检索结果-内蒙古大学图书馆

Group-Based Distinctive Image Captioning with Memory Difference Encoding and Attention

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年第4期133卷 1435-1455页

作者： Wang, Jiuniu Xu, Wenjia Wang, Qingzhong Chan, Antoni B. City Univ Hong Kong Dept Comp Sci Kowloon Hong Kong Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

Recent advances in image captioning have focused on enhancing accuracy by substantially increasing the dataset and model size. While conventional captioning models exhibit high performance on established metrics such as BLEU, CIDEr, and SPICE, the capability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employed contrastive learning or re-weighted the ground-truth captions. However, these approaches often overlook the relationships among objects in a similar image group (e.g., items or properties within the same album or fine-grained events). In this paper, we introduce a novel approach to enhance the distinctiveness of image captions, namely Group-based Differential Distinctive Captioning Method, which visually compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we introduce a Group-based Differential Memory Attention (GDMA) module, designed to identify and emphasize object features in an image that are uniquely distinguishable within its image group, i.e., those exhibiting low similarity with objects in other images. This mechanism ensures that such unique object features are prioritized during caption generation for the image, thereby enhancing the distinctiveness of the resulting captions. To further refine this process, we select distinctive words from the ground-truth captions to guide both the language decoder and the GDMA module. Additionally, we propose a new evaluation metric, the Distinctive Word Rate (DisWordRate), to quantitatively assess caption distinctiveness. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves state-of-the-art performance on distinctiveness while not excessively sacrificing accuracy. Moreover, the results of our user study are consistent with the quantitative evaluation and demonstrate the r

关键词： Image caption Vision and language Distinctiveness Memory attention

来源：评论

学校读者我要写书评

暂无评论

G³R: Generating Rich and Fine-Grained mmWave Radar Data From 2D Videos for Generalized Gesture Recognition

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第4期24卷 2917-2934页

作者： Deng, Kaikai Zhao, Dong Zheng, Wenxin Ling, Yue Yin, Kangwen Ma, Huadong Beijing Univ Posts & Telecommun Sch Comp Sci State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Henan Univ Sci & Technol Luoyang 471023 Peoples R China

Millimeter wave radar is gaining traction recently as a promising modality for enabling pervasive and privacy-preserving gesture recognition. However, the lack of rich and fine-grained radar datasets hinders progress in developing generalized deep learning models for gesture recognition across various user postures (e.g., standing, sitting), positions, and scenes. To remedy this, we resort to designing a software pipeline that exploits wealthy 2D videos to generate realistic radar data, but it needs to address the challenge of simulating diversified and fine-grained reflection properties of user gestures. To this end, we design G(3)R with three key components: i) a gesture reflection point generator expands the arm's skeleton points to form human reflection points;ii) a signal simulation model simulates the multipath reflection and attenuation of radar signals to output the human intensity map;iii) an encoder-decoder model combines a sampling module and a fitting module to address the differences in number and distribution of points between generated and real-world radar data for generating realistic radar data. We implement and evaluate G(3)R using 2D videos from public data sources and self-collected real-world radar data, demonstrating its superiority over other state-of-the-art approaches for gesture recognition.

关键词： Generalized sensing synthetic radar data cross domain translation cross domain translation gesture recognition gesture recognition 2D videos 2D videos 2D videos

来源：评论

学校读者我要写书评

暂无评论

Transitioning RingCT Accounts: From Classical to Post-Quantum Security

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第2期12卷 2090-2105页

作者： Duan, Junke Wang, Wei Wang, Licheng Gu, Lize Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Inst Technol Sch Cyberspace Sci & Technol Beijing 100081 Peoples R China

Ring confidential transactions (RingCT) is a classical protocol that enhances transaction privacy within blockchain technology. It is primarily utilized in anonymous cryptocurrencies such as Monero. In recent years, to counter the security threats posed by quantum computing to classical RingCT (C-RCT), several post-quantum RingCT (P-RCT) protocols were proposed. However, prior studies do not address the account transition from C-RCT to P-RCT, which is essential to ensure the quantum resistance and usability of user accounts following the upgrade from C-RCT to P-RCT. In this article, we introduce a RingCT account transition protocol (RAT), which allows users to migrate their accounts from the blockchain with C-RCT to that with P-RCT. The protocol consists of two cryptographic components: 1) a zero-knowledge proof scheme used to prove that two group generators correspond to the same witness and 2) a cross-cryptosystems commitment transition protocol. RAT is fully decentralized and does not require any trusted third parties. Additionally, the transition process does not disclose the account balance and maintains both atomicity and consistency. The security of our protocol relies on the cryptographic components within RingCT, without the need for additional security assumptions, such as a trusted setup. The experimental results demonstrate the effectiveness of our protocol in practice.

关键词： Protocols Security Blockchains Privacy Qubit Public key Internet of Things Blockchain commitment post-quantum ring confidential transactions (RingCT) transition

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Deterministic Delay Performance Guarantee Strategy in RIS-Assisted Communication Networks

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第2期12卷 1907-1921页

作者： Xu, Xiaodong Meng, Zhuo Zhang, Jingxuan Han, Shujun Wang, Bizhu Sun, Mengying Wang, Weidong Zhang, Ping Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Peng Cheng Lab Shenzhen 518066 Guangdong Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Univ Sci & Technol Beijing Beijing Engn & Technol Res Ctr Convergence Network Beijing 100083 Peoples R China Beijing Univ Posts & Telecommun Key Lab Universal Wireless Commun Minist Educ Beijing 100876 Peoples R China

In order to satisfy the requirements for service transformation and upgrading toward industrial digitization, networking, and intelligence, sixth generation-enabled industrial Internet of Things (IIoT) imposes new requirements on deterministic delay. However, the existing best-effort communication networks increase the uncertainty of transmission, making it difficult for users to ensure deterministic delay performance. In this article, we propose a deterministic delay guarantee strategy (DDGS) under reconfigurable intelligent surface (RIS)-assisted communication networks to ensure network performance in IIoT scenarios. In particular, we utilize stochastic network calculus (SNCs) to derive the probability that the delay falls within a specific time window, characterizing the probabilistic bounds of deterministic delay. Then, we explore the relationship between delay determinacy and wireless resources by jointly optimizing the transmit power, the channel blocklength allocation, and the phase-shift matrix at the RIS to maximize delay determinacy. Based on the interdependence of action choices among users and past experience, this article proposes a performance guarantee parameterized deep Q-network (PG-PDQN) algorithm to solve the complex problem containing a mixture of discrete and continuous action spaces. Simulation results show that the DDGS strategy significantly improves the delay determinacy compared to other strategies, and the PG-PDQN algorithm has good convergence, thus effectively improving the network performance.

关键词： Delays Industrial Internet of Things Communication networks Resource management Jitter 6G mobile communication Reliability Deep reinforcement learning (DRL) deterministic delay industrial Internet of Things (IIoT) performance guarantee strategy reconfigurable intelligence surface stochastic network calculus (SNCs)

来源：评论

学校读者我要写书评

暂无评论

Semantic Base Enabled Image Transmission With Fine-Grained HARQ

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第4期24卷 3606-3622页

作者： Zheng, Yuan Wang, Fengyu Xu, Wenjun Zhang, Ping Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing 100876 Peoples R China

Semantic communications (SemComs) which utilize the inherent meanings and relationships of data, have shown significant advantages for information transmission in recent years. In this paper, a novel semantic base (Seb) enabled SemCom framework is proposed, where Sebs, the basic units of fine-grained image semantics, are explicitly shared among transceivers to support image transmission. Specifically, first, to improve source coding efficiency, a Seb-based image codec is proposed, where semantics in each image patch are encoded with synchronized Sebs, that are generated from recent images. To ensure semantic consistency among the embeddings of Sebs, Gray coding is used to establish the projection, enhancing the framework's robustness against channel noise. The details of images are further refined by a residual codec for high-quality reconstructions. Second, to enhance transmission reliability with overhead as small as possible, a semantic-aware fine-grained hybrid automatic repeat request (SAFG-HARQ) is proposed, where only erroneous Sebs are retransmitted to precisely refine corrupted semantics using contextual correlations. Extensive simulations demonstrate that the proposed framework outperforms state-of-the-art works, where the image reconstruction quality is improved by 20% in learned perceptual image patch similarity (LPIPS), with a 60% reduction in transmission costs.

关键词： Semantics Image communication Image reconstruction Reliability Codecs Wireless communication Artificial neural networks Training Image coding Data models Semantic communications explicit semantic base image transmission semantic-aware HARQ

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Snow Mask Prediction and Single Image Desnowing with a Bidirectional Attention Transformer Network 7th

Simultaneous Snow Mask Prediction and Single Image Desnowing...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Zhang, Yonghong Yan, Danfeng BUPT State Key Lab Networking & Switching Technol Beijing Peoples R China BUPT Sch Comp Beijing Peoples R China

ISBN: (纸本)9789819786848;9789819786855

Snow's diverse shapes and sizes pose a significant challenge for single-image desnowing. Current methods typically rely on simple networks to predict the snow masks and subsequently remove snow from images accordingly. However, inaccurate predictions often result in incomplete snow removal. This paper introduces BAT-Net, a novel solution equipped with an image transformer encoder and dual transformer decoders. This architecture enables precise snow mask prediction and comprehensive single image desnowing simultaneously. The image encoder enhances and consolidates features from various layers using Scale Conversion Modules (SCM) and a Feature Aggregation Module (FAM). To ensure accurate snow mask prediction, the snow decoder mirrors the complete transformer structure of the background decoder. Within the background decoder, multiple Bidirectional Attention Modules (BAM) with integrated forward and reverse attention branches effectively leverage snow features and reverse snow features from the snow decoder, facilitating complete snow removal. Moreover, real-world desnowing datasets often contain fallen snow, complicating model training and validation. To address this challenge, we introduce the FallingSnow dataset, exclusively featuring scenes of falling snow. Experimental results across five diverse synthetic and real-world snow removal datasets demonstrate BAT-Net's significant advancements in addressing the challenges of snow mask prediction and single-image desnowing.

关键词： Single image desnowing Snow mask prediction Bidirectional attention

来源：评论

学校读者我要写书评

暂无评论

Toward Copyright Integrity and Verifiability via Multi-Bit Watermarking for Intelligent Transportation Systems

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年

作者： Wang, Yihao Li, Lingxiao Tang, Yifan Zhang, Ru Liu, Jianyi Beijing Univ Posts & Telecommun Sch Cyberspace Secur Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

Intelligent transportation systems (ITS) use advanced technologies such as artificial intelligence to significantly improve traffic flow management efficiency, and promote the intelligent development of the transportation industry. However, if the data in ITS is attacked, such as tampering or forgery, it will endanger public safety and cause social losses. Therefore, this paper proposes a watermarking that can verify the integrity of copyright in response to the needs of ITS, termed ITSmark. ITSmark focuses on functions such as extracting watermarks, verifying permission, and tracing tampered locations. The scheme uses the copyright information to build the multi-bit space and divides this space into multiple segments. These segments will be assigned to tokens. Thus, the next token is determined by its segment which contains the copyright. In this way, the obtained data contains the custom watermark. To ensure the authorization, key parameters are encrypted during copyright embedding to obtain cipher data. Only by possessing the correct cipher data and private key, can the user entirely extract the watermark. Experiments show that ITSmark surpasses baseline performances in data quality, extraction accuracy, and unforgeability. It also shows unique capabilities of permission verification and tampered location tracing, which ensures the security of extraction and the reliability of copyright verification. Furthermore, ITSmark can also customize the watermark embedding position and proportion according to user needs, making embedding more flexible.

关键词： Watermarking Data mining Security Ciphers Telecommunications Data integrity Encryption Copyright protection Vehicular ad hoc networks Transportation Intelligent transportation systems copyright watermark large language models GenAI

来源：评论

学校读者我要写书评

暂无评论

A Concurrent Multibeam Passive Radar for Respiratory Detection From Multiple Subjects

引用

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES 2025年

作者： Huang, Shuaiming Zhao, Heng Hong, Hong Guo, Fengxian Peng, Mugen Zhu, Xiaohua Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing 210094 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

The proliferation of the Internet of Things (IoT) technology has increased wireless interconnectivity, enhancing smart living environments. The millimeter-wave radar is prevalent for indoor positioning, and it consumes spectrum resources and risk interference in multiradar scenarios. In contrast, passive sensing leverages ambient electromagnetic signals, detecting targets through channel variations without occupying the spectrum. However, existing systems are constrained by hardware designs, thus resulting in limited environmental adaptability and poor sensing capabilities. In this article, a concurrent multibeam passive radar is proposed for localization and respiration detection of multiple human targets. Utilizing 16 independent digital receivers with a variable frequency local oscillator (LO), the radar adaptively senses ambient radio frequency signals and selects suitable ones for target detection. Upon identifying the positions of radiation sources and targets, the system generates multiple independent beams to capture motion, mitigating multipath echo interference from wide-beam antennas and enhancing environmental adaptability. Performance evaluation of the passive radar involved various experiments with simulated radiation sources, sliding platforms, and real human targets. The proposed passive radar system accurately localizes and distinguishes external illuminator from human targets, achieving an angular estimation error of sub-2(degrees) in 3 m. It also detects respiration signals through orthogonal baseband processing, with a maximum error of 0.2 beats per minute (BPM) and a median error below 0.03 BPM, ensuring high-precision respiratory monitoring.

关键词： Passive radar Sensors Radar Baseband Radar antennas Monitoring Interference Radar detection Wireless sensor networks Wireless fidelity Digital receiver multibeam passive radar noncontact vital sign detection

来源：评论

学校读者我要写书评

暂无评论

A novel rotor dynamic balancing method based on blade tip clearance measurement without the once per revolution sensor

引用

Chinese Journal of Aeronautics 2025年第2期38卷 445-458页

作者： Weibo LI Weimin WANG Shuai ZHANG Jiale WANG Yulong LIN Tianqing LI Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical TechnologyBeijing 100029China State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical TechnologyBeijing 100029China

The existence of the aeroengine casing,limited monitoring points,and multi-fault characteristics make obtaining the rotor’s vibration transmission characteristics challenging,resulting in difficulties accurately identifying the rotor *** paper utilizes a high-frequency composite sensor to monitor the engine’s blade tip clearance(BTC)and extracts unbalanced information from BTC signals for rotor dynamic balancing,while avoiding the need for the once per revolution(OPR)***,the vibration characteristics of the rotor-blade system under multi-fault conditions are ***,based on BTC measurement,a none OPR method and an unbalance identification method are proposed,in which the radial vibration of the blade tip in the BTC signals at different speeds is extracted and operated in the time domain to obtain the rotor unbalanced vibration,the signal is reconstructed,and cross-correlation analysis is used to accurately identify the magnitude and phase of the unbalanced ***,a rotor test bench is utilized for experimental *** results reveal that the dynamic balancing method based on the BTC signal can more precisely identify the rotor unbalance than the traditional rotor dynamic balancing *** application of this technique will effectively improve engine health management and fault prediction.

关键词： Aeroengine Rotor unbalance Composite sensor None once per revolution Blade tip clearance Dynamic balancing

来源：评论

学校读者我要写书评

暂无评论

Effective Throughput Maximization for NOMA-Enabled URLLC Transmission in Industrial IoT Systems: A Generative AI-Based Approach

引用

IEEE Internet of Things Journal 2025年第10期12卷 13327-13339页

作者： Wang, Xudong Du, Hongyang Feng, Lei Zhou, Fanqin Li, Wenjing Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong

The development of B5G and 6G technologies has led to an explosive growth in device connectivity density in Industrial Internet of Things (IIoT) systems. However, the limited spectrum resources in industrial wireless networks pose significant challenges for large-scale access and communication rates, especially for factory automation applications that are sensitive to control stability and latency. In this paper, we investigate an uplink non-orthogonal multiple access (NOMA) transmission for ultra-reliable and low-latency communication (URLLC) services in IIoT systems, where sensors in NOMA clusters transmit collected data to the base station to meet the high communication rate and control stability requirements of controlled devices. The dynamic control convergence constraint is theoretically transformed into an optimal control condition in each communication round based on the decoding error probability. Additionally, we formulate an optimization problem to maximize the effective throughput of the considered system in the finite blocklength regime by jointly optimizing blocklength allocation, power allocation, and decoding error probability. To solve this mixed integer non-linear programming (MINLP) problem, we decompose it into two sub-problems and propose an efficient optimization framework based on generative AI. Specifically, we apply successive convex approximation (SCA) to solve the blocklength allocation sub-problem, and use a diffusion model to address the joint power control and decoding error probability sub-problem. Finally, extensive simulation results demonstrate the effectiveness of this approach. © 2014 IEEE.

关键词： Decoding

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：