检索结果-内蒙古大学图书馆

7th International Conference on Image Information Processing, ICIIP 2023

作者： Tajinder Sharma, Sahil International Institute of Information Technology Bangalore India Ulster University School of Computing Engineering And Intelligent Systems Londonderry United Kingdom

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371406

The objective of Image-based Virtual Try-On (VTO) is to effectively superimpose retail clothing items onto a specific individual, creating a seamless integration between the garments and the person. Despite significant advancements in VTO (Virtual Try-On) technology, numerous techniques struggle to maintain semantic integrity, particularly when faced with difficult inputs like complicated human poses and complex clothing designs. The presence of these discrepancies undermines the overall quality of the final visual outputs, hence reducing both the user experience and the effectiveness of the Virtual Try-On (VTO) system. This study provides an in-depth investigation into the enduring problem by utilizing advanced deep learning techniques. In addition to just recognizing the obstacles, this study emphasizes a thorough comprehension derived from extensive literature reviews and practical code experiments. We aim to tackle the significant issue of preserving semantic detail in VTO applications by implementing cutting-edge techniques. This article adopts a future-oriented approach to not only illuminate current constraints but also provide a trajectory for forthcoming initiatives that seek to enhance the virtual retail domain and fully actualize the capabilities of AI-driven fashion technology. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Practical Teaching Reform of Programming Courses Based on Online Coding Platforms 18th

Practical Teaching Reform of Programming Courses Based on On...

引用

18th International Conference on Computer Science and Education, ICCSE 2023

作者： Yuan, Guowu Yue, Kun Hu, Kuang School of Information Science and Engineering Yunnan University Yunnan Kunming650504 China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan Kunming650504 China

ISBN: (纸本)9789819707904

Programming proficiency stands as one of the most vital competencies for students majoring in computer-related disciplines. This paper scrutinizes the issues prevailing in the cultivation of programming skills. Notably, it emphasizes an imbalance in teaching, whereby concepts and syntax receive undue attention while hands-on programming experiences are inadequately incorporated. Furthermore, the absence of standardized assessment mechanisms and avenues for advanced students to enhance their skills compounds these challenges. To augment students’ programming capabilities, we have established an online coding platform, facilitating a practical teaching reform in programming courses guided by "learning, practicing, certification and competing". "Learning" entails knowledge learning, "practicing" involves extensive programming practicing, "certification" signifies reaching programming competency standards, and "competing" denotes participation in programming competitions to enhance skill sets. Over seven years, this implementation has markedly improved students’ programming prowess. It has also led to advancements in certified software professional (CSP) and various programming competition outcomes, effectively embodying the "promoting learning and teaching through competitions" philosophy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Byte-Sized Reviewers: Exploring Review Generation through LNRG-S 3

Byte-Sized Reviewers: Exploring Review Generation through LN...

引用

2023 IEEE 3rd International Conference on Data Science and Computer Application, ICDSCA 2023

作者： Li, Yiting Fu, Min Sun Yat-sen University School of Intelligent Systems Engineering Shenzhen China Macquarie University Department of Computing Sydney Australia

ISBN: (纸本)9798350341546

The development of network technology has led to an explosive growth of user-generated comments. These contents are based on users' experiences after using services and products, reflecting users' evaluations. Automatically generating high-quality and controllable sentiment comments can help creators improve work quality, help service providers enhance service levels, and improve consumers' consumption experience. However, current methods have some limitations. Seq2seq models have difficulty maintaining semantic consistency and generating long texts, LSTM can maintain a memory state and generate coherent text, but is prone to overfitting, generating repetitive text, and having difficulty establishing local coherence. N-gram models text locally but cannot understand the global context. This paper proposes a hybrid architecture, called LNRG-S (LSTM N-gram Reviews Generator with Sentiments), which combines LSTM and N-gram to model both global and local dependencies, and trains separate LSTM generators for positive and negative samples to control sentiment polarity of generated comments. We computed the perplexity of comments generated by different models. LNRG-S has 43.93% and 18.89% lower perplexity than LSTM and n-gram respectively, demonstrating that LNRG-S generates more fluent and coherent text. © 2023 IEEE.

关键词： LSTM n-gram Perplexity Sentiment control User-generated reviews

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Long-Short Term Memory with Byte Pair Encoding and Back Translation for Bangla-English Machine Translation 1st

Bidirectional Long-Short Term Memory with Byte Pair Encoding...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Tanvir, Md. Tasnin Oishy, Asfia Moon Akhand, M.A.H. Siddique, Nazmul Department of Computer Science and Engineering Khulna University of Engineering and Technology Khulna Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Londonderry United Kingdom

ISBN: (纸本)9783031346187

Machine Translation (MT) has emerged as an important research area in the computational intelligence domain to translate huge online resources cost-effectively. Among different MT approaches, Neural based Machine Translation (NMT) is in widespread use nowadays. In NMT, Bidirectional Long-Short Term Memory (BiLSTM) is popular due to its higher accuracy and improved performance. This study investigates different performance improvements with standard BiLSTM for Bangla-English MT (BEMT). Attention (ATT) mechanism, Byte Pair Encoding (BPE) and Back Translation (BT) are integrated independently and combinedly through a systematic approach. Four different models such as BiLSTM+ATT, BiLSTM+ATT+BPE, BiLSTM+ATT+BT and BiLSTM+ATT+BPE+BT have been tested rigorously on a benchmark corpus. The effectiveness of ATT, BPE and BT on a BiLSTM model are identified by comparing the performance of the individual models. Finally, the integrated model of BPE and BT with BiLSTM showed the best generalization ability and outperformed other models. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multilabel Aggressive Text Classification from Social Media using Transformer-based Approaches 26

Multilabel Aggressive Text Classification from Social Media ...

引用

26th International Conference on Computer and Information Technology, ICCIT 2023

作者： Hossain, Jawad Das, Avishek Hoque, Mohammed Moshiul Siddique, Nazmul Chittagong University of Engineering and Technology Department of Computer Science & Engineering Chattogram4349 Bangladesh Ulster University School of Computing Engineering and Intelligent Systems United Kingdom

ISBN: (纸本)9798350359015

The prevalence of multilabel aggressive text content on social media has a detrimental societal impact attracting the attention of government agencies and tech corporations to undertake measures against the spread of it. Hitherto research has focused on high-resource languages like English, leaving low-resource languages like Bengali out of the spotlight. This work presents a transformer-based technique to classify multilabel aggressive texts in Bengali into their targets to aid research in this area. A dataset (EM-BAD) containing 13728 texts is developed into five target classes: Religious Aggression (ReAG), Political Aggression (PoAG), Verbal Aggression (VeAG), Gender Aggression (GeAG), and Racial Aggression (RaAG) to perform the aggressive texts classification. Experimental results demonstrate that the Bangla-BERT with adjusted pooling layer and fine-tuning outdoes all ML, DL, and transformer-base baselines and existing techniques. The Bangla-BERT shows the highest weighted f1-score of 0.89 in the multilabel aggressive text classification task. © 2023 IEEE.

关键词： Aggressive text classification Deep learning Natural language processing Text corpora Text processing

来源：评论

学校读者我要写书评

暂无评论

Classifying Textual Sentiment Using Bidirectional Encoder Representations from Transformers 26

Classifying Textual Sentiment Using Bidirectional Encoder Re...

引用

26th International Conference on Computer and Information Technology, ICCIT 2023

作者： Ahsan, Shawly Tasnia, Fairooz Tabassum, Nafisa Das, Avishek Hoque, Mohammed Moshiul Siddique, Nazmul Chittagong University of Engineering and Technology Department of Computer Science & Engineering Chattogram4349 Bangladesh Ulster University School of Computing Engineering and Intelligent Systems United Kingdom

ISBN: (纸本)9798350359015

Textual sentiment analysis (TSA) has gained significant attention recently for its wide-ranging applications across various research domains and industries. However, most existing research and sentiment analysis tools are primarily tailored for English texts. The unique linguistic complexities of the Bengali language, coupled with a paucity of comprehensive resources and tools, pose distinctive challenges for TSA in Bengali. This paper introduces an intelligent approach, leveraging transformer-based learning techniques by harnessing the potent capabilities of self-attention mechanisms for dealing with Bengali sentences containing ungrammatical structures or local dialects. To tackle the downstream TSA task in Bengali, this work explores a range of machine learning (ML), deep learning (DL), and transformer-based baselines. Experimental results reveal that the Bangla BERT model outperforms the other baselines, achieving the highest weighted f1-score of 0.69. © 2023 IEEE.

关键词： Natural language processing Sentiment analysis Sentiment corpus Text processing Transformer learning

来源：评论

学校读者我要写书评

暂无评论

Keypoint Changes for Fast Human Activity Recognition

引用

SN Computer Science 2023年第5期4卷 1-11页

作者： Reid, Shane Coleman, Sonya Kerr, Dermot Vance, Philip O’Neill, Siobhan School of Computing Engineering and Intelligent Systems Londonderry Ulster University Magee Campus Derry United Kingdom School of Psychology Ulster University Coleraine Campus Coleraine United Kingdom

Human activity recognition has been an open problem in computer vision for almost 2 decades. During this time, there have been many approaches proposed to solve this problem, but very few have managed to solve it in a way that is sufficiently computationally efficient for real-time applications. Recently, this has changed, with keypoint-based methods demonstrating a high degree of accuracy with low computational cost. These approaches take a given image and return a set of joint locations for each individual within an image. In order to achieve real-time performance, a sparse representation of these features over a given time frame is required for classification. Previous methods have achieved this using a reduced number of keypoints, but this approach gives a less robust representation of the individual’s body pose and may limit the types of activity that can be detected. We present a novel method for reducing the size of the feature set, by calculating the Euclidian distance and the direction of keypoint changes across a number of frames. This allows for a meaningful representation of the individuals movements over time. We show that this method achieves accuracy on par with current state-of-the-art methods, while demonstrating real-time performance. © 2023, The Author(s).

关键词： Activity recognition Feature extraction Keypoints MLP Social signal processing

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction Methods for Neural Networks in the Classification of Structural Health Anomalies 15

Feature Extraction Methods for Neural Networks in the Classi...

引用

15th International Joint Conference on Computational Intelligence, IJCCI 2023

作者： Hamilton, Natasha Harkin, Jim McDaid, Liam Liu, Junxiu Furey, Eoghan School of Computing Engineering and Intelligent Systems Ulster University Northland Road Derry United Kingdom Department of Computing Atlantic Technological University Port Road Donegal Ireland

ISBN: (纸本)9789897586743

Failure of large complex structures such as buildings and bridges can have monumental repercussions such as human mortality, environmental destruction and economic consequences. It is therefore paramount that detection of structural damage or anomalies are identified and managed early. This highlights the need to develop automated Structural Health Monitoring (SHM) systems that can continuously allow the safety status of structures to be determined, even in the worst and most isolated conditions, to ultimately help prevent destruction and save lives. Signal processing is a crucial step to detecting structural anomalies and recent work demonstrates the opportunities for neural networks, however the encoding of data for SHM requires the extraction of features due to often, noisy data. This paper focuses on feature extraction methods for artificial neural networks (ANNs) and spiking neural networks (SNNs) and aims to identify bespoke features which enable SNNs to encode data and perform the classification of anomalies. Results show that extraction of particular features in large real-world applications improve the classification accuracy of SNNs. © 2023 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Relevance Search over Knowledge Graph with User-entity Interaction Data 12

Relevance Search over Knowledge Graph with User-entity Inter...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Li, Jianyu Yue, Kun Yunnan University School of Information Science and Engineering China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Kunming China

ISBN: (纸本)9798350340181

Relevance search is to find a list of entities in a knowledge graph (KG), which are associative to a query entity. However, many entities are not linked in KG but are actually associated by user interactions. To this end, we propose a joint weighting function to evaluate the entity associations from both KG and user-entity interaction data simultaneously. Upon the subgraph extracted from KG w.r.t the query entity, we obtain the associative entities by calculating their association degrees. Experimental results show that the effectiveness of our method outperforms other competitors. © 2023 IEEE.

关键词： Association reactions

来源：评论

学校读者我要写书评

暂无评论

Gen-AI Perspective in Digital Healthcare: Ownership versus Practicality 7

Gen-AI Perspective in Digital Healthcare: Ownership versus P...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Gupta, Atantra Das Sharma, Sahil Marketing Area Management Development Institute Gurgaon India Ulster University School of Computing Engineering And Intelligent Systems Londonderry United Kingdom

ISBN: (纸本)9798350371406

The practical implementation and data ownership implications of artificial intelligence (AI) integration in digital healthcare is investigated in this article. It suggests conceptualizing every patient as a complex data structure to facilitate the implementation of personalized medicine. This, however, poses privacy and commercialization-related ethical concerns. The article emphasizes the capacity of artificial intelligence to enhance diagnosis and treatment via the analysis of massive datasets. However, obstacles persist concerning bias, transparency, and human oversight. It provides the conversion of MRI to CT scans via generative adversarial networks as an illustration of the utility of AI. Work remains, nevertheless, to guarantee that AI advances health equity. It is concluded in the paper that continuous research and stakeholder collaboration are required to strike a balance between technological advancement and patient rights. Additional research is necessary in privacy protection, human-AI interaction, and bias mitigation as the healthcare industry undergoes digital transformation. © 2023 IEEE.

关键词： Diagnosis

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：