检索结果-内蒙古大学图书馆

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Tang, Zhenglin Hu, Hai-Miao Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute of Beihang University Hangzhou China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9798400702051

The visible and near-infrared image fusion aims to generate an image that integrates complementary information from images captured in different spectral bands. However, existing fusion methods either only focus on the fusion of spatial information, or fuse spatial and spectral information without decoupling, resulting in undesirable effects such as halo artifacts, information loss, and inferior visual quality. To address these issues, we propose a Spatial-Spectral Decoupling Fusion (SSDF) framework that can effectively fuse the spatial and spectral information of visible and near-infrared images. The SSDF framework decomposes the image pairs into two main branches: the Spatial Feature Enhancement (SFE) branch and the Spectral Characteristic Preservation (SCP) branch. The SFE branch enhances the salient details in the fused image by exploiting the contrast between spatial features and generating region-based fusion weights, while the SCP branch preserves the intrinsic spectral characteristics of the scene by fusing the reflectance characteristics of visible and near-infrared images. The final image is obtained by combining the spatial and spectral information. We conduct extensive experiments to show that our SSDF method can achieve superior fusion performance in subjective visual quality and objective metrics compared with state-of-the-art methods. © 2023 Copyright held by the owner/author(s).

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

TalkingStyle: Personalized Speech-Driven 3D Facial Animation with Style Preservation

引用

IEEE Transactions on Visualization and computer Graphics 2024年 PP卷 1-12页

作者： Song, Wenfeng Wang, Xuan Zheng, Shi Li, Shuai Hao, Aimin Hou, Xia Computer School Beijing Information Science and Technology University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

It is a challenging task to create realistic 3D avatars that accurately replicate individuals' speech and unique talking styles for speech-driven facial animation. Existing techniques have made remarkable progress but still struggle to achieve lifelike mimicry. This paper proposes “TalkingStyle”, a novel method to generate personalized talking avatars while retaining the talking style of the person. Our approach uses a set of audio and animation samples from an individual to create new facial animations that closely resemble their specific talking style, synchronized with speech. We disentangle the style codes from the motion patterns, allowing our method to associate a distinct identifier with each person. To manage each aspect effectively, we employ three separate encoders for style, speech, and motion, ensuring the preservation of the original style while maintaining consistent motion in our stylized talking avatars. Additionally, we propose a new style-conditioned transformer decoder, offering greater flexibility and control over the facial avatar styles. We comprehensively evaluate TalkingStyle through qualitative and quantitative assessments, as well as user studies demonstrating its superior realism and lip synchronization accuracy compared to current state-of-the-art methods. To promote transparency and further advancements in the field, we also make the source code publicly available at https://***/wangxuanx/TalkingStyle. IEEE

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Pricing Policy for a Dynamic Spectrum Allocation Scheme with Batch Requests and Impatient Packets in Cognitive Radio Networks

引用

Journal of Systems Science and Systems Engineering 2022年第2期31卷 133-149页

作者： Haixing Wu Shunfu Jin Wuyi Yue School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan UniversityQinhuangdao 066004China Department of Intelligence and Informatics Konan UniversityKobe 658-8501Japan

In cognitive radio networks(CRNs),multiple secondary users may send out requests simultaneously and one secondary user may send out multiple requests at one time,i.e.,request arrivals usually show an aggregate ***,a secondary user packet waiting in the buffer may leave the system due to impatience before it is transmitted,and this impatient behavior inevitably has an impact on the system *** to investigate the influence of the aggregate behavior of requests and the likelihood of impatience on a dynamic spectrum allocation scheme in CRNs,in this paper a batch arrival queueing model with possible reneging and potential transmission interruption is *** constructing a Markov chain and presenting a transition rate matrix,the steady-state distribution of the queueing model along with a dynamic spectrum allocation scheme is derived to analyze the stochastic behavior of the ***,some important performance measures such as the loss rate,the balk rate and the average delay of secondary user packets are ***,system experiments are carried out to show the change trends of the performance measures with respect to batch arrival rates of secondary user packets for different impatience parameters,different batch sizes of secondary user packets,and different arrival rates of primary user ***,a pricing policy for secondary users is presented and the dynamic spectrum allocation scheme is socially optimized.

关键词： Cognitive radio networks dynamic spectrum scheme batch arrival impatient packets Markov chain social optimization

来源：评论

学校读者我要写书评

暂无评论

From Global to Local: An Adaptive Environmental Illumination Estimation for Non-uniform Scattering 5

From Global to Local: An Adaptive Environmental Illumination...

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Liu, Huaizhuo Hu, Hai-Miao Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute of Beihang University Hangzhou China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9798400702051

The atmospheric scattering model is one of the most widely used model to describe the optical imaging processing of hazy images. However, the global atmospheric light used in the traditional atmospheric scattering model has limitations in describing images with varying local environmental illumination. In this paper, by extending the global atmospheric light to the local illumination, a non-uniform scattering model is proposed, which can better describe real scenes under non-uniform environmental illumination. Based on this model, an adaptive local illumination estimation for hazy image is proposed, which can adapt to the local differences of environment illumination. The experimental results demonstrate that the proposed algorithm can outperform the state-of-the-art algorithms in terms of not only the non-uniform scattering removal but also the adaptability. © 2023 Copyright held by the owner/author(s).

关键词： atmospheric scattering model global atmospheric light local environment illumination non-uniform scattering removal

来源：评论

学校读者我要写书评

暂无评论

Optimizing Link-Identified Forwarding Framework in LEO Satellite Networks 21

Optimizing Link-Identified Forwarding Framework in LEO Satel...

引用

21st International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, WiOpt 2023

作者： Zhang, Hefan Wang, Zhiyuan Zhang, Shan Meng, Qingkai Luo, Hongbin School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Institute of Artificial Intelligence Beihang University Beijing China State Key Laboratory of Software Development Environment China State Key Laboratory of Virtual Reality Technology and Systems China

ISBN: (纸本)9783903176553

Low earth orbit (LEO) satellite networks have the potential to provide low-latency communication with global coverage. To unleash this potential, it is crucial to achieve efficient data delivery. In this paper, we analyze the topology characteristics of LEO satellite networks, and propose a source-route-style forwarding framework. Specifically, we leverage the deterministic neighbor relationship and identify all the unidirectional inter-satellite links (ISLs). Moreover, our framework utilizes the in-packet bloom filter (BF) to store the source-route-style forwarding information. This way, the source satellite could encode multiple ISL identifiers into the BF, which actually specifies the forwarding path. The intermediate satellites only need to check whether the outgoing ISLs are encoded and forward packets accordingly. Due to false positives caused by BF, the more ISLs are encoded at a time, the more redundant forwardings emerge. To reduce forwarding overhead, we take into account segment encoding, allowing the source and intermediate satellites to encode part of ISLs towards the destination. Overall, segment encoding seeks the right balance between forwarding overhead and encoding delay. We characterize a wide range of segment encoding policy in a unified framework, and derive the expected forwarding overhead in a closed-form. The segment encoding design is formulated as a binary non-linear programming, which is NP-hard. To overcome the challenge, we leverage its decomposable structure, and propose an efficient algorithm to solve it optimally. Finally, we validate our analytical results via packet-level experiments. Results also show that our proposed segment encoding policy significantly reduces the queuing delay compared to source encoding. © 2023 IFIP.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Why Go Full? Elevating Federated Learning Through Partial Network Updates 38

Why Go Full? Elevating Federated Learning Through Partial Ne...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Attribute Recognition as Label-balanced Multi-label Learning 41

Pedestrian Attribute Recognition as Label-balanced Multi-lab...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhou, Yibo Hu, Hai-Miao Xiang, Yirong Zhang, Xiaokang Wu, Haotian Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Hangzhou Innovation Institute of Beihang University Hangzhou310051 China The University of Manchester United Kingdom

Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards the side of majority labels;(2) semantics imbalance: model is easily overfitted on the under-represented attributes due to their insufficient semantic *** render perfect label balancing, we propose a novel framework that successfully decouples label-balanced data re-sampling from the curse of attributes co-occurrence, i.e., we equalize the sampling prior of an attribute while not biasing that of the co-occurred *** diversify the attributes semantics and mitigate the feature noise, we propose a Bayesian feature augmentation method to introduce true in-distribution *** both imbalances jointly, our work achieves best accuracy on various popular benchmarks, and importantly, with minimal computational budget. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Power of Age-based Reward in Fresh Information Acquisition 42

The Power of Age-based Reward in Fresh Information Acquisiti...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Wang, Zhiyuan Meng, Qingkai Zhang, Shan Luo, Hongbin Beihang University School of Computer Science and Engineering Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems China Beihang University Institute of Artificial Intelligence Beijing China State Key Laboratory of Software Development Environment China

ISBN: (纸本)9798350334142

Many Internet platforms collect fresh information of various points of interest (PoIs) relying on users who happen to be nearby the PoIs. The platform will offer reward to incentivize users and compensate their costs incurred from information acquisition. In practice, the user cost (and its distribution) is hidden to the platform, thus it is challenging to determine the optimal reward. In this paper, we investigate how the platform dynamically rewards the users, aiming to jointly reduce the age of information (AoI) and the operational expenditure (OpEx). Due to the hidden cost distribution, this is an online non-convex learning problem with partial feedback. To overcome the challenge, we first design an age-based rewarding scheme, which decouples the OpEx from the unknown cost distribution and enables the platform to accurately control its OpEx. We then take advantage of the age-based rewarding scheme and propose an exponentially discretizing and learning (EDAL) policy for platform operation. We prove that the EDAL policy performs asymptotically as well as the optimal decision (derived based on the cost distribution). Simulation results show that the age-based rewarding scheme protects the platform's OpEx from the influence of the user characteristics, and verify the asymptotic optimality of the EDAL policy. © 2023 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Towards Practical Facial Video-based Remote Heart Rate Estimation via Cross Domain rPPG Adaptation 23

Towards Practical Facial Video-based Remote Heart Rate Estim...

引用

Proceedings of the 2023 10th International Conference on Biomedical and Bioinformatics Engineering

作者： Ze Yang Haofei Wang Feng Lu Qinping Zhao the State Key Laboratory of Virtual Reality Technology and Systems and the School of Computer Science and Engineering at Beihang University China Peng Cheng Laboratory China the State Key Laboratory of Virtual Reality Technology and Systems and the School of Computer Science and Engineering at Beihang University China and Peng Cheng Laboratory China

ISBN: (纸本)9798400708343

Remote photoplethysmography (rPPG) is a non-contact technology that can estimate heart rate using facial video and holds significant potential for health monitoring. Despite the latest deep learning-based rPPG approaches can predict high-quality rPPG signal under similar scenarios, these methods often suffer from degraded performance when encountering variations in subjects, environments, or illumination conditions in target domains. To address this challenge, we propose an uncertainty-guided self-training approach that leverages model uncertainty and periodic priors to enhance generalization across different domains without requiring labels in the target domain. We iteratively update the model using pseudo-labels generated from its own predictions on unlabelled data in the target domain, with varying confidence levels informed by the model’s uncertainty estimation. To achieve this, we modify a standard Convolutional Neural Network (CNN) into a Bayesian Neural Network (BNN) for uncertainty estimation, which guides the assignment of pseudo-labels with varying confidence levels. By employing the adversarially learned periodic priors of rPPG signals shared across domains as regularization terms, we further stabilize the model adaptation process. We evaluate the proposed method on two public datasets (PURE and UBFC-rPPG) across five cross-domain tasks. Experimental results demonstrate improved performance over the baselines, with gains ranging from 60.5% to 97.2%, outperforming existing methods in generalization performance for rPPG-based heart rate measurement.

关键词： heart rate estimation remote photoplethysmography unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

GraphFed: A Personalized Subgraph Federated Learning Framework for Non-IID Graphs 20

GraphFed: A Personalized Subgraph Federated Learning Framewo...

引用

20th IEEE International Conference on Mobile Ad Hoc and Smart Systems, MASS 2023

作者： Deng, Pan Liu, Xuefeng Niu, Jianwei Hu, Chunming Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798350324334

Recently, federated graph learning has attracted significant attention, as subgraphs of a global graph may often distribute across different institutions and are subject to privacy restrictions. However, inevitable data heterogeneity among sub-graphs can lead to poor performance of Graph Neural Networks (GNNs) trained by vanilla federated learning algorithm, which has been neglected before. To address this problem we look at subgraphs and find that there are usually overlapping nodes among them. Inspired by the common overlapping nodes among subgraphs, we propose GraphFed, a subgraph federated learning framework which solve the challenge in terms of both data augmentation and personalized federated learning. GraphFed uses common overlapping nodes among subgraphs to locate lost node information and applies data augmentation by retrieving lost nodes and forming common node sets that mitigates data distribution difference. Furthermore, GraphFed treats the overlapping nodes as bridges to calculate the distance among different subgraphs, which implies the similarity of the graph data distribution. Then, we use the distance to perform personalized federated learning. Empirical results and analysis on three real-world graph datasets with graph federated learning settings demonstrate the effectiveness of our proposed framework. © 2023 IEEE.

关键词： Graph neural networks

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：