检索结果-内蒙古大学图书馆

Application of improved virtual sample and sparse representation in face recognition

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1391-1402页

作者： Yongjun Zhang Zewei Wang Xuexue Zhang Zhongwei Cui Bob Zhang Jinrong Cui Lamin LJanneh College of Computer Science and Technology Guizhou UniversityGuiyangChina Big Data Science and Intelligent Engineering Research Institute Guizhou Education UniversityGuiyangChina School of Mathematics and Big Data Guizhou Education UniversityGuiyangChina Department of Computer and Information Science University of MacaoAvenida da UniversidadeTaipaMacaoChina School of Mathematics and Information South China Agricultural UniversityGuangzhouChina

Sparse representation plays an important role in the research of face *** a deformable sample classification task,face recognition is often used to test the performance of classification *** face recognition,differences in expression,angle,posture,and lighting conditions have become key factors that affect recognition ***,there may be significant differences between different image samples of the same face,which makes image classification very ***,how to build a robust virtual image representation becomes a vital *** solve the above problems,this paper proposes a novel image classification ***,to better retain the global features and contour information of the original sample,the algorithm uses an improved non‐linear image representation method to highlight the low‐intensity and high‐intensity pixels of the original training sample,thus generating a virtual ***,by the principle of sparse representation,the linear expression coefficients of the original sample and the virtual sample can be calculated,*** obtaining these two types of coefficients,calculate the distances between the original sample and the test sample and the distance between the virtual sample and the test *** two distances are converted into distance ***,a simple and effective weight fusion scheme is adopted to fuse the classification scores of the original image and the virtual *** fused score will determine the final classification *** experimental results show that the proposed method outperforms other typical sparse representation classification methods.

关键词： representation sample image

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Self-Perception Enhanced Large Language Model for 3D Region-of-Interest Captioning With Limited data

引用

IEEE Transactions on Multimedia 2025年 27卷 2935-2948页

作者： Shi, Lu Kan, Shichao Jin, Yi Zhang, Linna Cen, Yigang Bejing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation School of Computer Science and Technology Visual Intellgence + X International Cooperation Joint Laboratory of MOE Beijing100044 China Central South University School of Computer Science and Engineering Changsha410083 China Beijing Jiaotong University Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education and the School of Computer Science and Technology Beijing100044 China Guizhou University School of Mechanical Engineering Guiyang550025 China

3D Region-of-Interest (RoI) Captioning involves translating a model's understanding of specific objects within a complex 3D scene into descriptive captions. Recent advancements in Large Language Models (LLMs) have shown great potential in this area. Existing methods capture the visual information from RoIs as input tokens for LLMs. However, this approach may not provide enough detailed information for LLMs to generate accurate region-specific captions. In this paper, we introduce Self-RoI, a Large Language Model with multi-modal self-perception capabilities for 3D RoI captioning. To ensure LLMs receive more precise and sufficient information, Self-RoI incorporates Implicit Textual Info. Perception to construct a multi-modal vision-language information. This module utilizes a simple mapping network to generate textual information about basic properties of RoI from vision-following response of LLMs. This textual information is then integrated with the RoI's visual representation to form a comprehensive multi-modal instruction for LLMs. Given the limited availability of 3D RoI-captioning data, we propose a two-stage training strategy to optimize Self-RoI efficiently. In the first stage, we align 3D RoI vision and caption representations. In the second stage, we focus on 3D RoI vision-caption interaction, using a disparate contrastive embedding module to improve the reliability of the implicit textual information and employing language modeling loss to ensure accurate caption generation. Our experiments demonstrate that Self-RoI significantly outperforms previous 3D RoI captioning models. Moreover, the Implicit Textual Info. Perception can be integrated into other multi-modal LLMs for performance enhancement. We will make our code available for further research. © 1999-2012 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Alignment Work for Urban Accessibility: A Study of How Wheelchair Users Travel in Urban Spaces

引用

Proceedings of the ACM on Human-computer Interaction 2022年第CSCW2期6卷 1–22页

作者： Wu, Yiying Ding, Xianghua Dai, Xuelan Zhang, Peng Lu, Tun Gu, Ning School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Computing Science University of Glasgow Glasgow United Kingdom

Mobility is the key for people with disabilities to have full participation in life. To support their mobility, previous work primarily focused on accessibility as an attribute of the external environment to be evaluated, labeled, visualized, and improved. Relatively less work has looked at how people with disabilities go out and move around in practice and work to achieve mobility. This paper presents a qualitative study of 14 wheelchair users' travel practices in everyday life in China, highlighting urban accessibility as alignment work-the use of an awareness of the conditions along the journey to continuously align and re-Align various resources to ensure accessibility and mobility across contexts and moments. By highlighting alignment work, we present another side of the story of urban accessibility, and broaden design considerations to support mobility for wheelchair users. © 2022 ACM.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa 9

English-to-Low-Resource Translation: A Multimodal Approach f...

引用

9th Conference on Machine Translation, WMT 2024

作者： Hatami, Ali Banerjee, Shubhanker Arcan, Mihael Buitelaar, Paul McCrae, John Philip Insight SFI Research Centre for Data Analytics Data Science Institute University of Galway Ireland ADAPT Centre Data Science Institute University of Galway Ireland Lua Health Galway Ireland School of Computer Science University of Galway Ireland

ISBN: (纸本)9798891761797

Multimodal machine translation leverages multiple data modalities to enhance translation quality, particularly for low-resourced languages. This paper uses a multimodal model that integrates visual information with textual data to improve translation accuracy from English to Hindi, Malayalam, Bengali, and Hausa. This approach employs a gated fusion mechanism to effectively combine the outputs of textual and visual encoders, enabling more nuanced translations that consider both language and contextual visual cues. The model’s performance was evaluated against the text-only machine translation model based on BLEU, ChrF2 and TER. Experimental results demonstrate that the multimodal approach consistently outperforms the text-only baseline, highlighting the potential of integrating visual information in low-resourced language translation tasks. ©2024 Association for Computational Linguistics.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

A Transmission and Transformation Fault Detection Algorithm Based on Improved YOLOv5

引用

computers, Materials & Continua 2023年第9期76卷 2997-3011页

作者： Xinliang Tang Xiaotong Ru Jingfang Su Gabriel Adonis School of Information Science and Engineering Hebei University of Science and TechnologyShijiazhuang050000China Department of Computer Science and Information Systems Birkbeck Institute for Data AnalyticsLondonB100ABWC1E 7HXUK

On the transmission line,the invasion of foreign objects such as kites,plastic bags,and balloons and the damage to electronic components are common transmission line *** these faults is of great significance for the safe operation of power ***,a YOLOv5 target detection method based on a deep convolution neural network is *** this paper,Mobilenetv2 is used to replace Cross Stage Partial(CSP)-Darknet53 as the *** structure uses depth-wise separable convolution to reduce the amount of calculation and parameters;improve the detection *** the same time,to compensate for the detection accuracy,the Squeeze-and-Excitation Networks(SENet)attention model is fused into the algorithm framework and a new detection scale suitable for small targets is added to improve the significance of the fault target area in the *** pictures of foreign matters such as kites,plastic bags,balloons,and insulator defects of transmission lines,and sort theminto a data *** experimental results on datasets show that themean Accuracy Precision(mAP)and recall rate of the algorithm can reach 92.1%and 92.4%,*** the same time,by comparison,the detection accuracy of the proposed algorithm is higher than that of other methods.

关键词： Transmission line YOLOv5 multi-scale integration SENet

来源：评论

学校读者我要写书评

暂无评论

Machine learning and data augmentation in the proxy means test for poverty targeting

引用

Statistical Journal of the IAOS 2023年第4期39卷 961-977页

作者： Wobcke, Wayne Mariyah, Siti School of Computer Science and Engineering UNSW Data Science Hub (uDASH) University of New South Wales Sydney NSW Australia

Recent years have seen increased interest in the use of alternative data sources in the definition and production of official statistics and indicators for the UN Sustainable Development Goals. In this paper, we consider the application of data science to the production of official statistics, illustrating our perspective through the use of poverty targeting as an application. We show that machine learning can play a central role in the generation of official statistics, combining a variety of types of data (survey, administrative and alternative). We focus on the problem of poverty targeting using the Proxy Means Test in Indonesia, comparing a number of existing statistical and machine learning methods, then introducing new approaches in the spirit of small area estimation that utilize area-level features and data augmentation at the subdistrict level to develop more refined models at the district level, evaluating the methods on three districts in Indonesia on the problem of estimating 2020 per capita household expenditure using data from 2016-2019. The best performing method, XGBoost, is able to reduce inclusion/exclusion errors on the problem of identifying the poorest 40% of the population in comparison to the commonly used Ridge Regression method by between 4.5% and 13.9% in the districts studied. © 2023 - IOS Press. All rights reserved.

关键词： data augmentation machine learning Poverty targeting

来源：评论

学校读者我要写书评

暂无评论

Latent Logic Tree Extraction for Event Sequence Explanation from LLMs 41

Latent Logic Tree Extraction for Event Sequence Explanation ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Song, Zitao Yang, Chao Wang, Chaojie An, Bo Li, Shuang School of Computer Science and Engineering Nanyang Technological University Singapore School of Data Science The Chinese University of Hong Kong Shenzhen China Skywork AI Singapore

Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences. Our goal is to design an efficient, plug- and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to provide customized insights into each observed event sequence. Built on the temporal point process model for events, our method employs the likelihood function as a score to evaluate generated logic trees. We propose an amortized Expectation-Maximization (EM) learning framework and treat the logic tree as latent variables. In the E-step, we evaluate the posterior distribution over the latent logic trees using an LLM prior and the likelihood of the observed event sequences. LLM provides a high-quality prior for the latent logic trees, however, since the posterior is built over a discrete combinatorial space, we cannot get the closed-form solution. We propose to generate logic tree samples from the posterior using a learnable GFlowNet, which is a diversity-seeking generator for structured discrete variables. The M-step employs the generated logic rules to approximate marginalization over the posterior, facilitating the learning of model parameters and refining the tunable LLM prior parameters. In the online setting, our locally built, lightweight model will iteratively extract the most relevant rules from LLMs for each sequence using only a few iterations. Empirical demonstrations showcase the promising performance and adaptability of our framework. Copyright 2024 by the author(s)

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Probabilistic time series forecasting with deep non-linear state space models

引用

CAAI Transactions on Intelligence Technology 2023年第1期8卷 3-13页

作者： Heming Du Shouguo Du Wen Li School of Computer Science College of Engineering and Computer ScienceAustralian National UniversityCanberraAustralian Capital TerritoryAustralia Shanghai Municipal Big Data Center ShanghaiChina Department of Economic Statistics School of Statistics and InformationShanghai University of International Business and EconomicsShanghaiChina

Probabilistic time series forecasting aims at estimating future probabilistic distributions based on given time series *** is a widespread challenge in various tasks,such as risk management and decision *** investigate temporal patterns in time series data and predict subsequent probabilities,the state space model(SSM)provides a general *** of SSM achieve considerable success in many fields,such as engineering and ***,since underlying processes in real-world scenarios are usually unknown and complicated,actual time series observations are always irregular and ***,it is very difficult to determinate an SSM for classical statistical *** this paper,a general time series forecasting framework,called Deep Nonlinear State Space Model(DNLSSM),is proposed to predict the probabilistic distribution based on estimated underlying unknown processes from historical time series *** fuse deep neural networks and statistical methods to iteratively estimate states and network parameters and thus exploit intricate temporal patterns of time series *** particular,the unscented Kalman filter(UKF)is adopted to calculate marginal likelihoods and update distributions recursively for non-linear *** that,a non-linear Joseph form covariance update is developed to ensure that calculated covariance matrices in UKF updates are symmetric and positive ***,the authors enhance the tolerance of UKF to round-off errors and manage to combine UKF and deep neural *** this manner,the DNLSSM effectively models non-linear correlations between observed time series data and underlying dynamic *** in both synthetic and real-world datasets demonstrate that the DNLSSM consistently improves the accuracy of probability forecasts compared to the baseline methods.

关键词： Artificial Intelligence machine learning time series

来源：评论

学校读者我要写书评

暂无评论

Effort-aware cross-project just-in-time defect prediction framework for mobile apps

引用

Frontiers of computer science 2022年第6期16卷 15-29页

作者： Tian CHENG Kunsong ZHAO Song SUN Muhammad MATEEN Junhao WEN School of Big Data and Software Engineering Chongqing UniversityChongqing401331China School of Computer Science Wuhan UniversityWuhan430072China Department of Computer Science Air University Multan CampusMultan60000Pakistan

As the boom of mobile devices,Android mobile apps play an irreplaceable roles in people’s daily life,which have the characteristics of frequent updates involving in many code commits to meet new ***-in-Time(JIT)defect prediction aims to identify whether the commit instances will bring defects into the new release of apps and provides immediate feedback to developers,which is more suitable to mobile *** the within-app defect prediction needs sufficient historical data to label the commit instances,which is inadequate in practice,one alternative method is to use the cross-project *** this work,we propose a novel method,called KAL,for cross-project JIT defect prediction task in the context of Android mobile *** specifically,KAL first transforms the commit instances into a high-dimensional feature space using kernel-based principal component analysis technique to obtain the representative ***,the adversarial learning technique is used to extract the common feature embedding for the model *** conduct experiments on 14 Android mobile apps and employ four effort-aware indicators for performance *** results on 182 cross-project pairs demonstrate that our proposed KAL method obtains better performance than 20 comparative methods.

关键词： kernel-based principal component analysis adversarial learning just-in-time defect prediction cross-project model

来源：评论

学校读者我要写书评

暂无评论

VaeDiff-DocRE: End-to-end data Augmentation Framework for Document-level Relation Extraction 31

VaeDiff-DocRE: End-to-end Data Augmentation Framework for Do...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Tran, Khai Phan Hua, Wen Li, Xue School of Electrical Engineering and Computer Science The University of Queensland Australia Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9798891761964

Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets. To tackle this challenge, we propose a novel data augmentation approach using generative models to enhance data from the embedding space. Our method leverages the Variational Autoencoder (VAE) architecture to capture all relation-wise distributions formed by entity pair representations and augment data for underrepresented relations. To better capture the multi-label nature of DocRE, we parameterize the VAE's latent space with a Diffusion Model. Additionally, we introduce a hierarchical training framework to integrate the proposed VAE-based augmentation module into DocRE systems. Experiments on two benchmark datasets demonstrate that our method outperforms state-of-the-art models, effectively addressing the long-tail distribution problem in DocRE. Our code is released at: https://***/khaitran22/VaeDiff-DocRE. © 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

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：