well as efficiently identifying by updating the identification model constantly according to the ledger which is maintained by all gateways collaboratively. Experiments show that the identification accuracy can achieve up to 99.5 %.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Target High-Utility Itemsets

arXiv

引用

arXiv 2022年

作者： Miao, Jinbao Gan, Wensheng Wan, Shicheng Wu, Yongdong Fournier-Viger, Philippe The College of Cyber Security Jinan University Guangzhou510632 China The School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China The College of Computer Science and Software Engineering Shenzhen University China

For applied intelligence, utility-driven pattern discovery algorithms can identify insightful and useful patterns in databases. However, in these techniques for pattern discovery, the number of patterns can be huge, and the user is often only interested in a few of those patterns. Hence, targeted mining of high-utility itemsets has emerged as a key research topic, where the aim is to find a subset of patterns that meet a target pattern constraint instead of all patterns. This is a challenging task because efficiently finding tailored patterns in a very large search space requires a targeted mining algorithm. A first algorithm called TargetUM has been proposed, which adopts an approach similar to post-processing using a tree structure, but the running time and memory consumption are unsatisfactory in many situations. In this paper, we address this issue by proposing a novel list-based algorithm with pattern matching mechanism, named THUIM (Targeted High-Utility Itemset Mining), which can quickly match high-utility itemsets during the mining process to select the target patterns. Extensive experiments were conducted on different datasets to compare the performance of the proposed algorithm with state-of-the-art algorithms. Results show that THUIM performs very well in terms of runtime and memory consumption, and has good scalability compared to TargetUM. Copyright © 2022, The Authors. All rights reserved.

关键词： Pattern matching

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：