检索结果-内蒙古大学图书馆

Multimodal Large Models Are Effective Action Anticipators

IEEE Transactions on Multimedia 2025年 27卷 2949-2960页

作者： Wang, Binglu Tian, Yao Wang, Shunzhou Yang, Le College of Information and Control Engineering Xi'an University of Architecture and Technology Xi'an710055 China Northwestern Polytechnical University School of Astronautics Xi'an710072 China Peking University School of Electronic and Computer Engineering Shenzhen Graduate School Shenzhen518055 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence China University of Science and Technology of China School of Information Science and Technology Hefei230022 China

The task of long-term action anticipation demands solutions that can effectively model temporal dynamics over extended periods while deeply understanding the inherent semantics of actions. Traditional approaches, which primarily rely on recurrent units or Transformer layers to capture long-term dependencies, often fall short in addressing these challenges. Large Language Models (LLMs), with their robust sequential modeling capabilities and extensive commonsense knowledge, present new opportunities for long-term action anticipation. In this work, we introduce the ActionLLM framework, a novel approach that treats video sequences as successive tokens, leveraging LLMs to anticipate future actions. Our baseline model simplifies the LLM architecture by setting future tokens, incorporating an action tuning module, and reducing the textual decoder layer to a linear layer, enabling straightforward action prediction without the need for complex instructions or redundant descriptions. To further harness the commonsense reasoning of LLMs, we predict action categories for observed frames and use sequential textual clues to guide semantic understanding. In addition, we introduce a Cross-Modality Interaction Block, designed to explore the specificity within each modality and capture interactions between vision and textual modalities, thereby enhancing multimodal tuning. Extensive experiments on benchmark datasets demonstrate the superiority of the proposed ActionLLM framework, encouraging a promising direction to explore LLMs in the context of action anticipation. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Modality Sensing in mmWave Beamforming for Connected Vehicles Using Deep Learning

arXiv

引用

arXiv 2025年

作者： Mollah, Muhammad Baqer Wang, Honggang Karim, Mohammad Ataul Fang, Hua Department of Electrical and Computer Engineering University of Massachusetts DartmouthMA02747 United States Department of Graduate Computer Science and Engineering Katz School of Science and Health Yeshiva University NY10016 United States Department of Computer and Information Science University of Massachusetts DartmouthMA02747 United States

Beamforming techniques are considered as essential parts to compensate severe path losses in millimeter-wave (mmWave) communications. In particular, these techniques adopt large antenna arrays and formulate narrow beams to obtain satisfactory received powers. However, performing accurate beam alignment over narrow beams for efficient link configuration by traditional standard defined beam selection approaches, which mainly rely on channel state information and beam sweeping through exhaustive searching, imposes computational and communications overheads. And, such resulting overheads limit their potential use in vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communications involving highly dynamic scenarios. In comparison, utilizing out-of-band contextual information, such as sensing data obtained from sensor devices, provides a better alternative to reduce overheads. This paper presents a deep learning-based solution for utilizing the multi-modality sensing data for predicting the optimal beams having sufficient mmWave received powers so that the best V2I and V2V line-of-sight links can be ensured proactively. The proposed solution has been tested on real-world measured mmWave sensing and communication data, and the results show that it can achieve up to 98.19% accuracies while predicting top-13 beams. Correspondingly, when compared to existing been sweeping approach, the beam sweeping searching space and time overheads are greatly shortened roughly by 79.67% and 91.89%, respectively which confirm a promising solution for beamforming in mmWave enabled communications. Copyright © 2025, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

A Survey on DRL based UAV Communications and Networking: DRL Fundamentals, Applications and Implementations

arXiv

引用

arXiv 2025年

作者： Zhao, Wei Cui, Shaoxin Qiu, Wen He, Zhiqiang Liu, Zhi Zheng, Xiao Mao, Bomin Kato, Nei School of Computer Science and Technology Anhui University of Technology China Department of Computer and Network Engineering The University of Electro-Communications Japan School of Cybersecurity Northwestern Polytechnical University China Graduate School of Information Sciences Tohoku University Sendai Japan

Unmanned aerial vehicles (UAVs) are playing an increasingly pivotal role in modern communication networks, offering flexibility and enhanced coverage for a variety of applications. However, UAV networks pose significant challenges due to their dynamic and distributed nature, particularly when dealing with tasks such as power allocation, channel assignment, caching, and task offloading. Traditional optimization techniques often struggle to handle the complexity and unpredictability of these environments, leading to suboptimal performance. This survey provides a comprehensive examination of how deep reinforcement learning (DRL) can be applied to solve these mathematical optimization problems in UAV communications and networking. Rather than simply introducing DRL methods, the focus is on demonstrating how these methods can be utilized to solve complex mathematical models of the underlying problems. We begin by reviewing the fundamental concepts of DRL, including value-based, policy-based, and actor-critic approaches. Then, we illustrate how DRL algorithms are applied to specific UAV network tasks by discussing from problem formulations to DRL implementation. By framing UAV communication challenges as optimization problems, this survey emphasizes the practical value of DRL in dynamic and uncertain environments. We also explore the strengths of DRL in handling large-scale network scenarios and the ability to continuously adapt to changes in the environment. In addition, future research directions are outlined, highlighting the potential for DRL to further enhance UAV communications and expand its applicability to more complex, multi-agent settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Room-scale magnetoquasistatic wireless power transfer using a cavity-based multimode resonator

arXiv

引用

arXiv 2025年

作者： Sasatani, Takuya Sample, Alanson P. Kawahara, Yoshihiro Department of Electrical Engineering and Information Systems Graduate School of Engineering The University of Tokyo Bunkyo-ku Tokyo Japan Electrical Engineering and Computer Science Department University of Michigan Ann ArborMI United States

Magnetoquasistatic wireless power transfer can be used to charge and power electronic devices such as smartphones and small home appliances. However, existing coil-based transmitters, which are composed of wire conductors, have a limited range. Here, we show that multimode-quasistatic cavity resonance can provide room-scale wireless power transfer. The approach uses multidirectional, widely distributed currents on conductive surfaces that are placed around the target volume. It generates multiple, mutually unique, three-dimensional magnetic field patterns, where each pattern is attributed to different eigenmodes of a single room scale resonator. Using these modes together, a power delivery efficiency exceeding 37.1% can be achieved throughout a 3 m × 3 m × 2 m test room. With this approach, power exceeding 50 W could potentially be delivered to mobile receivers, while in accordance with safety guidelines. Copyright © 2025, The Authors. All rights reserved.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Rate Maximization for RIS-Aided Edge Computing in Wireless Consumer Application Networks

Deep Reinforcement Learning-Based Computation Rate Maximizat...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Tong Liu Dongyang Xu Tiantian Zhang Shilong Zhang Jinhua Chen Keping Yu Victor C. M. Leung Graduate School of Science and Engineering Hosei University Japan School of Information and Communications Engineering Xi'an Jiaotong University China Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Computer Science and Software Engineering Shenzhen University China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The accelerated development of the Industrial Internet of Things (IoT) has significantly enhanced the computational efficiency and processing capabilities of Wireless Consumer Application Networks (WCAN). Despite these advancements, the performance of WCAN remains constrained by the inherent limitations in computational capacity and energy resources of wireless devices. To address these issues, this paper proposes a wireless powered-mobile edge computing system with Reconfigurable Intelligent Surface (RIS) assistance for WCAN, where wireless consumer devices can not only harvest energy from access point, but also offload computing tasks to edge server with the help of RIS. Aiming to maximize the system computation rate, a non-convex problem is developed and a block optimization with deep reinforcement learning (BO-DRL) scheme is proposed. First, the RIS phase shifts in the Wireless Power Transfer (WPT) stage and offloading stage are optimized using closed-form solutions and the gradient ascent algorithm, respectively. Subsequently, the offloading strategies are optimized using deep reinforcement learning, and a convex optimization algorithm is employed to obtain the time allocation for the WPT and offloading stages. Numerical results illustrate that the BO-DRL algorithm greatly enhances computation rate by 20% compared to without RIS.

关键词： Wireless communication Training Performance evaluation Wireless power transfer Reconfigurable intelligent surfaces Deep reinforcement learning Convex functions Resource management Servers Uplink

来源：评论

学校读者我要写书评

暂无评论

Enhanced adaptive data rate strategies for energy-efficient Internet of Things communication in LoRaWAN

引用

International Journal of Communication Systems 2025年第2期38卷

作者： Ali Lodhi, Muhammad Wang, Lei Mahmood, Khalid Farhad, Arshad Chen, Jenhui Kumari, Saru School of Software Technology Dalian University of Technology Dalian China Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliu Taiwan Department of Computer Science FAST-National University of Computer and Emerging Sciences Islamabad Pakistan Department of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan Department of Mathematics Chaudhary Charan Singh University Meerut India School of Chemical Engineering and Physical Sciences Lovely Professional University Jalandhar India

The long-range wide area network (LoRaWAN) is a standard for the Internet of Things (IoT) because it has low cost, long range, not energy-intensive, and capable of supporting massive end devices (EDs). The adaptive data rate (ADR) adjusts parameters at both EDs and the network server (NS). This includes modifying the transmission spreading factor (SF) and transmit power (TP) to minimize packet errors and optimize transmission performance at the NS. The ADR managed by NS aims to provide reliable and energy-efficient resources (e.g., SF and TP) to EDs by monitoring the packets received from the EDs. However, since the channel condition changes rapidly in LoRaWAN due to mobility, the existing ADR algorithm is unsuitable and results in a significant amount of packet loss and retransmissions causing an increase in energy consumption. In this paper, we enhance the ADR by introducing Kalman filter-based ADR (KF-ADR) and moving median-based ADR (Median-ADR), which estimate the optimal SNR by considering the mobility later used to assign the SF and TP to EDs. The simulation results showed that the proposed techniques outperform the legacy ADRs in terms of convergence period, energy consumption, and packet success ratio. © 2024 John Wiley & Sons Ltd.

关键词： adaptive data rate Internet of Things Kalman filter LoRa LoRaWAN mobility resource allocation

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Naming Rule Checking Function and its Applications to Java programming Codes

An Implementation of Naming Rule Checking Function and its A...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Khaing Hsu Wai Nobuo Funabiki Mustika Mentari Soe Thandar Aung Htoo Htoo Sandi Kyaw Shingo Yamaguchi Wen-Chung Kao Graduate School of Science and Engineering Akita University Akita Japan Department of Information and Communication Systems Okayama University Okayama Japan Department of Computer and Information Science Tokyo University of Agriculture and Technology Tokyo Japan Graduate School of Sciences and Technology for Innovation Yamaguchi University Japan Department of Electrical Engineering National Taiwan Normal University Taipei Taiwan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Currently, a lot of universities are offering Java programming courses for teaching the first-step object-oriented programming language. For novice students, to master writing readable codes using proper names for variables, classes, and methods is crucial in Java programming, to improve under-standability and maintainability. In this paper, we consider four naming rules to write a readable code and implement the naming rule checking function to check whether the given code follows them. For evaluations, we applied the proposal to 2, 908 source codes submitted in Java programming courses from students in Okayama University, Japan, Malang State Polytechnic, Indonesia, and Yamaguchi University, Japan. The results confirm the effectiveness of the proposal.

关键词： Java Codes Source coding Education programming Writing Proposals Object oriented programming Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Separability Membrane: 3D Active Contour for Point Cloud Surface Reconstruction

arXiv

引用

arXiv 2025年

作者： Pratamasunu, Gulpi Qorik Oktagalu Hao, Guoqing Fukui, Kazuhiro Department of Computer Science Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba305-0085 Japan Department of Integrated Information Technology Aoyama Gakuin University Kanagawa Sagamihara252-5258 Japan

This paper proposes Separability Membrane, a robust 3D active contour for extracting a surface from 3D point cloud object. Our approach defines the surface of a 3D object as the boundary that maximizes the separability of point features, such as intensity, color, or local density, between its inner and outer regions based on Fisher’s ratio. Separability Membrane identifies the exact surface of a 3D object by maximizing class separability while controlling the rigidity of the 3D surface model with an adaptive B-spline surface that adjusts its properties based on the local and global separability. A key advantage of our method is its ability to accurately reconstruct surface boundaries even when they are ambiguous due to noise or outliers, without requiring any training data or conversion to volumetric representation. Evaluations on a synthetic 3D point cloud dataset and the 3DNet dataset demonstrate the membrane’s effectiveness and robustness under diverse conditions. © 2025, CC BY.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark

arXiv

引用

arXiv 2025年

作者： Wang, Shiao Wang, Xiao Wang, Chao Jin, Liye Zhu, Lin Jiang, Bo Tian, Yonghong Tang, Jin School of Computer Science and Technology Anhui University Hefei230601 China Beijing Institute of Technology Beijing China Peng Cheng Laboratory Shenzhen China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China

Recent years have witnessed unprecedented growth in the field of visual object tracking using bio-inspired event cameras. Previous research in this domain has primarily followed two paths: aligning RGB data and event streams for precise tracking or developing trackers that rely solely on events. However, while the former approach often incurs significant computational costs during inference, the latter may struggle with challenges posed by noisy event data or limited spatial resolution. In this paper, we present a hierarchical knowledge distillation framework designed to leverage multi-modal and multi-view information during the training phase, while utilizing only event signals for tracking. Specifically, we first train a teacher Transformer-based multi-modal/multi-view tracking network by simultaneously feeding RGB frames and event streams. We then introduce a novel hierarchical knowledge distillation strategy that incorporates the similarity matrix, feature representation, and response map-based distillation to guide the learning of the student Transformer network. We also enhance the model’s ability to capture temporal dependencies by applying the temporal Fourier transform to establish temporal relationships between video frames. We adapt the network model to specific target objects during testing via a newly proposed test-time tuning strategy to achieve high performance and flexibility in target tracking. Recognizing the limitations of existing event-based tracking datasets, which are predominantly low-resolution (346 × 260), we propose EventVOT, the first large-scale high-resolution (1280 × 720) event-based tracking dataset. It comprises 1141 videos spanning diverse categories such as pedestrians, vehicles, UAVs, ping pong, etc. Extensive experiments on both low-resolution (FE240hz, VisEvent, FELT), and our newly proposed high-resolution EventVOT dataset fully validated the effectiveness of our proposed method. Both the benchmark dataset and source code have

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

RDVC: Efficient Deep Video Compression with Regulable Rate and Complexity Optimization

引用

IEEE Transactions on Multimedia 2025年

作者： Wei, Xiaojie Lin, Jielian Xu, Jiawei Gao, Wei Zhao, Tiesong Putian University School of Mechanical Electrical & Information Engineering PutianFujian China Shenzhen Graduate School Peking University School of Electronic and Computer Engineering Shenzhen518055 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou350108 China Tsinghua University Department of Electronic Engineering Beijing100084 China

Deep video coding has paved a way to break through the performance bottleneck of reigning hybrid video coding. However, unlike hybrid video codecs, existing deep video codecs cannot offer both flexible rates and regulable complexities within one single codec, which limits their applications. In this paper, we propose a Regulable Deep Video Codec (RDVC) to address the above issue. First, we propose an Adaptive Feature Compression (AFC) network that generates variable rates while ensuring Rate-Distortion (RD) performance. The network introduces a two-stage coarse-to-fine rate adjustment that can be controlled by a user-specified rate level. Second, we propose a Spatio-Temporal Feature Propagation (STFP) mechanism to provide high-quality reference information for AFC process. Third, we also utilize slimmable convolutional components in our framework to adjust decoding complexity constrained by user configuration. Experimental results demonstrate that RDVC can adjust the codec structure flexibly according to different user configurations while maintaining advanced performance. On average, it reduces the bit-per-pixel (bpp) by 9.35%/58.12% while maintaining the same PSNR/MS-SSIM as the reference software VTM-13.2. Sourcecode is available at: https://***/WXJ0001/RDVC. © 2025 IEEE.

关键词： Signal distortion

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：