检索结果-内蒙古大学图书馆

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Large Scale Model Enabled Semantic Communications Based on Robust Knowledge Distillation

Large Scale Model Enabled Semantic Communications Based on R...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Kuiyuan Ding Fangfang Liu Yang Yang Mingzhe Chen Caili Guo Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering and the Institute for Data Science and Computing University of Miami Coral Gables FL USA Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Large scale artificial intelligence (AI) models possess excellent capabilities in semantic representation and understanding, making them particularly well-suited for semantic encoding and decoding. However, the substantial scale of these AI models imposes unacceptable computational resources and communication delays. To address this issue, we propose a semantic communication scheme based on robust knowledge distillation (RKD-SC) for large scale model enabled semantic communications. In the considered system, a transmitter extracts the features of the source image for robust transmission and accurate image classification at the receiver. To effectively utilize the superior capability of large scale model while make the cost affordable, we first transfer knowledge from a large scale model to a smaller scale model to serve as the semantic encoder. Then, to enhance the robustness of the system against channel noise, we propose a channel-aware autoencoder (CAA) based on the Transformer architecture. Experimental results show that the encoder of proposed RKD-SC system can achieve over 93.3% of the performance of a large scale model while compressing 96.67% number of parameters. Code: https://***/echojayne/RKD-SC.

关键词： Transmitters Computational modeling Noise Autoencoders Receivers Semantic communication Transformers Feature extraction Robustness Decoding

来源：评论

学校读者我要写书评

暂无评论

t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Hu, Pengfei Qian, Yuhang Zheng, Tianyue Li, Ang Chen, Zhe Gao, Yue Cheng, Xiuzhen Luo, Jun School of Computer Science and Technology Shandong University China Department of Computer Science and Engineering Southern University of Science and Technology China Department of Electrical and Computer Engineering University of Maryland College Park United States Institue of Space Internet School of Computer Science Fudan University China College of Computing and Data Science Nanyang Technological University Singapore

Given the wide adoption of multimodal sensors (e.g., camera, lidar, radar) by autonomous vehicles (AVs), deep analytics to fuse their outputs for a robust perception become imperative. However, existing fusion methods often make two assumptions rarely holding in practice: i) similar data distributions for all inputs and ii) constant availability for all sensors. Because, for example, lidars have various resolutions and failures of radars may occur, such variability often results in significant performance degradation in fusion. To this end, we present t-READi, an adaptive inference system that accommodates the variability of multimodal sensory data and thus enables robust and efficient perception. t-READi identifies variation-sensitive yet structure-specific model parameters;it then adapts only these parameters while keeping the rest intact. t-READi also leverages a cross-modality contrastive learning method to compensate for the loss from missing modalities. Both functions are implemented to maintain compatibility with existing multimodal deep fusion methods. The extensive experiments evidently demonstrate that compared with the status quo approaches, t-READi not only improves the average inference accuracy by more than 6% but also reduces the inference latency by almost 15× with the cost of only 5% extra memory overhead in the worst case under realistic data and modal variations. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition

arXiv

引用

arXiv 2024年

作者： Wang, Zihan Song, Siyang Luo, Cheng Deng, Songhe Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China University of Leicester United Kingdom Monash University Australia

Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hierarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatio-temporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and magnitude in different AUs’ activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://***/CVI-SZU/MDHR. © 2024, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Constructive Interference Precoding Empowered NOMA-ISAC Design

引用

IEEE Transactions on Wireless Communications 2025年

作者： Wang, Wei Dong, Chao Zhao, Nan Wu, Qihui Niyato, Dusit Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing210023 China Dalian University of Technology School of Information and Communication Engineering Dalian116024 China Nanyang Technological University College of Computing and Data Science 639798 Singapore

Non-orthogonal multiple access (NOMA) can help integrated sensing and communication (ISAC) to accommodate more users and well manage interference. In this paper, we first propose a NOMA-ISAC scheme, in which a multiantenna base station (BS) transmits ISAC signal to detect a radar user (RU), and provide wireless service to the RU and the communication user (CU) simultaneously. The inter-user interference can be mitigated by the successive interference cancellation (SIC). We further investigate the trade-off between minimizing the beampattern matching error and maximizing the CU’s achievable signal-to-noise ratio (SNR), and propose a penalty-based semi-definite relaxation (SDR) method to solve this non-convex problem. Then, to mitigate the instantaneous NOMA-ISAC beampattern shaking and enhance its stability, we utilize constructive interference precoding (CIP) to assist the NOMA-ISAC beampattern design. Introducing CIP can convert the interference from RU into the beneficial signal to CU and the complex SIC can be avoided. Then, the corresponding trade-off can be transformed into a convex problem by the Taylor-series approximation, and an iterative algorithm is proposed to solve it. Moreover, the Manopt toolbox assisted initialization is utilized to accelerate its convergence speed. Simulation results verify that the proposed CIP-NOMA-ISAC scheme can effectively enhance the stability of instantaneous NOMA-ISAC beampattern over limited time slots, and provide higher SNR for CU. © 2002-2012 IEEE.

关键词： Taylor series

来源：评论

学校读者我要写书评

暂无评论

Towards Context-aware Support for Color Vision Deficiency: An Approach Integrating LLM and AR

Towards Context-aware Support for Color Vision Deficiency: A...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Shogo Morita Yan Zhang Takuto Yamauchi Sinan Chen Jialong Li Kenji Tei School of Computing Tokyo Institute of Technology Tokyo Japan International Research Center for Neurointelligence University of Tokyo Tokyo Japan Department of Computer Science and Engineering Waseda University Tokyo Japan Center of Mathematical and Data Sciences Kobe University Kobe Japan

ISBN: (数字)9798350355079

ISBN: (纸本)9798350355086

People with color vision deficiency often face challenges in distinguishing colors such as red and green, which can complicate daily tasks and require the use of assistive tools or environmental adjustments. Current support tools mainly focus on presentation-based aids, like the color vision modes found in iPhone accessibility settings. However, offering context-aware support, like indicating the doneness of meat, remains a challenge since task-specific solutions are not cost-effective for all possible scenarios. To address this, our paper proposes an application that provides contextual and autonomous assistance. This application is mainly composed of: (i) an augmented reality interface that efficiently captures context; and (ii) a multi-modal large language model-based reasoner that serves to cognitize the context and then reason about the appropriate support contents. Preliminary user experiments with two color vision deficient users across five different scenarios have demonstrated the effectiveness and universality of our application.

关键词： Green products Color Faces Consumer electronics Augmented reality Context modeling

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Competitive Multiobjective Multitasking: One-Pass Optimization of Heterogeneous Pareto Solutions

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Li, Yanchi Wu, Xinyi Gong, Wenyin Xu, Meng Wang, Yubo Gu, Qiong China University of Geosciences School of Computer Wuhan430074 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Hubei University of Arts and Science School of Computer Engineering Xiangyang441053 China Hubei University of Arts and Science Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle Xiangyang441053 China

Competitive multiobjective multitask optimization (CMO-MTO) problems involve multiple tasks with comparable objectives but heterogeneous decision variables. The final Pareto front in CMO-MTO consists of multiple subsets corresponding to different tasks. Since the Pareto front subset of one task may be dominated by that of another, competition arises among tasks. Additionally, there may be exploitable similarities among tasks that evolutionary multitasking methods can leverage. For a comprehensive study of CMO-MTO, we construct 12 benchmark CMO-MTO problems with varied competitive relationships and inter-task similarities. To effectively solve CMO-MTO problems, we propose a reference vector contribution-based multitask evolutionary algorithm (RVC-MTEA). RVC-MTEA facilitates both global and local knowledge transfer based on vector contributions and integrates global archives to gather non-dominated solutions across multiple competitive tasks. Comparative results with four popular single-task and six state-of-the-art multitask evolutionary algorithms demonstrate the efficacy of RVC-MTEA. Finally, we apply RVC-MTEA to several real-world applications, showcasing the potential of CMO-MTO in practical decision-making scenarios. © 1997-2012 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization

arXiv

引用

arXiv 2023年

作者： Chen, Jinbiao Wang, Jiahai Zhang, Zizhen Cao, Zhiguang Ye, Te Chen, Siyuan School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Computing and Information Systems Singapore Management University Singapore

Recently, neural heuristics based on deep reinforcement learning have exhibited promise in solving multi-objective combinatorial optimization problems (MOCOPs). However, they are still struggling to achieve high learning efficiency and solution quality. To tackle this issue, we propose an efficient meta neural heuristic (EMNH), in which a meta-model is first trained and then fine-tuned with a few steps to solve corresponding single-objective subproblems. Specifically, for the training process, a (partial) architecture-shared multi-task model is leveraged to achieve parallel learning for the meta-model, so as to speed up the training;meanwhile, a scaled symmetric sampling method with respect to the weight vectors is designed to stabilize the training. For the fine-tuning process, an efficient hierarchical method is proposed to systematically tackle all the subproblems. Experimental results on the multi-objective traveling salesman problem (MOTSP), multi-objective capacitated vehicle routing problem (MOCVRP), and multi-objective knapsack problem (MOKP) show that, EMNH is able to outperform the state-of-the-art neural heuristics in terms of solution quality and learning efficiency, and yield competitive solutions to the strong traditional heuristics while consuming much shorter time. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Wireless Networks: Graph Representation, Architecture and Evaluation

arXiv

引用

arXiv 2024年

作者： Lu, Yang Li, Yuhang Zhang, Ruichen Chen, Wei Ai, Bo Niyato, Dusit School of Computer and Technology China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing100044 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China

Graph neural networks (GNNs) have been regarded as the basic model to facilitate deep learning (DL) to revolutionize resource allocation in wireless networks. GNN-based models are shown to be able to learn the structural information about graphs representing the wireless networks to adapt to the time-varying channel state information and dynamics of network topology. This article aims to provide a comprehensive overview of applying GNNs to optimize wireless networks via answering three fundamental questions, i.e., how to input the system parameters of wireless networks into GNNs, how to improve the expressive performance of GNNs, and how to evaluate GNNs. Particularly, two graph representations are given to transform wireless network parameters into graph-structured data. Then, we focus on the architecture design of the GNN-based models via introducing the basic message passing as well as model improvement methods including multi-head attention mechanism and residual structure. At last, we give task-oriented evaluation metrics for DL-enabled wireless resource allocation schemes. We also highlight certain challenges and potential research directions for the application of GNNs in wireless networks. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Image Retrieval Efficiency through Secure Optimization

Enhancing Cloud Image Retrieval Efficiency through Secure Op...

引用

Knowledge engineering and Communication Systems (ICKECS), International Conference on

作者： N. BalaKrishna M. Sakthivel G.Sai Ushasri J.Naga Thanmai K.Bharath Kumar G.Venkaiah Swamy Department of AI/ML School of Computing Mohan Babu University Data science Tirupati AndhraPradesh India Department of Artificial Intelligence Sri Shanmugha College of Engineering and Technology Sankari Salem Tamilnadu India Department of CSE Sree Sree Vidyanikethan Engineering college Tirupati Andhra pradesh India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

There is a growing trend of using public clouds for image search outsourcing. However, privacy issues arise when image datasets are directly outsourced to untrusted clouds. Recently, a number of secure image retrieval techniques have been put forth. Nevertheless, the majority of them demand input from image owners in order to create secure indexes, wasting a significant amount of their computational power. Numerous approaches are put forth to address this issue; however, their search accuracy is poor when applied to large datasets. We present the first secure image retrieval scheme in this paper that addresses these two issues at the same time to achieve more precise search results. To reduce search time and image owner costs, we allow cloud servers to locally build a reliable hierarchical index graph using the encrypted image features. Moreover, parallel construction and updating of the secure index is possible. We offer a security analysis of the suggested plan.

关键词： Cloud computing Accuracy Image retrieval Market research Vectors Encryption Outsourcing

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：