检索结果-内蒙古大学图书馆

Gloss-driven Conditional Diffusion Models for Sign Language Production

ACM Transactions on Multimedia Computing, Communications and Applications 2025年第4期21卷 1-17页

作者： Tang, Shengeng Xue, Feng Wu, Jingjing Wang, Shuo Hong, Richang School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China School of Data Science School of Information Science and Technology University of Science and Technology of China Hefei China

Sign Language Production (SLP) aims to convert text or audio sentences into sign language videos corresponding to their semantics, which is challenging due to the diversity and complexity of sign languages, and cross-modal semantic mapping issues. In this work, we propose a Gloss-driven Conditional Diffusion Model (GCDM) for SLP. The core of the GCDM is a diffusion model architecture, in which the sign gloss sequence is encoded by a Transformer-based encoder and input into the diffusion model as a semantic prior condition. In the process of sign pose generation, the textual semantic priors carried in the encoded gloss features are integrated into the embedded Gaussian noise via cross-attention. Subsequently, the model converts the fused features into sign language pose sequences through T-round denoising steps. During the training process, the model uses the ground-truth labels of sign poses as the starting point, generates Gaussian noise through T rounds of noise, and then performs T rounds of denoising to approximate the real sign language gestures. The entire process is constrained by the MAE loss function to ensure that the generated sign language gestures are as close as possible to the real labels. In the inference phase, the model directly randomly samples a set of Gaussian noise, generates multiple sign language gesture sequence hypotheses under the guidance of the gloss sequence, and outputs a high-confidence sign language gesture video by averaging multiple hypotheses. Experimental results on the Phoenix2014T dataset show that the proposed GCDM method achieves competitiveness in both quantitative performance and qualitative visualization. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Forming

来源：评论

学校读者我要写书评

暂无评论

Successive Interference Cancellation-Enabled Timely Status Update in Linear Multi-Hop Wireless Networks

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 5298-5311页

作者： Han, Xinhui Pan, Haoyuan Wang, Zhaorui Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Future Network of Intelligence Institute School of Science and Engineering Shenzhen518172 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology College of Computer Science and Software Engineering Shenzhen518060 China

We investigate the timely status update in linear multi-hop wireless networks, where a source tries to deliver status update packets to a destination through a sequence of half-duplex relays. Timeliness is measured by the age of information (AoI) metric. Maintaining a low AoI at the destination typically necessitates frequent transmission of update packets from the source. However, high packet transmission frequency in multi-hop scenarios can result in mutual wireless interference at intermediate relays. Specifically, when an intermediate relay receives wireless signals of a new packet from its previous node, simultaneous transmission of an old packet by its subsequent node to the next hop may cause wireless signals to interfere at the intermediate relay, conventionally leading to packet collision. A key motivation to solve this issue is that the intermediate relay has previously received the old packet (which can thus be forwarded to the subsequent node for further relaying). Hence, successive interference cancellation (SIC) can be employed to mitigate interference of the old packet and recover the new packet. This paper designs an SIC-enabled packet relaying scheme tailored to low AoI. Initially focusing on a three-hop network, we subsequently extend our approach to general multi-hop networks. We model the multi-hop relaying scheme using a Markov chain to derive the theoretical average AoI. Theoretical and simulation results indicate that the SIC-enabled packet relaying scheme significantly reduces the average AoI compared to the non-SIC approaches, owing to an increased packet transmission frequency at the source and the effectiveness of SIC techniques at the relays. © 2002-2012 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-Box Scenario

引用

IEEE Transactions on Multimedia 2025年 27卷 2666-2681页

作者： Liu, Renyang Lam, Kwok-Yan Zhou, Wei Wu, Sixing Zhao, Jun Hu, Dongting Gong, Mingming Yunnan University School of Information Science and Engineering Kunming650500 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Yunnan University School of Software Engineering Research Center of Cyberspace Kunming650500 China University of Melbourne Melbourne Centre for Data Science School of Mathematics and Statistics ParkvilleVIC3010 Australia

Extensive studies have revealed that deep neural networks (DNNs) are vulnerable to adversarial attacks, especially black-box ones, which can heavily threaten the DNNs deployed in the real world. Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness. Despite the significant progress made recently, existing black-box attack methods still suffer from unsatisfactory performance due to the vast number of queries needed to optimize desired perturbations. Besides, the other critical challenge is that adversarial examples built in a noise-adding manner are abnormal and struggle to successfully attack robust models, whose robustness is enhanced by adversarial training against small perturbations. There is no doubt that these two issues mentioned above will significantly increase the risk of exposure and result in a failure to dig deeply into the vulnerability of DNNs. Hence, it is necessary to evaluate DNNs' fragility sufficiently under query-limited settings in a non-additional way. In this paper, we propose the Spatial Transform Black-box Attack (STBA), a novel framework to craft formidable adversarial examples in the query-limited scenario. Specifically, STBA introduces a flow field to the high-frequency part of clean images to generate adversarial examples and adopts the following two processes to enhance their naturalness and significantly improve the query efficiency: a) we apply an estimated flow field to the high-frequency part of clean images to generate adversarial examples instead of introducing external noise to the benign image, and b) we leverage an efficient gradient estimation method based on a batch of samples to optimize such an ideal flow field under query-limited settings. Compared to existing score-based black-box baselines, extensive experiments indicated that STBA could effectively improve the imperceptibility of the adversarial examples and remarkably boost the attack success rate u

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

A sharding blockchain-based UAV system for search and rescue missions

引用

Frontiers of Computer science 2025年第3期19卷 103-118页

作者： Xihan ZHANG Jiashuo ZHANG Jianbo GAO Libin XIA Zhi GUAN Hao HU Zhong CHEN School of Computer Science Peking UniversityBeijing 100871China Peking University Chongqing Research Institute of Big Data Chongqing 401329China National Engineering Research Center for Software Engineering Peking UniversityBeijing 100871China State Key Lab for Novel Software Technology Nanjing UniversityNanjing 210023China

Sharding is a promising technique to tackle the critical weakness of scalability in blockchain-based unmanned aerial vehicle(UAV)search and rescue(SAR)*** breaking up the blockchain network into smaller partitions called shards that run independently and in parallel,shardingbased UAV systems can support a large number of search and rescue UAVs with improved scalability,thereby enhancing the rescue ***,the lack of adaptability and interoperability still hinder the application of sharded blockchain in UAV SAR *** refers to making adjustments to the blockchain towards real-time surrounding situations,while interoperability refers to making cross-shard interactions at the mission *** address the above challenges,we propose a blockchain UAV system for SAR missions based on dynamic sharding *** from the benefits in scalability brought by sharding,our system improves adaptability by dynamically creating configurable and mission-exclusive shards,and improves interoperability by supporting calls between smart contracts that are deployed on different *** implement a prototype of our system based on Quorum,give an analysis of the improved adaptability and interoperability,and conduct experiments to evaluate the *** results show our system can achieve the above goals and overcome the weakness of blockchain-based UAV systems in SAR scenarios.

关键词： blockchain sharding unmanned aerial vehicle search and rescue blockchain interoperability

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Secure data Aggregation for Smart Grids with Privacy Preservation

引用

Computers, Materials & Continua 2025年第1期82卷 799-816页

作者： Congcong Wang Chen Wang Wenying Zheng Wei Gu School of Software Nanjing University of Information Science and TechnologyNanjing210044China School of Information Science and Engineering Zhejiang Sci-Tech UniversityHangzhou310018China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China School of Computer Science and Technology(School of Artificial Intelligence) Zhejiang Sci-Tech UniversityHangzhou310018China School of Computer Science(School of Cyber Science and Engineering) Nanjing University of Information Science and TechnologyNanjing210044China

As smart grid technology rapidly advances,the vast amount of user data collected by smart meter presents significant challenges in data security and privacy *** research emphasizes data security and user privacy concerns within smart ***,existing methods struggle with efficiency and security when processing large-scale *** efficient data processing with stringent privacy protection during data aggregation in smart grids remains an urgent *** paper proposes an AI-based multi-type data aggregation method designed to enhance aggregation efficiency and security by standardizing and normalizing various data *** approach optimizes data preprocessing,integrates Long Short-Term Memory(LSTM)networks for handling time-series data,and employs homomorphic encryption to safeguard user *** also explores the application of Boneh Lynn Shacham(BLS)signatures for user *** proposed scheme’s efficiency,security,and privacy protection capabilities are validated through rigorous security proofs and experimental analysis.

关键词： Smart grid data security privacy protection artificial intelligence data aggregation

来源：评论

学校读者我要写书评

暂无评论

Advances in Robust Federated Learning: A Survey With Heterogeneity Considerations

引用

IEEE Transactions on Big data 2025年第3期11卷 1548-1567页

作者： Chen, Chuan Liao, Tianchi Deng, Xiaojun Wu, Zihou Huang, Sheng Zheng, Zibin Sun Yat-sen University School of Computer Science and Engineering Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Sun Yat-sen University School of Software Engineering Zhuhai519000 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Sun Yat-sen University School of Systems Science and Engineering Guangzhou510006 China Sun Yat-sen University School of Software Engineering Zhuhai Key Laboratory of Trusted Large Language Models Zhuhai519000 China

In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and collaboratively train models across multiple clients with different data distributions, model structures, task objectives, computational capabilities, and communication resources. This diversity leads to significant heterogeneity, which increases the complexity of model training. In this paper, we first outline the basic concepts of heterogeneous FL and summarize the research challenges in FL in terms of five aspects: data, model, task, device and communication. In addition, we explore how existing state-of-the-art approaches cope with the heterogeneity of FL, and categorize and review these approaches at three different levels: data-level, model-level, and architecture-level. Subsequently, the paper extensively discusses privacy-preserving strategies in heterogeneous FL environments. Finally, the paper discusses current open issues and directions for future research, aiming to promote the further development of heterogeneous FL. © 2015 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

MPNAS: Multimodal Sentiment Analysis Pruning via Neural Architecture Search

MPNAS: Multimodal Sentiment Analysis Pruning via Neural Arch...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Binyan Ren, Ao Zhang, Zihao Duan, Moming Liu, Duo Tan, Yujuan Zhong, Kan College of Computer Science Chongqing University Chongqing China School of Big Data Software & Engineering Chongqing University Chongqing China Institute of Data Science National University of Singapore Singapore

ISBN: (纸本)9798350368741

With the rapid development of social media, sentiment analysis from multimodal posts has garnered significant attention in recent years. However, the substantial size of these models impedes their deployment on resource-constrained embedded devices. Although pruning has been extensively studied to reduce the size of unimodal models, specific challenges remain for Multimodal Sentiment Analysis (MSA) models. First, existing techniques prune fixed original models into sparse models, while our findings indicate that different model architectures of identical size yield varying performance outcomes. Second, prior studies fail to explore the unique characteristics of MSA models, resulting in suboptimal pruning performance. To address these challenges, we propose MPNAS, a unified pruning framework via Neural Architecture Search (NAS) for MSA models. Specifically, we formulate pruning as a NAS problem and analyze MSA model characteristics to guide the subnet search. We conduct an initial coarse-grained NAS on the original model, expanding the search space slightly to identify suitable subnets that enhance pruning rates and accuracy. Subsequently, we refine coarse-grained subnets in a fine-grained NAS stage, where MSA model characteristics guide the search process. Extensive experiments on three representative datasets demonstrate the superiority of our approach over existing methods. © 2025 IEEE.

关键词： Multimodal Compression NAS

来源：评论

学校读者我要写书评

暂无评论

AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator 31

AI Hospital: Benchmarking Large Language Models in a Multi-a...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Fan, Zhihao Wei, Lai Tang, Jialong Chen, Wei Wang, Siyuan Wei, Zhongyu Xie, Jun Huang, Fei Zhou, Jingren Alibaba Inc. China School of Software Engineering Huazhong University of Science and Technology China University of Southern California United States School of Data Science Fudan University China

ISBN: (纸本)9798891761964

Artificial intelligence has significantly revolutionized healthcare, particularly through large language models (LLMs) that demonstrate superior performance in static medical question answering benchmarks. However, evaluating the potential of LLMs for real-world clinical applications remains challenging due to the intricate nature of doctor-patient interactions. To address this, we introduce AI Hospital, a multi-agent framework emulating dynamic medical interactions between Doctor as player and NPCs including Patient and Examiner. This setup allows for more practical assessments of LLMs in simulated clinical scenarios. We develop the Multi-View Medical Evaluation (MVME) benchmark, utilizing high-quality Chinese medical records and multiple evaluation strategies to quantify the performance of LLM-driven Doctor agents on symptom collection, examination recommendations, and diagnoses. Additionally, a dispute resolution collaborative mechanism is proposed to enhance medical interaction capabilities through iterative discussions. Despite improvements, current LLMs (including GPT-4) still exhibit significant performance gaps in multi-turn interactive scenarios compared to non-interactive scenarios. Our findings highlight the need for further research to bridge these gaps and improve LLMs' clinical decision-making capabilities. Our data, code, and experimental results are all open-sourced at https://***/LibertFan/AI_Hospital. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 1-14页

作者： Tan, Mingkui Chen, Guohao Wu, Jiaxiang Zhang, Yifan Chen, Yaofo Zhao, Peilin Niu, Shuaicheng South China University of Technology School of Software Engineering China Pazhou Laboratory Guangzhou China XVERSE China National University of Singapore School of Computing Singapore Tencent AI Lab China Nanyang Technological University College of Computing and Data Science Singapore

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two key challenges: 1) prior methods have to perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications;2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). To this end, we have proposed an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples for test-time entropy minimization. To alleviate forgetting, EATA introduces a Fisher regularizer estimated from test samples to constrain important model parameters from drastic changes. However, in EATA, the adopted entropy loss consistently assigns higher confidence to predictions even when the samples are underlying uncertain, leading to overconfident predictions that underestimate the data uncertainty. To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA. Specifically, we compare the divergence between predictions from the full network and its sub-networks to measure the reducible model uncertainty, on which we propose a test-time uncertainty reduction strategy with divergence minimization loss to encourage consistent predictions instead of overconfident ones. To further re-calibrate predicting confidence on different samples, we utilize the disagreement among predicted labels as an indicator of the data uncertainty. Based on this, we devise a min-max entropy

关键词： Semantic Segmentation

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

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

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：