检索结果-内蒙古大学图书馆

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Majdi Owda Amani Yousef Owda Maria Fasli Faculty of Data Science UNESCO Chair in Data Science for Sustainable Development Arab American University Ramallah West Bank Palestine Deprtment of Natural Engineering and Technology Sciences Faculty of Graduate Studies Arab American University Ramallah West Bank Palestine University of Essex School of Computer Science and Electronic Engineering Institute for Analytics and Data Science Colchester UK

Exploratory data analysis and visualization are essential tools for discovering patterns, highlighting anomalies, and discovering insights from datasets. In addition, visualizations tend to provide information in a way that is more accessible for the audience to understand and comprehend. Underprivileged communities will need an easier way to comprehend issues, challenges, and threats such as avoiding diseases. The use of exploratory data analysis and visualizations of diabetes datasets can be used as a means to make this topic easier to understand for underprivileged communities. A methodology has been developed to explore a dataset collection of diabetes patients. The dataset was obtained from the Palestinian community medical center (first-hand dataset), then the dataset was prepared and cleaned, and all rows with missing values or wrong values were dropped and removed, then an exploratory data analysis with a large number of data visualizations was produced, and last, a sample of the produced visualizations have been used to conduct a social acceptance experiment to educate an underprivileged population in the Palestinian community about the risks of diabetes. The result of the experiment was excellent and very promising in which participants understood the contents in a much easier way and provided very positive feedback on utilizing visualizations of diabetes datasets for public awareness and good.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Large Models Are Effective Action Anticipators

arXiv

引用

arXiv 2025年

作者： Wang, Binglu Tian, Yao Wang, Shunzhou Yang, Le College of Information and Control Engineering Xi'an University of Architecture and Technology Xi'An710055 China The School of Astronautics Northwestern Polytechnical University Xi'An710072 China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University Shenzhen518055 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China The School of Information Science and Technology University of Science and Technology of China Hefei230022 China

The task of long-term action anticipation demands solutions that can effectively model temporal dynamics over extended periods while deeply understanding the inherent semantics of actions. Traditional approaches, which primarily rely on recurrent units or Transformer layers to capture long-term dependencies, often fall short in addressing these challenges. Large Language Models (LLMs), with their robust sequential modeling capabilities and extensive commonsense knowledge, present new opportunities for long-term action anticipation. In this work, we introduce the ActionLLM framework, a novel approach that treats video sequences as successive tokens, leveraging LLMs to anticipate future actions. Our baseline model simplifies the LLM architecture by setting future tokens, incorporating an action tuning module, and reducing the textual decoder layer to a linear layer, enabling straightforward action prediction without the need for complex instructions or redundant descriptions. To further harness the commonsense reasoning of LLMs, we predict action categories for observed frames and use sequential textual clues to guide semantic understanding. In addition, we introduce a Cross-Modality Interaction Block, designed to explore the specificity within each modality and capture interactions between vision and textual modalities, thereby enhancing multimodal tuning. Extensive experiments on benchmark datasets demonstrate the superiority of the proposed ActionLLM framework, encouraging a promising direction to explore LLMs in the context of action anticipation. Code is available at https://***/2tianyao1/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Quantitative Evaluation to Detect Crack Depth in Beams Based on CNN-RNN-LSTM Approach

Quantitative Evaluation to Detect Crack Depth in Beams Based...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Mohammad Asif Gandhi A. N. Swaminathen Deepak T. Patil A Ravitheja R. Kamali Akshay Rajput Department of Mechanical Engineering Anjuman-I-Islam's Kalsekar Technical Campus Panvel Maharashtra India Adi Shankara Institute of Engineering and Technology Kerala India Bharati Vidyapeeth college of Architecture Navi Mumbai Maharashtra India Department of Civil Engineering SVR Engineering College Kurnool Andhra Pradesh India Department of Computer Science And Engineering Knowledge Institute of Technology Salem Tamilnadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

In this study, the proposed approach offers a novel hybrid image-based deep learning method for autonomous concrete fracture identification. Cracks are easier to spot and false positives are reduced with hybrid images that include visual and infrared thermography data. In specifically, a Visible and infrared camera as well as a line laser make up a hybrid imaging system for spatially scanning unmanned vehicles can efficiently assess large-scale concrete-made constructions like bridges and dams. Crack detection is a commonplace task in many industrial domains, however the current method of relying on expert judgment is typically laborious, time consuming, and inaccurate. The practical benefits of automated decision-making increase as the size of the target concrete construction grows. Cracks can be automatically identified and seen using the proposed method. Preprocessing, segmentation, feature extraction, and model training are the four components of the proposed method. It performs clever edge recognition, scaling, and greyscale conversion as part of its preparation. Improved K-Means segmentation is used for the separation. It employs GLCM for feature extraction, and CNN-RNN-LSTM for model training. The new method is compared to two established approaches, CNN-RNN and CNN-LSTM, and is found to be superior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Over-the-Air Federated Learning in Multi-Antenna Systems

arXiv

引用

arXiv 2023年

作者： Wang, Sihua Chen, Mingzhe Shen, Cong Yin, Changchuan Brinton, Christopher G. The Beijing Laboratory of Advanced Information Network The Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Charles L. Brown Department of Electrical and Computer Engineering University of Virginia CharlottesvilleVA United States The School of Electrical and Computer Engineering Purdue University West LafayetteIN United States

In this paper, the performance optimization of federated learning (FL), when deployed over a realistic wireless multiple-input multiple-output (MIMO) communication system with digital modulation and over-the-air computation (AirComp) is studied. In particular, a MIMO system is considered in which edge devices transmit their local FL models (trained using their locally collected data) to a parameter server (PS) using beamforming to maximize the number of devices scheduled for transmission. The PS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all devices. Due to the limited bandwidth in a wireless network, AirComp is adopted to enable efficient wireless data aggregation. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. To tackle this challenge, we propose a modified federated averaging (FedAvg) algorithm that combines digital modulation with AirComp to mitigate wireless fading while ensuring the communication efficiency. This is achieved by a joint transmit and receive beamforming design, which is formulated as an optimization problem to dynamically adjust the beamforming matrices based on current FL model parameters so as to minimize the transmitting error and ensure the FL performance. To achieve this goal, we first analytically characterize how the beamforming matrices affect the performance of the FedAvg in different iterations. Based on this relationship, an artificial neural network (ANN) is used to estimate the local FL models of all devices and adjust the beamforming matrices at the PS for future model transmission. The algorithmic advantages and improved performance of the proposed methodologies are demonstrated through extensive numerical experiments. Copyright © 2023, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

I³: Interactive Iterative Improvement for Few-Shot Action Segmentation

I³: Interactive Iterative Improvement for Few-Shot Action S...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Martina Gassen Frederic Metzler Erik Prescher Lisa Scherf Vignesh Prasad Felix Kaiser Dorothea Koert Interactive AI & Cognitive Models for Human-AI Interaction (IKIDA) TU Darmstadt Germany Centre for Cognitive Science TU Darmstadt Germany Department of Computer Science Institute for Intelligent Autonomous Systems TU Darmstadt Germany Department of Law and Economics Chair for Marketing and Human Resource Management TU Darmstadt Germany

Extracting modular segments from raw video demonstrations of high-level actions is important to understand the underlying building blocks for different tasks in human-robot interaction. While (data-hungry) supervised learning approaches for Action Segmentation show good performance when the underlying segments are predefined, their performance degrades when unseen actions are introduced on-the-go as new data samples are scarce. In this regard, Zero-and Few-Shot Learning approaches have shown good performance in generalizing to unseen examples. In Action Segmentation, where each frame needs to be labeled, annotating new data even for a few tasks can become tedious as the number of tasks scale. In this work, we propose Interactive Iterative Improvement $(I^{3})$ for Few-Shot Action Segmentation, a Semi-Supervised Interactive Meta-Learning approach for Zero-Shot Learning on unlabeled videos and Few-Shot Learning on small amounts of labeled videos. $I^{3}$ consists of a Prototypical Network model for frame-wise prediction coupled with a Hidden-Semi-Markov-Model to prevent over-segmentation. The model is iteratively improved in an interactive manner through users’ annotations provided via a webinterface. This is done in a task-agnostic manner that, in theory, can be reused for a number of different actions. Our model provides sequentially accurate segmentations using only a limited amount of labeled data which shows the efficacy of our learning approach. A lower edit distance compared to baselines indicates a lower number of required user edits making it well suited for non-expert users to smoothly provide annotations enabling them to have more control over the learned model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data

SynFacePAD 2023: Competition on Face Presentation Attack Det...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Meiling Fang Marco Huber Julian Fierrez Raghavendra Ramachandra Naser Damer Alhasan Alkhaddour Maksim Kasantcev Vasiliy Pryadchenko Ziyuan Yang Huijie Huangfu Yingyu Chen Yi Zhang Yuchen Pan Junjun Jiang Xianming Liu Xianyun Sun Caiyong Wang Xingyu Liu Zhaohua Chang Guangzhe Zhao Juan Tapia Lazaro Gonzalez-Soler Carlos Aravena Daniel Schulz Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Biometrics and Data Pattern Analytics Lab Universidad Autonoma de Madrid Spain Norwegian University of Science and Technology (NTNU) Norway ID R&D Inc New York US School of Cyber Science and Engineering Sichuan University Chengdu China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China Biometrics and Security Research Group Hochschule Darmstadt Darmstadt Germany I+D Vision Center Santiago Chile

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Low-Precision Computation Potential of Tensor Cores on GPUs

Unleashing the Low-Precision Computation Potential of Tensor...

引用

International Symposium on Code Generation and Optimization (CGO)

作者： Guangli Li Jingling Xue Lei Liu Xueying Wang Xiu Ma Xiao Dong Jiansong Li Xiaobing Feng School of Computer Science and Technology University of Chinese Academy of Sciences China School of Computer Science and Engineering University of New South Wales Australia SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China College of Computer Science and Technology Jilin University China

ISBN: (数字)9781728186139

ISBN: (纸本)9781728186146

Tensor-specialized hardware for supporting low-precision arithmetic has become an inevitable trend due to the ever-increasing demand on computational capability and energy efficiency in intelligent applications. The main challenge faced when accelerating a tensor program on tensor-specialized hardware is how to achieve the best performance possible in reduced precision by fully utilizing its computational resources while keeping the precision loss in a controlled manner. In this paper, we address this challenge by proposing QUANTENSOR, a new approach for accelerating general-purpose tensor programs by replacing its tensor computations with low-precision quantized tensor computations on NVIDIA Tensor Cores. The key novelty is a new residual-based precision refinement technique for controlling the quantization errors, allowing tradeoffs between performance and precision to be made. Evaluation with GEMM, deep neural networks, and linear algebra applications shows that QUANTENSOR can achieve remarkable performance improvements while reducing the precision loss incurred significantly at acceptable overheads.

关键词： Tensors Quantization (signal) Neural networks Market research Hardware Acceleration Optimization

来源：评论

学校读者我要写书评

暂无评论

Reducing Redundancy in Data Organization and Arithmetic Calculation for Stencil Computations

Reducing Redundancy in Data Organization and Arithmetic Calc...

引用

Supercomputing Conference

作者： Kun Li Liang Yuan Yunquan Zhang Yue Yue State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Scienceslice Beijing China

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

Stencil computation is one of the most important kernels in various scientific and engineering applications. A variety of work has focused on vectorization techniques, aiming at exploiting the in-core data parallelism. However, they either incur spatial data conflicts or hurt the data locality when integrated with tiling. In this paper, a novel spatial computation folding is devised to reduce the data reorganization overhead for vectorization and preserve the data locality for tiling in the data space simultaneously. We then propose an approach of temporal computation folding enhanced with shifts reusing, tessellate tiling, and semi-automatic code generation. It aims to further reduce the redundancy of arithmetic calculations and exploit the register reuse along the time dimension. Experimental results on the AVX2 and AVX-512 CPUs show that our approach obtains significant performance improvements compared with state-of-the-art techniques.

关键词： Codes High performance computing Redundancy Organizations Parallel processing Spatial databases Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Distributed Learning by Local Training ADMM

Distributed Learning by Local Training ADMM

引用

IEEE Conference on Decision and Control

作者： Xiaoxing Ren Nicola Bastianello Karl H. Johansson Thomas Parisini Department of Electrical and Electronic Engineering Imperial College London London United Kingdom 2School of Electrical Engineering and Computer Science and Digital Futures KTH Royal Institute of Technology Stockholm Sweden Department of Electronic Systems Aalborg University Denmark Department of Engineering and Architecture University of Trieste Trieste Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this paper, we focus on distributed learning over peer-to-peer networks. In particular, we address the challenge of expensive communications (which arise when e.g. training neural networks), by proposing a novel local training algorithm, LTADMM. We extend the distributed ADMM enabling the agents to perform multiple local gradient steps per communication round (local training). We present a preliminary convergence analysis of the algorithm under a graph regularity assumption, and show how the use of local training does not compromise the accuracy of the learned model. We compare the algorithm with the state of the art for a classification task, and in different set-ups. The results are very promising showing a great performance of LT-ADMM, and paving the way for future important theoretical developments.

关键词： Training computer aided instruction Analytical models Accuracy Distance learning Neural networks Classification algorithms Topology Peer-to-peer computing Convergence

来源：评论

学校读者我要写书评

暂无评论

A Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements 63

A Multi-Player Potential Game Approach for Sensor Network Lo...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Xu, Gehui Chen, Guanpu Fidan, Baris Hong, Yiguang Qi, Hongsheng Parisini, Thomas Johansson, Karl H. Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Stockholm100 44 Sweden University of Waterloo Department of Mechanical and Mechatronics Engineering WaterlooONN2L 3G1 Canada Tongji University Department of Control Science and Engineering shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China University of Chinese Academy of Sciences School of Mathematical Sciences Beijing China Aalborg University Department of Electronic Systems Denmark Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom University of Trieste Department of Engineering and Architecture Italy

ISBN: (纸本)9798350316339

Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multiplayer non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies. © 2024 IEEE.

关键词： Nash equilibrium

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：