检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Songpan Li, Xu School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9783031781247

Facial expression recognition (FER) plays a crucial role in human-computer interaction and emotion analysis. However, recognizing expressions in low-resolution images remains a significant challenge. This paper introduces a practical method called Dynamic Resolution Guidance for Facial Expression Recognition (DRGFER) to effectively recognize facial expressions in images with varying resolutions without compromising the accuracy of the FER model. Our framework comprises two main components: the Resolution Recognition Network (RRN) and the Multi-Resolution Adaptation Facial Expression Recognition Network (MRAFER). The RRN determines the resolution of the input image, and the MRAFER assigns the image to the most suitable facial expression recognition network according to its resolution. We evaluated the performance of DRGFER on two widely used datasets, RAF-DB and FERPlus. The results demonstrate that our method maintains optimal model performance at each resolution and outperforms alternative resolution-handling approaches. The proposed framework exhibits robustness against variations in both resolution and facial expressions, offering a promising solution for real-world applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese Emotion Classification Based on Bilingual Feature Fusion 27th

Improving Chinese Emotion Classification Based on Bilingual...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lan, Haocheng Ou, Jie Wang, Zhaokun Tian, Wenhong School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9783031781186

The growing popularity of Chinese social media platforms such as Sina Weibo has created a large number of user generated text content, which is of great value for understanding public emotions. However, the existence of mixed languages in these texts, especially Chinese and English, and mixed expressions pose a major challenge to current emotion classification methods. To address these issues, we propose a Bilingual Feature Fusion Network (BFFN) that leverages the multilingual capabilities of pre-trained language models to enhance the semantic feature extraction of Chinese text. Additionally, we introduce a Bilingual Cross Attention Mechanism (BCAM) that utilizes emotional features as the primary factor to capture cross-lingual emotional information effectively. Furthermore, we employ a lightweight fine-tuning approach that combines Low-Rank Adaptation (LoRA) and Embedding Fine-tuning (LEF) to reduce the complexity of fine-tuning model weights for downstream tasks. Extensive experiments on various datasets demonstrate the superiority of our proposed method, outperforming state-of-the-art models like ERNIE by 1.43% in accuracy. Our work contributes to the advancement of emotion classification in the context of mixed-language communication culture and provides a practical solution for real-world applications. Our code has been published on the open source community Github (https://***/oujieww/BFFN). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Simulation of unmanned survey path planning in debris flow gully based on GRE-Bat algorithm

引用

Journal of Mountain Science 2024年第12期21卷 4062-4082页

作者： LIU Dunlong FENG Duanguo SANG Xuejia ZHANG Shaojie YANG Hongjuan College of Software Engineering Chengdu University of Information TechnologyChengdu 610225China State Key Laboratory of Mountain Hazards and Engineering Resilience Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610299China

Unmanned aerial vehicle(UAV)paths in the field directly affect the efficiency and accuracy of payload data *** planning of UAV advancing along river valleys in wild environments is one of the first and most difficult problems faced by unmanned surveys of debris flow *** study proposes a new hybrid bat optimization algorithm,GRE-Bat(Good point set,Reverse learning,Elite Pool-Bat algorithm),for unmanned exploration path planning of debris flow sources in outdoor *** the GRE-Bat algorithm,the good point set strategy is adopted to evenly distribute the population,ensure sufficient coverage of the search space,and improve the stability of the convergence accuracy of the ***,a reverse learning strategy is introduced to increase the diversity of the population and improve the local stagnation problem of the *** addition,an Elite pool strategy is added to balance the replacement and learning behaviors of particles within the population based on elimination and local perturbation *** demonstrate the effectiveness of the GRE-Bat algorithm,we conducted multiple simulation experiments using benchmark test functions and digital terrain *** to commonly used path planning algorithms such as the Bat Algorithm(BA)and the Improved Sparrow Search Algorithm(ISSA),the GRE-Bat algorithm can converge to the optimal value in different types of test functions and obtains a near-optimal solution after an average of 60 *** GRE-Bat algorithm can obtain higher quality flight routes in the designated environment of unmanned investigation in the debris flow gully basin,demonstrating its potential for practical application.

关键词： Bat algorithm Unmanned surveys Debris flow gully Path planning Unmanned aerial vehicle Reverse learning

来源：评论

学校读者我要写书评

暂无评论

Universal Adversarial Attack for Trustworthy LiDAR based Object Detection in Embedded Applications 4

Universal Adversarial Attack for Trustworthy LiDAR based Obj...

引用

4th International Conference on Intelligent technology and Embedded Systems, ICITES 2024

作者： Cai, Mumuxin Wang, Xupeng Sohel, Ferdous Lei, Hang School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Information Technology Murdoch University Murdoch Australia

ISBN: (纸本)9798331506292

3D object detection based on deep neural networks (DNNs) has widely been adopted in the field of embedded applications, such as autonomous driving. Nonetheless, recent studies have demonstrated that LiDAR data tends to exhibit intense corruptions, resulting in the failure of 3D object detection tasks. Considering the vulnerability of existing DNNs and the wide applications of 3D object detection to safety-critical scenarios, the robustness of deep 3D detection models under adversarial attacks is investigated in this work. The proposed universal adversarial attack is encoded into a perturbation voxel, which adds point-wise perturbations to benign LiDAR scenes. The detector-level perturbation voxel is generated by suppressing the detector's predictions on training samples, which covers the entire perceptual range of the detector. The designed perturbation voxels can be applied to the entire scene to simulate the global perturbation inherent in LiDAR. And it can adapt to other detectors with various point cloud representations, which makes attack universal. To test the effectiveness of the proposed attack, it was launched against a number of deep 3D detectors using several datasets. The results demonstrate its superiority over existing art. © 2024 IEEE.

关键词： 3D object detection LiDAR sensors Point cloud Security of embedded applications Universal adversarial attack

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Power of Deep Learning: A Comparative Study of LSTM, BERT, and GRU for Disaster Tweet Classification

引用

IEIE Transactions on Smart Processing and Computing 2023年第6期12卷 526-534页

作者： Ullah, Ihsan Jamil, Anum Ul Hassan, Imtiaz Kim, Byung-Seo Department of Software and Communication Engineering Hongik University Korea Republic of Department of Physics NED University of Engineering & Technology Karachi Pakistan Department of Computer Science and Information Technology NED University of Engineering & Technology Karachi Pakistan

Disasters have serious effects on people's lives and buildings. Therefore, social media platforms, such as Twitter, have become more critical. They are crucial tools for responding to and managing disasters effectively. This study examined the effectiveness of various deep learning models, such as bidirectional encoder representations from transformers (BERT), gated recurrent units (GRU), and long short-term memory (LSTM) for classifying disaster-related tweets. Twitter data related to different disasters were collected using hashtags. The data were then cleaned, preprocessed, and manually annotated by a team. The annotated data were divided into training, validation, and testing sets. The data were used to train three models based on BERT, GRU, and LSTM for the categorical classification of disaster tweets. Finally, the three models were evaluated and compared using the test data. BERT achieved an accuracy of 96.2%, making it the most effective model. In contrast, the LSTM and GRU models achieved an accuracy of 93.2% and 88.4%, respectively. These findings underscore the potential effectiveness of deep learning models in classifying disaster-related tweets, offering insights that could enhance disaster management strategies, refine social media monitoring processes, bolster public safety, and provide directions for future research. © 2023 Institute of Electronics and information Engineers. All rights reserved.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Image Representations of Numerical Simulations for Training Neural Networks

引用

Computer Modeling in engineering & Sciences 2023年第2期134卷 821-833页

作者： Yiming Zhang Zhiran Gao Xueya Wang Qi Liu School of Civil and Transportation Engineering Hebei University of TechnologyTianjin300401China School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China

A large amount of data can partly assure good fitting quality for the trained neural *** the quantity of experimental or on-site monitoring data is commonly insufficient and the quality is difficult to control in engineering practice,numerical simulations can provide a large amount of controlled high quality *** the neural networks are trained by such data,they can be used for predicting the properties/responses of the engineering objects instantly,saving the further computing efforts of simulation ***,a strategy for efficiently transferring the input and output data used and obtained in numerical simulations to neural networks is desirable for engineers and *** this work,we proposed a simple image representation strategy of numerical simulations,where the input and output data are all represented by *** temporal and spatial information is kept and the data are greatly *** addition,the results are readable for not only computers but also human *** examples are given,indicating the effectiveness of the proposed strategy.

关键词： Numerical simulations neural network pre-/post-processing data compression

来源：评论

学校读者我要写书评

暂无评论

Diffusion model for adversarial attack against NLP models

Diffusion model for adversarial attack against NLP models

引用

2023 International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2023

作者： Qiu, Shilin Gou, Min Liang, Tao School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9781510677685

Current black-box adversarial attacks have proven to be highly effective in generating adversarial texts that can successfully deceive natural language processing models, thereby revealing potential weaknesses in these models. This research proposes an innovative transfer-based black-box attack method, which capitalizes on the combined generative and discriminative abilities of the diffusion model. To ensure semantic similarity and enhance the adversarial ability of generated texts, well-designed semantic-preserving and adversarial objectives are introduced to the training procedure of the diffusion model. The results show that the proposed method can generate adversarial texts that successfully attack text classification models. © 2024 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Offshore software Maintenance Outsourcing Process Model Validation:A Case Study Approach

引用

Computers, Materials & Continua 2023年第3期74卷 5035-5048页

作者： Atif Ikram Masita Abdul Jalil Amir Bin Ngah Adel Sulaiman Muhammad Akram Ahmad Salman Khan Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala TerengganuMalaysia Department of Computer Science&Information Technology Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Department of Computer Science College of Computer Science and Information SystemsNajran UniversityNajranSaudi Arabia Department of Software Engineering Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan

The successful execution and management of Offshore software Maintenance Outsourcing(OSMO)can be very beneficial for OSMO vendors and the OSMO *** a lot of research on software outsourcing is going on,most of the existing literature on offshore outsourcing deals with the outsourcing of software development *** frameworks have been developed focusing on guiding software systemmanagers concerning offshore software ***,none of these studies delivered comprehensive guidelines for managing the whole process of *** is a considerable lack of research working on managing OSMO from a vendor’s ***,to find the best practices for managing an OSMO process,it is necessary to further investigate such complex and multifaceted phenomena from the vendor’s *** study validated the preliminary OSMO process model via a case study research *** results showed that the OSMO process model is applicable in an industrial setting with few *** industrial data collected during the case study enabled this paper to extend the preliminary OSMO process *** refined version of the OSMO processmodel has four major phases including(i)Project Assessment,(ii)SLA(iii)Execution,and(iv)Risk.

关键词： Offshore outsourcing process model model validation vendor challenges case study

来源：评论

学校读者我要写书评

暂无评论

Bidirectional attentional mechanism for Arabic chatbot

引用

International Journal of information technology (Singapore) 2024年第5期16卷 3109-3120页

作者： Youness, Farida Elshenawy, Ayman Makour, Mohamed Ashraf Systems and Computer Engineering Department Faculty of Engineering Al-Azhar University Cairo Egypt Software Engineering and Information Technology Department Faculty of Engineering and Technology Egyptian Chinees University Cairo Egypt

A chatbot is an intelligent agent that developed based on Natural language processing (NLP) to interact with people in a natural language. The development of multiple deep NLP models has allowed for the creation of a vector representation of words and sentences that captures meaning in context. In this paper, a generative Arabic chatbot is trained with the Sequence to Sequence (Seq2Seq) model based on encoder-decoder architecture. It utilizes both the bi-directional encoder types of Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM). The chatbot was trained using preprocessed dataset of 12 k conversations that were translated from English to Arabic. An attention layer was provided to the RNNs to focus on the important data between the input and output sequences. The obtained results showed that the proposed chatbot performed well with long sentences and elicited positive responses. In addition to that BiLSTM with attention performs better than BiGRU without attention. To assess the model, the Bilingual Evaluation Understudy (BLEU) Score is employed. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Arabic chatbot Attention mechanism Deep learning RNN

来源：评论

学校读者我要写书评

暂无评论

Outlier item detection in bundle recommendation via the attention mechanism

引用

High-Confidence Computing 2024年第3期4卷 51-57页

作者： Yuan Liang School of Information Engineering Suqian UniversitySuqian 223800China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic TechnologyGuilin 541004China

Bundle recommendation offers users more holistic insights by recommending multiple compatible items at ***,the intricate correlations between items,varied user preferences,and the pronounced data sparsity in combinations present significant challenges for bundle recommendation ***,current bundle recommendation methods fail to identify mismatched items within a given set,a process termed as‘‘outlier item detection’’.These outlier items are those with the weakest correlations within a *** them can aid users in refining their item *** the correlation among items can predict the detection of such outliers,the adaptability of combinations might not be adequately responsive to shifts in individual items during the learning *** limitation can hinder the algorithm’s *** tackle these challenges,we introduce an encoder–decoder architecture tailored for outlier item *** encoder learns potential item correlations through a self-attention ***,the decoder garners efficient inference frameworks by directly assessing item *** have validated the efficacy and efficiency of our proposed algorithm using real-world datasets.

关键词： Bundle recommendation Outlier item detection Attention mechanism Decoder encoder

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：