检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ma, Jie Gao, Zhitao Chai, Qi Liu, Jun Wang, Pinghui Tao, Jing Su, Zhou Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Guangdong Guangzhou510000 China

Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. Moreover, current datasets may not effectively diagnose these methods. To address these challenges, we first introduce a novel dataset, FortisAVQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-AVQA dataset and (2) introducing distribution shifts across questions. The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions. Second, we introduce a robust Multimodal Audio-Visual Epistemic Network (MAVEN) that leverages a multifaceted cycle collaborative debiasing strategy to mitigate bias learning. Experimental results demonstrate that our architecture achieves state-of-the-art performance on FortisAVQA, with a notable improvement of 7.81%. Extensive ablation studies on both datasets validate the effectiveness of our debiasing components. Additionally, our evaluation reveals the limited robustness of existing multimodal QA methods. We also verify the plug-and-play capability of our strategy by integrating it with various baseline models across both datasets. Our dataset and code are available at https://***/reml-group/fortisavqa. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Layer-Wise Learning Rate Optimization for Task-Dependent Fine-Tuning of Pre-Trained Models: An Evolutionary Approach

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第4期4卷 1-23页

作者： Bu, Chenyang Liu, Yuxin Huang, Manzong Shao, Jianxuan Ji, Shengwei Luo, Wenjian Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Artificial Intelligence and Big Data Hefei University Hefei China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

The superior performance of large-scale pre-Trained models, such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformer (GPT), has received increasing attention in both academic and industrial research and has become one of the current research hotspots. A pre-Trained model refers to a model trained on large-scale unlabeled data, whose purpose is to learn general language representation or features for fine-Tuning or transfer learning in subsequent tasks. After pre-Training is complete, a small amount of labeled data can be used to fine-Tune the model for a specific task or domain. This two-stage method of "pre-Training+fine-Tuning"has achieved advanced results in natural language processing (NLP) tasks. Despite widespread adoption, existing fixed fine-Tuning schemes that adapt well to one NLP task may perform inconsistently on other NLP tasks given that different tasks have different latent semantic structures. In this article, we explore the effectiveness of automatic fine-Tuning pattern search for layer-wise learning rates from an evolutionary optimization perspective. Our goal is to use evolutionary algorithms to search for better task-dependent fine-Tuning patterns for specific NLP tasks than typical fixed fine-Tuning patterns. Experimental results on two real-world language benchmarks and three advanced pre-Training language models show the effectiveness and generality of the proposed framework. © 2024 held by the owner/author(s).

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improved lattice-based CCA2-secure PKE in the standard model

引用

science China(Information sciences) 2020年第8期63卷 147-168页

作者： Jiang ZHANG Yu YU Shuqin FAN Zhenfeng ZHANG State Key Laboratory of Cryptology Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Jinan University Department of Computer Science and Engineering Shanghai Jiao Tong University Trusted Computing and Information Assurance Laboratory Institute of SoftwareChinese Academy of Sciences

Based on the identity-based encryption(IBE) from lattices by Agrawal et al.(Eurocrypt’10),Micciancio and Peikert(Eurocrypt’12) presented a CCA1-secure public-key encryption(PKE), which has the best known efficiency in the standard model and can be used to obtain a CCA2-secure PKE from lattices by using the generic BCHK transform(SIAM J Comput, 2006) with a cost of introducing extra overheads to both computation and storage for the use of other primitives such as signatures and commitments. In this paper, we propose a more efficient standard model CCA2-secure PKE from lattices by carefully combining a different message encoding(which encodes the message into the most significant bits of the LWE’s "secret term") with several nice algebraic properties of the tag-based lattice trapdoor and the LWE problem(such as unique witness and additive homomorphism). Compared to the best known lattice-based CCA1-secure PKE in the standard model due to Micciancio and Peikert(Eurocrypt’12), we not only directly achieve the CCA2-security without using any generic transform(and thus do not use signatures or commitments), but also reduce the noise parameter roughly by a factor of 3. This improvement makes our CCA2-secure PKE more efficient in terms of both computation and storage. In particular, when encrypting a 256-bit(respectively,512-bit) message at 128-bit(respectively, 256-bit) security, the ciphertext size of our CCA2-secure PKE is even 33%–44%(respectively, 36%–46%) smaller than that of their CCA1-secure PKE.

关键词： lattice public-key encryption chosen ciphertext security standard model

来源：评论

学校读者我要写书评

暂无评论

Wireless Hallucination in Generative AI-enabled Communications: Concepts, Issues, and Solutions

arXiv

引用

arXiv 2025年

作者： Wang, Xudong Wang, Jiacheng Feng, Lei Niyato, Dusit Zhang, Ruichen Kang, Jiawen Xiong, Zehui Du, Hongyang Mao, Shiwen State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China College of Computing and Data Science Nanyang Technological University Singapore School of Automation Guangdong University of Technology Guangzhou510006 China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong Department of Electrical and Computer Engineering Auburn University Auburn United States

Generative AI (GenAI) is driving the intelligence of wireless communications. Due to data limitations, random generation, and dynamic environments, GenAI may generate channel information or optimization strategies that violate physical laws or deviate from actual real-world requirements. We refer to this phenomenon as wireless hallucination, which results in invalid channel information, spectrum wastage, and low communication reliability but remains underexplored. To address this gap, this article provides a comprehensive concept of wireless hallucinations in GenAI-driven communications, focusing on hallucination mitigation. Specifically, we first introduce the fundamental, analyze its causes based on the GenAI workflow, and propose mitigation solutions at the data, model, and post-generation levels. Then, we systematically examines representative hallucination scenarios in GenAI-enabled communications and their corresponding solutions. Finally, we propose a novel integrated mitigation solution for GenAI-based channel estimation. At the data level, we establish a channel estimation hallucination dataset and employ generative adversarial networks (GANs)-based data augmentation. Additionally, we incorporate attention mechanisms and large language models (LLMs) to enhance both training and inference performance. Experimental results demonstrate that the proposed hybrid solutions reduce the normalized mean square error (NMSE) by 0.19, effectively reducing wireless hallucinations. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant quantum algorithms for quantum molecular systems: A survey

arXiv

引用

arXiv 2025年

作者： Zhang, Yukun Zhang, Xiaoming Sun, Jinzhao Lin, Heng Huang, Yifei Lv, Dingshun Yuan, Xiao Center on Frontiers of Computing Studies Peking University Beijing100871 China School of Computer Science Peking University Beijing100871 China South China Normal University Guangzhou510006 China Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials Guangdong-Hong Kong Joint Laboratory of Quantum Matter South China Normal University Guangzhou510006 China Clarendon Laboratory University of Oxford Parks Road OxfordOX1 3PU United Kingdom State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Tsinghua University Beijing100084 China ByteDance Research Zhonghang Plaza No. 43 North 3rd Ring West Road Haidian District Beijing100089 China

Solving quantum molecular systems presents a significant challenge for classical computation. The advent of early fault-tolerant quantum computing (EFTQC) devices offers a promising avenue to address these challenges, leveraging advanced quantum algorithms with reduced hardware requirements. This review surveys the latest developments in EFTQC and fully fault-tolerant quantum computing (FFTQC) algorithms for quantum molecular systems, covering encoding schemes, advanced Hamiltonian simulation techniques, and ground-state energy estimation methods. We highlight recent progress in overcoming practical barriers, such as reducing circuit depth and minimizing the use of ancillary qubits. Special attention is given to the potential quantum advantages achievable through these algorithms, as well as the limitations imposed by dequantization and classical simulation techniques. The review concludes with a discussion of future directions, emphasizing the need for optimized algorithms and experimental validation to bridge the gap between theoretical developments and practical implementation in EFTQC and FFTQC for quantum molecular systems. © 2025, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

CATIRI:An Efficient Method for Content-and-Text Based Image Retrieval

引用

Journal of Computer science & Technology 2019年第2期34卷 287-304页

作者： Mengqi Zeng Bin Yao Zhi-Jie Wang Yanyan Shen Feifei Li Jianfeng Zhang Hao Lin Minyi Guo Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Data and Computer Science Sun Yat-sen University Guangzhou 510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou 510006 China National Engineering Laboratory for Big Data Analysis and Applications Beijing 100871 China School of Computing University of Utah Salt Lake City 84112 U.S.A. Alibaba Group Hangzhou 311121 China

The combination of visual and textual information in image retrieval remarkably alleviates the semantic gap of traditional image retrieval methods,and thus it has attracted much attention *** retrieval based on such a combination is usually called the content-and-text based image retrieval(CTBIR).Nevertheless,existing studies in CTBIR mainly make efforts on improving the retrieval *** the best of our knowledge,little attention has been focused on how to enhance the retrieval ***,image data is widespread and expanding rapidly in our daily ***,it is important and interesting to investigate the retrieval *** this end,this paper presents an efficient image retrieval method named CATIRI(content-and-text based image retrieval using indexing).CATIRI follows a three-phase solution framework that develops a new indexing structure called *** MHIM-tree seamlessly integrates several elements including Manhattan Hashing,Inverted index,and *** use our MHIM-tree wisely in the query,we present a set of important metrics and reveal their inherent *** on them,we develop a top-k query algorithm for *** results based on benchmark image datasets demonstrate that CATIRI outperforms the competitors by an order of magnitude.

关键词： image retrieval text-and-visual feature indexing top-k

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotional Talking Face Generation based on Action Units

引用

IEEE Transactions on Circuits and Systems for Video Technology 2024年第5期35卷 4026-4038页

作者： Lyu, Jiayi Lan, Xing Hu, Guohong Jiang, Hanyu Gan, Wei Wang, Jinbao Xue, Jian University of Chinese Academy of Sciences School of Engineering Science Beijing100049 China Peng Cheng Laboratory Shenzhen518055 China Shenzhen University National Engineering Laboratory for Big Data System Computing Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Talking face generation focuses on creating natural facial animations that align with the provided text or audio input. Current methods in this field primarily rely on facial landmarks to convey emotional changes. However, spatial key-points are valuable, yet limited in capturing the intricate dynamics and subtle nuances of emotional expressions due to their restricted spatial coverage. Consequently, this reliance on sparse landmarks can result in decreased accuracy and visual quality, especially when representing complex emotional states. To address this issue, we propose a novel method called Emotional Talking with Action Unit (ETAU), which seamlessly integrates facial Action Units (AUs) into the generation process. Unlike previous works that solely rely on facial landmarks, ETAU employs both Action Units and landmarks to comprehensively represent facial expressions through interpretable representations. Our method provides a detailed and dynamic representation of emotions by capturing the complex interactions among facial muscle movements. Moreover, ETAU adopts a multi-modal strategy by seamlessly integrating emotion prompts, driving videos, and target images, and by leveraging various input data effectively, it generates highly realistic and emotional talking-face videos. Through extensive evaluations across multiple datasets, including MEAD, LRW, GRID and HDTF, ETAU outperforms previous methods, showcasing its superior ability to generate high-quality, expressive talking faces with improved visual fidelity and synchronization. Moreover, ETAU exhibits a significant improvement on the emotion accuracy of the generated results, reaching an impressive average accuracy of 84% on the MEAD dataset. © 1991-2012 IEEE.

关键词： Faces Face recognition Head Accuracy Mouth Feature extraction Lips Facial muscles Facial animation Diffusion models

来源：评论

学校读者我要写书评

暂无评论

DSAFF-Net:A Backbone Network Based on Mask R-CNN for Small Object Detection

引用

Computers, Materials & Continua 2023年第2期74卷 3405-3419页

作者： Jian Peng Yifang Zhao Dengyong Zhang Feng Li Arun Kumar Sangaiah Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computing Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India

Recently,object detection based on convolutional neural networks(CNNs)has developed *** backbone networks for basic feature extraction are an important component of the whole detection ***,we present a new feature extraction strategy in this paper,which name is *** this strategy,we design:1)a sandwich attention feature fusion module(SAFF module).Its purpose is to enhance the semantic information of shallow features and resolution of deep features,which is beneficial to small object detection after feature fusion.2)to add a new stage called D-block to alleviate the disadvantages of decreasing spatial resolution when the pooling layer increases the receptive *** method proposed in the new stage replaces the original method of obtaining the P6 feature map and uses the result as the input of the regional proposal network(RPN).In the experimental phase,we use the new strategy to extract *** experiment takes the public dataset of Microsoft Common Objects in Context(MS COCO)object detection and the dataset of Corona Virus Disease 2019(COVID-19)image classification as the experimental object *** results show that the average recognition accuracy of COVID-19 in the classification dataset is improved to 98.163%,and small object detection in object detection tasks is improved by 4.0%.

关键词： Small object detection classification RPN MS COCO COVID-19

来源：评论

学校读者我要写书评

暂无评论

Adaptive disentangled target representation for unsupervised domain adaptation in remote sensing segmentation

引用

engineering Applications of Artificial Intelligence 2025年 156卷

作者： Runuo Lu Shoubin Dong Jianxin Jia Xusheng Wang Kai Liu Jinsong Chen Shanxin Guo Xiaorou Zheng Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou 510641 China Department of Photogrammetry and Remote Sensing Finnish Geospatial Research Institute Espoo FI-02150 Finland Center for Geo-Spatial Information Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application Shenzhen 518055 China

Due to the significant differences between the source and target domains, semantic segmentation models for remote sensing images trained on the source domain often struggle to generalize effectively to new target domains, leading to performance degradation. Most solutions disentangle features into domain-invariant features shared by both domains and domain-specific features unique to each domain, relying primarily on the domain-invariant features for model construction and inference. However, during this process, critical domain-specific features as essential information are often discarded as noise, leading to a reduction in segmentation accuracy. To address these issues, this study proposes an unsupervised domain adaptation, called ChameleonRS 1 . ChameleonRS separates the domain-invariant features and the domain-specific features by disentanglement learning, and introduces a multi-level feature alignment module to enhance the representation of domain-invariant features. More importantly, it aligns predictions based on domain-invariant features with those based on fused invariant and specific features using contrastive learning, effectively capturing target-specific features. This study explores two cross-domain semantic segmentation tasks: (I) Geographic location variation. (II) Geographic location and imaging mode variation. Results show that under setting (I), ChameleonRS outperforms the state-of-the-art method by 4.79% in Intersection over Union (IoU) and 6.51% in the F1 score. Under setting (II), it achieves improvements of 4.46% and 4.82% in IoU and F1 score. Results demonstrate the superiority and adaptability of ChameleonRS under varying geographical and imaging conditions, effectively mitigating the generalization issues caused by distribution differences, and thereby promoting the development and application of remote sensing technologies in practical scenarios.

关键词：

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：