检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Yangtao Chen, Zixuan Yin, Junhui Huo, Jing Tian, Pinzhuo Shi, Jieqi Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Suzhou China School of Computer Engineering and Science Shanghai University Shanghai China

Robots’ ability to follow language instructions and execute diverse 3D manipulation tasks is vital in robot learning. Traditional imitation learning-based methods perform well on seen tasks but struggle with novel, unseen ones due to variability. Recent approaches leverage large foundation models to assist in understanding novel tasks, thereby mitigating this issue. However, these methods lack a task-specific learning process, which is essential for an accurate understanding of 3D environments, often leading to execution failures. In this paper, we introduce GravMAD, a sub-goal-driven, language-conditioned action diffusion framework that combines the strengths of imitation learning and foundation models. Our approach breaks tasks into sub-goals based on language instructions, allowing auxiliary guidance during both training and inference. During training, we introduce Sub-goal keypose Discovery to identify key sub-goals from demonstrations. Inference differs from training, as there are no demonstrations available, so we use pre-trained foundation models to bridge the gap and identify sub-goals for the current task. In both phases, GravMaps are generated from sub-goals, providing GravMAD with more flexible 3D spatial guidance compared to fixed 3D positions. Empirical evaluations on RLBench show that GravMAD significantly outperforms state-of-the-art methods, with a 28.63% improvement on novel tasks and a 13.36% gain on tasks encountered during training. Evaluations on real-world robotic tasks further show that GravMAD can reason about real-world tasks, associate them with relevant visual information, and generalize to novel tasks. These results demonstrate GravMAD’s strong multi-task learning and generalization in 3D manipulation. Video demonstrations are available at: https://***. © 2024, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Tkstagnet: A Top-K Spatio-Temporal Attention Gating Network for Air Pollution Prediction

SSRN

引用

SSRN 2024年

作者： Zhou, Hongliang Mao, Yingchi Li, Xiang Rong, Yi Chen, Ling Yin, Changkui College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Nanjing China

Accurate air pollution prediction is of great significance for human health, travel and environmental management. As an emerging artificial intelligence technology, Transformer has already shown tremendous potential in air pollution prediction. Unfortunately, existing Transformer-based methods are challenging to accurately predict air pollution due to two limitations: 1) they neglect irrelevant spatial and temporal neighbors (e.g., neighboring sensors and timesteps) when modeling spatio-temporal correlations, and 2) they lack an adaptive mechanism to mine different effects caused by various external factors (e.g., meteorological conditions). Jointly taking these limitations into account, we propose a novel Transformer-based architecture for air pollution prediction, named Top-K Spatio-Temporal Attention Gating Network (TKSTAGNet). In this architecture, to effectively extract spatio-temporal correlations, we first design a TopKpooling Spatial Attention (TopK-SA) and a TopKpooling Temporal Attention (TopK-TA). In TopK-SA, the TopKpooling mechanism is introduced into spatial attention to filter out irrelevant spatial neighbors, accurately capturing spatial dependencies. In TopK-TA, the TopKpooling mechanism is integrated with temporal attention to identify and exclude irrelevant temporal neighbors, precisely extracting temporal dependencies. To adaptively fuse various external factors, a gating fusion module is then proposed. We conduct experiments on two real-world air pollution datasets from urban regions in Beijing and Shanghai, respectively. Experimental results demonstrate that TKSTAGNet outperforms state-of-the-art baselines in prediction precision and fitting the variation trends of air pollution. © 2024, The Authors. All rights reserved.

关键词： Air pollution

来源：评论

学校读者我要写书评

暂无评论

HyperDiff: Masked Diffusion Model with High-efficient Transformer for Hyperspectral Image Cross-Scene Classification

HyperDiff: Masked Diffusion Model with High-efficient Transf...

引用

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

作者： Zhang, Pei Wang, Dong Wu, Chanyue Yang, Jing Kang, Lei Bai, Zongwen Li, Ying Shen, Qiang School of Computer Science Northwestern Polytechnical University Xi'an China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan'an University Yan'an China School of Automation and Software Engineering Shanxi University Taiyuan China Qingdao Topscomm Communication Co. Ltd. Qingdao China Department of Computer Science Aberystwyth University Aberystwyth United Kingdom

ISBN: (纸本)9798350368741

Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of HSI representations remains limited, mainly due to class label imbalance. This paper introduces a dual-stage learning framework based on transfer learning to enhance classification accuracy in the TD. The framework includes a self-supervised learning stage and a supervised fine-tuning stage. The self-supervised stage focuses on learning robust representations by leveraging inherent structures within HSI data, while the fine-tuning stage uses training labels to extract semantic information. A masked diffusion model predicts masked tokens from unmasked ones, capturing both high-level structures and fine details in HSI data. An efficient spatiospectral Transformer, which removes self-attention from the decoder, is proposed to enhance the self-supervised process. This design allows mask tokens to obtain information from visible tokens without interacting with each other, reducing sequence length and computational costs. By decoding each mask token conditionally independently, only a subset of masked tokens is processed. Extensive experiments on two public HSI datasets demonstrate that the proposed method outperforms state-of-the-art techniques. © 2025 IEEE.

关键词： Cross-scene classification Diffusion model Hyperspectral image Transformer

来源：评论

学校读者我要写书评

暂无评论

A Crowdsourcing Digital Forensics Platform for IoT Environments Powered by Blockchain

A Crowdsourcing Digital Forensics Platform for IoT Environme...

引用

IEEE International Conference on Communications (ICC)

作者： Yaqing Zhang Xiao Fu Bin Luo Xiaojiang Du State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Digital forensics is a security research field that has evolved with the advancement of digital technologies, such as computer and network technology. With the emergence of complex forensic environments, such as those found in the IoT and cloud computing, investigators are required to possess higher technical capabilities and knowledge. Completing digital forensics tasks more effectively has become a challenge. Therefore, this paper proposes a blockchain-based collaborative crowdsourcing platform for digital forensics. Through collaborating on the crowdsourcing platform, professional investigators can enhance the supervision of the digital forensics process, reduce the difficulty of digital forensics tasks, and improve their quality. In addition, we introduce blockchain technology to maintain the credibility of the investigation process. We have developed a smart contract and conducted experiments based on Ethereum. The experimental results show that our solution is feasible.

关键词： Crowdsourcing Technological innovation Digital forensics Smart contracts Collaboration Prediction algorithms Blockchains

来源：评论

学校读者我要写书评

暂无评论

A theoretical analysis of backdoor poisoning attacks in convolutional neural networks 24

A theoretical analysis of backdoor poisoning attacks in conv...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Boqi Li Weiwei Liu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

The rising threat of backdoor poisoning attacks (BPAs) on Deep Neural Networks (DNNs) has become a significant concern in recent years. In such attacks, the adversaries strategically target a specific class and generate a poisoned training set. The neural network (NN), well-trained on the poisoned training set, is able to predict any input with the trigger pattern as the targeted label, while maintaining accurate outputs for clean inputs. However, why the BPAs work remains less explored. To fill this gap, we employ a dirty-label attack and conduct a detailed analysis of BPAs in a two-layer convolutional neural network. We provide theoretical insights and results on the effectiveness of BPAs. Our experimental results on two real-world datasets validate our theoretical findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expression-Aware Masking and Progressive Decoupling for Cross-Database Facial Expression Recognition

Expression-Aware Masking and Progressive Decoupling for Cros...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Tao Zhong Xiaole Xian Zihan Wang Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Cross-database facial expression recognition (CD-FER) has been widely studied due to its promising applicability in real-life situations, while the generalization performance is the main concern in this task. For improving cross-database generalization, current works frequently resort to masked auto encoder (MAE) to learn the expression representation in an unsupervised manner, and disentanglement of expression and domain features. (i) For MAE, current algorithms mainly employ random masking, and leverage the reconstruction of these masked regions to enable networks to learn the expression representation. However, these masked regions are expression-irrelevant, can not well reflect the characteristics of expression, thus are not efficient enough in representation learning. To this end, we propose an expression-aware masking in MAE to improve the learning efficiency of expression representation, by guiding MAE to mask out expression-aware regions during training. (ii) For disentanglement of expression and domain features, current algorithms realize it mainly in the deep layers. However, the coupling of these features in the shallow layers are rarely concerned, which may largely affect the disentanglement performance in deep layers. Thus, we propose a progressive decoupler to disentangle these features block by block, to use the feature disentanglement in shallow layers to facilitate that in deep layers. Extensive quantitative and qualitative results on multiple expression datasets show that our method can largely outperform the state of the arts in terms of cross-database generalization performance.

关键词： Training Representation learning Couplings Face recognition Gesture recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Intelligent Surface-Aided Covert Communications: A Multi-User Scenario

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Hu, Xiaoyan Zhao, Pengze Xiao, Han Zheng, Tong-Xing Wang, Wenjie Yang, Kun Xi'an Jiaotong University School of Information and Communications Engineering Xi'an710049 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Nanjing University State Key Laboratory of Novel Software Technology Nanjing210008 China School of Intelligent Software and Engineering Suzhou215163 China University of Essex School of Computer Science and Electronic Engineering United Kingdom

This paper explores a multi-user covert communication scenario with the assistance of a reconfigurable intelligent surface (RIS). Except a covert user monitored by the warden, there are multiple public users existing in the service area. For the purpose of evaluating the efficacy of the covert communication system, a covert constraint is derived measuring the minimum detection error probability of the warden through the Kullback-Leibler (KL) divergence. Then an optimization problem is formulated to maximize the convert rate, while ensuring the constraints of covertness, transmit power and quality of service (QoS) for public users. A two-step iterative algorithm jointly designing the active and passive beamforming, is put forth to efficiently resolve this non-convex optimization problem. Additionally, the numerical results clearly demonstrate that the proposed RIS-assisted scheme can significantly enhance the covert communication performance on the premise of guaranteeing the public communication performance of the system. © 1967-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Sequential Kernel Goodness-of-fit testing 24

Sequential Kernel Goodness-of-fit testing

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Zhengyu Zhou Weiwei Liu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Goodness-of-fit testing, a classical statistical tool, has been extensively explored in the batch setting, where the sample size is predetermined. However, practitioners often prefer methods that adapt to the complexity of a problem rather than fixing the sample size beforehand. Classical batch tests are generally unsuitable for streaming data, as valid inference after data peeking requires multiple testing corrections, resulting in reduced statistical power. To address this issue, we delve into the design of consistent sequential goodness-of-fit tests. Following the principle of testing by betting, we reframe this task as selecting a sequence of payoff functions that maximize the wealth of a fictitious bettor, betting against the null in a repeated game. We conduct experiments to demonstrate the adaptability of our sequential test across varying difficulty levels of problems while maintaining control over type-I errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lifeline Consensus: Protect Small-scale Blockchain From Typical Attacks

Lifeline Consensus: Protect Small-scale Blockchain From Typi...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Kundu Chen Jie Luo State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Haidian District Beijing China

Blockchain is a distributed network system known for its anonymity, security, and decentralized nature. While blockchains with robust networks such as Bitcoin and Ethereum are proving immutable to attacks, many others are vulnerable to security threats. To address this issue, we proposed the Lifeline consensus, which aims to protect small-scale blockchains by delivering safety from a strong leading blockchain to a relatively vulnerable following blockchain using a new type of data called Coil. Coil carries the proof-of-work evidence created by miners from an arbitrary following blockchain, which the leading blockchain then gathers and generates immutable blocks that contained them. Miners from the following blockchain can use the coils in the leading blockchain for validation, thereby protecting small-scale blockchains from typical blockchain threats such as 51% attacks and selfish mining. We implemented our protocol and encountered adversaries in the local network, and analyzed its performance. The results showed that the Lifeline protocol is dependable with a Trusted Leader. These findings suggest that our protocol has the potential to improve the security of small-scale blockchains and enhance the overall performance of the blockchain network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Handover Scheme in LEO Satellite Networks Based on QoE for Streaming Services

Handover Scheme in LEO Satellite Networks Based on QoE for S...

引用

International Conference on Communication Technology (ICCT)

作者： Huazhi Feng Lidong Zhu Jianhong Zhou National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu China School of Computer and Software Engineering Xihua University Chengdu China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

The development of satellite communications has received considerable attention in recent years. Early satellite communications were dominated by voice and low-speed data services, but now they must support high-speed multimedia services. Low Earth orbit (LEO) satellites are an important part of the future realization of high-bandwidth and low-latency multimedia services. However, LEO satellites face many challenges in accessing and handover due to their fast-moving speed. For example, few studies have been conducted on the performance of multimedia services (including streaming services) in satellite communication environments at the Quality of Experience (QoE) level, and there are no relevant simulation systems to evaluate and examine them. Therefore, this paper builds a simulation system for streaming media services in LEO satellite communication scenarios in order to simulate the initial buffering, rebuffering, and idle state of the users during service. Then, an access and handover scheme for the QoE level of streaming media service is proposed. Finally, our proposed scheme is evaluated based on this simulation system. From the simulation results, the simulation system proposed in this paper can successfully realize the various functions of users in on- demand streaming media services. And the streaming QoE-based access and handover scheme can perform well in satellite, a resource-constrained scenario.

关键词： Satellites Simulation Low earth orbit satellites Streaming media Handover Quality of experience Multimedia communication Low latency communication Satellite communications Faces

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：