检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Shaofei Ling, Rui Li, Hongyu Hui, Tianrui Tang, Zongheng Wei, Xiaoming Han, Jizhong Liu, Si School of Computer Science and Information Engineering Hefei University of Technology Hefei China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence Beihang University Beijing China Meituan Beijing China

ISBN: (纸本)157735897X

In this paper, we propose an Audio-Language-Referenced SAM 2 (AL-Ref-SAM 2) pipeline to explore the training-free paradigm for audio and language-referenced video object segmentation, namely AVS and RVOS tasks. The intuitive solution leverages GroundingDINO to identify the target object from a single frame and SAM 2 to segment the identified object throughout the video, which is less robust to spatiotemporal variations due to a lack of video context exploration. Thus, in our AL-Ref-SAM 2 pipeline, we propose a novel GPT-assisted Pivot Selection (GPT-PS) module to instruct GPT-4 to perform two-step temporal-spatial reasoning for sequentially selecting pivot frames and pivot boxes, thereby providing SAM 2 with a high-quality initial object prompt. Within GPT-PS, two task-specific Chain-of-Thought prompts are designed to unleash GPT’s temporal-spatial reasoning capacity by guiding GPT to make selections based on a comprehensive understanding of video and reference information. Furthermore, we propose a Language-Binded Reference Unification (LBRU) module to convert audio signals into language-formatted references, thereby unifying the formats of AVS and RVOS tasks in the same pipeline. Extensive experiments show that our training-free AL-Ref-SAM 2 pipeline achieves performances comparable to or even better than fully-supervised fine-tuning methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Physical Layer Security for Full-Duplex Symbiotic Radio with AN Generation and Forward Noise Suppression

引用

IEEE Transactions on communications 2024年第7期72卷 3905-3918页

作者： Jin, Chi Chang, Zheng Hu, Fengye Chen, Hsiao-Hwa Hamalainen, Timo University of Jyväskylä Faculty of Information Technology Jyväskylä40014 Finland University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Jilin University College of Communication Engineering Changchun130012 China National Cheng Kung University Department of Engineering Science Tainan70101 Taiwan

Due to the constraints on power supply and limited encryption capability, data security based on physical layer security (PLS) techniques in backscatter communications has attracted a lot of attention. In this work, we propose to enhance PLS in a full-duplex symbiotic radio (FDSR) system with a proactive eavesdropper, which may overhear the information and interfere legitimate communications simultaneously by emitting attack signals. To deal with the eavesdroppers, we propose a security strategy based on pseudo-decoding and artificial noise (AN) injection to ensure the performance of legitimate communications through forward noise suppression. A novel AN signal generation scheme is proposed using a pseudo-decoding method, where AN signal is superimposed on data signal to safeguard the legitimate channel. The phase control in the forward noise suppression scheme and the power allocation between AN and data signals are optimized to maximize security throughput. The formulated problem can be solved via problem decomposition and alternate optimization algorithms. Simulation results demonstrate the superiority of the proposed scheme in terms of security throughput and attack mitigation performance. 0090-6778 © 2024 IEEE.

关键词： Backscattering

来源：评论

学校读者我要写书评

暂无评论

STGAT: Spatial-Temporal Graph Attention Networks for Traffic Flow Prediction 29

STGAT: Spatial-Temporal Graph Attention Networks for Traffic...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Ruan, Chang Tan, Xianchao Liao, Zhuofan Kuang, Lidan Li, Ping Changsha University of Science & Technology School of Computer and Communication Engineering Changsha China

ISBN: (纸本)9798350330717

Accurate traffic flow prediction is of great importance in Intelligent Transportation System (ITS) for improving traffic efficiency, reducing congestion and so on. However, due to the complex spatial and temporal dependencies, achieving the accurate prediction is challenging. Traditional attention-based networks for traffic flow prediction typically use sine and cosine functions to do position encoding, which fail to capture the spatial and temporal dependencies and do not contain the graph structure information. In this paper, we propose a novel model named Spatial-Temporal Graph ATtention networks (STGAT), which leverages structure-aware self-attention mechanism to predict future traffic flow. The model introduces temporal multi-head self-attention modules, and designs spatial multi-head graph self-attention modules with structure-aware graph filters to extract more temporal and spatial information. Besides, our model adopts temporal and spatial position embedding layers to capture the spatial-temporal dependencies in traffic flow data. Experimental results show that STGAT shows better prediction performance than the state-of-art models on three real-world datasets PEMS04, PEMS07 and PEMS08. For example, we observe up to 10.38% improvement in terms of Mean Absolute Percentage Error (MAPE) compared with the well-known model ASTGNN. © 2023 IEEE.

关键词： graph attention network self-attention spatial-temporal Traffic flow prediction

来源：评论

学校读者我要写书评

暂无评论

A Bloom Filter-based Algorithm for Fast Detection of Common Variables

A Bloom Filter-based Algorithm for Fast Detection of Common ...

引用

2023 International Conference on Frontiers of Robotics and Software engineering, FRSE 2023

作者： Wang, Zhen Liu, Kang Xu, Chao Changsha University of Science & Technology School of Computer and Communication Engineering Changsha China

ISBN: (纸本)9798350301113

Satisfiability problem has significant applications in many fields, such as software verification and Robot path planning. Researchers have proposed many reduction rules for the conjunctive normal form formula, some of which need to detect the common variables in the formula. Even though these reduction rules only take polynomial time, when the time complexity of the rules exceeds O(n3), recursive inprocessing detections with in each branch are time-consuming. Due to this, the Bloom Common Variable Detection Algorithm (CVDA-Bloom) is proposed, which is based on the Bloom filter concept and hash clause detection technique. The hash method is utilized as a filter to detect common variables, while the Bloom filter concept is used to reduce the false positive rate in the hash process. The experiments used 85 SAT instances from 7 series of the SAT2021 Competition. The results show that compared to the pure hash clause detection technique, the clause pass rate of the CVDA-Bloom algorithm decreases by 21.01% on average, and the false positive rate decreases by 66.57% on average. Furthermore, disabling the Bloom hash clause detection technique will increase the time by 260.03%. When used with the actual reduction rules, the CVDA-Bloom algorithm effectively lowers the number of clauses that must be checked explicitly, which can lower the performance overhead and speed up the detection. © 2023 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Deep Boosting Robustness of DNN-Based Image Watermarking via Dbmark

Deep Boosting Robustness of DNN-Based Image Watermarking via...

引用

2023 International Conference on Culture-Oriented science and technology, CoST 2023

作者： Ye, Guanhui Gao, Jiashi Yin, Bo Xie, Wei Wei, Xuetao Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China School of Journalism and Communication Hunan University Changsha China

ISBN: (纸本)9798350357998

Image watermarking is a technique for hiding information into images that can withstand distortions while requiring the encoded image to be perceptually identical to the original image. Recent work based on deep neural networks (DNN) has achieved impressive progression in digital watermarking. Higher robustness under various distortions is the eternal pursuit of digital image watermarking approaches. In this paper, we propose DB MARK, a novel end-to-end digital image watermarking framework to deep boost the robustness of DNN-based image watermarking. The key novelty is the synergy of invertible neural networks (INN) and effective watermark features generation. The framework generates watermark features with redundancy and error correction ability through the effective neural network based message processor, synergized with the powerful information embedding and extraction abilities of INN to achieve higher robustness and invisibility. The powerful learning ability of neural networks enables the message processor to adapt to various distortions. In addition, we propose to embed the watermark information in the discrete wavelet transform (DWT) domain and design low-low (LL) sub-band loss to enhance invisibility. Extensive experiment results demonstrate the superiority of the proposed framework compared with the state-of-the-art ones under various distortions such as dropout, cropout, crop, Gaussian filter, and JPEG compression. © 2023 IEEE.

关键词： Image watermarking

来源：评论

学校读者我要写书评

暂无评论

A Knowledge Graph-based Clustering Approach for Drug Side Effects Prediction

A Knowledge Graph-based Clustering Approach for Drug Side Ef...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zheng, Ying Xu, ShiBo Changsha University of Science & Technology School of Computer & Communication Engineering Changsha China

ISBN: (纸本)9798350337488

Research on drug side effects contributes to reducing health risks for patients and decreasing drug development costs. In recent years, machine learning methods have emerged as prominent tools to support analyzing and predicting drug side effects. In this paper, we propose a clustering model based on knowledge graph embedding (GEBC) to predict potential side effects. GEBC integrates various drug features into a heterogeneous network, then mines the underlying relationship of nodes in network using Node2vec algorithm. Finally, GEBC clusters the node embeddings by Gaussian Mixture Model, and builds a Bayesian probability prediction model. GEBC achieves 0.4343, 0.442, 0.411 AUPR score on three benchmark datasets, respectively. © 2023 IEEE.

关键词： clustering knowledge graph embedding side effect

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-based unknown reference tracking control of HMASs with nonidentical communication delays

引用

science China(Information sciences) 2023年第7期66卷 46-57页

作者： Yong XU Zheng-Guang WU Wei-Wei CHE Deyuan MENG School of Automation Beijing Institute of Technology Institute of Cyber-Systems and Control Zhejiang University College of Mathematics and Computer Science Zhejiang Normal University Department of Automation Qingdao University School of Automation Science and Electrical Engineering Beihang University(BUAA)

This paper focuses on the optimal output synchronization control problem of heterogeneous multiagent systems(HMASs) subject to nonidentical communication delays by a reinforcement learning *** with existing studies assuming that the precise model of the leader is globally or distributively accessible to all or some of the followers, the leader's precise dynamical model is entirely inaccessible to all the followers in this paper. A data-based learning algorithm is first proposed to reconstruct the leader's unknown system matrix online. A distributed predictor subject to communication delays is further devised to estimate the leader's state, where interaction delays are allowed to be nonidentical. Then, a learning-based local controller, together with a discounted performance function, is projected to reach the optimal output synchronization. Bellman equations and game algebraic Riccati equations are constructed to learn the optimal solution by developing a model-based reinforcement learning(RL) algorithm online without solving regulator equations, which is followed by a model-free off-policy RL algorithm to relax the requirement of all agents' dynamics faced by the model-based RL algorithm. The optimal tracking control of HMASs subject to unknown leader dynamics and communication delays is shown to be solvable under the proposed RL algorithms. Finally, the effectiveness of theoretical analysis is verified by numerical simulations.

关键词： heterogeneous multiagent systems HMAS reinforcement learning RL optimal output synchronization communication delays

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting Based on Dual Dynamic Predictive Filtering and Fast Fourier Convolution

Image Inpainting Based on Dual Dynamic Predictive Filtering ...

引用

2023 International Conference on New Trends in Computational Intelligence, NTCI 2023

作者： Xie, Zhengrong Zhang, Zhaoyuan Zhang, Jianming School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China

ISBN: (纸本)9798350380859

Despite outstanding performances of the existing image inpainting methods in restoring corrupted images, they often generate images with artifacts or missing details. Predictive filtering is a widely used image restoration technique which can preserve local structures and avoid artifacts, but it cannot fill large missing areas. Convolutional neural networks are suitable for large missing areas, but it is difficult to restore fine details. Therefore, we treat image inpainting as a filtering task, and propose a novel image inpainting method consisting of two networks, namely the Attention-Enhanced Kernel Predictive Network (AE-KPNet) and the Deep Generative Network (DGNet). The two parallel networks are linked, and DGNet provides features to AE-KPNet, while AE-KPNet trains dual dynamic predictive filtering kernels for DGNet. To address the issue of large missing areas, we introduce fast Fourier convolution into DGNet, and the operation in the frequency domain expands the spatial receptive field. We evaluate our model on three public datasets, CelebA, Places2, and Paris StreetView. Through quantitative and qualitative experiments, the results show that our method achieves the performance of state-of-the-art methods. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Provably Secure Lightweight Key Agreement Protocol for Wireless Body Area Networks in Healthcare System

引用

IEEE Transactions on Industrial Informatics 2023年第2期19卷 1683-1690页

作者： Zia, Maryam Obaidat, Mohammad S. Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Chaudhry, Shehzad Ashraf Comsats University Islamabad Department of Computer Science Sahiwal57000 Pakistan University of Jordan King Abdullah Ii School of Information Technology Amman11942 Jordan University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Amity University UP Noida201301 India National Yunlin University of Science and Technology Future Technology Research Center Yunlin64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan Abu Dhabi University Department of Computer Science and Information Technology College of Engineering Abu Dhabi United Arab Emirates Nisantasi University Department of Computer Engineering Faculty of Engineering and Architecture Istanbul34398 Turkey

Wireless Body Area Network (WBAN) is a vital application of the Internet of Things (IoT) that plays a significant role in gathering a patient's healthcare information. This collected data helps special professionals like doctors or physicians analyze patients' health status to cure different diseases. However, collecting such information from an insecure channel can be threatening due to the potential security threats. Therefore, it is crucial to secure this sensitive information. This article proposes a secure and lightweight authentication protocol for WBAN. The devised protocol is scalable, secure, and lightweight compared to various relevant competing protocols. The informal security analysis shows that the designed protocol is lightweight, secure, and efficient in resisting various major attacks. The performance analysis demonstrates our protocol's supremacy over various competing protocols in terms of computation and communication costs, inducing efficiency of 20.3% and 12.3%, respectively. Moreover, the practical performance of the designed protocol from the network point of view is measured using the widely recognized NS3 simulation tool. © 2005-2012 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Face Forgery Detection Based on Fine-Grained Clues and Noise Inconsistency

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 144-158页

作者： Zhang, Dengyong He, Ruiyi Liao, Xin Li, Feng Chen, Jiaxin Yang, Gaobo Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation the School of Computer and Communication Engineering Changsha410114 China Hunan University Changsha410082 China

Deepfake detection has gained increasing research attention in media forensics, and a variety of works have been produced. However, subtle artifacts might be eliminated by compression, and the convolutional neural networks (CNNs)-based detectors are invalidated for fake face images with compression. In this work, we propose a two-stream network for deepfake detection. We observed that high-frequency noise features and spatial features are inherently complementary to each other. Thus, both spatial features and high-frequency noise features are exploited for face forgery detection. Specifically, we design a double-frequency transformer module (DFTM) to guide the learning of spatial features from local artifact regions. To effectively fuse spatial features and high-frequency noise features, a dual-domain attention fusion module (DDAFM) is designed. We also introduce a local relationship constraint loss, which requires only image-level labels, for model training. We evaluate the proposed approach on five large-scale benchmark datasets, and extensive experimental results demonstrate the proposed approach outperforms most SOTA works. © 2024 IEEE.

关键词： Frequency domain analysis

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：