检索结果-内蒙古大学图书馆

Suitable and Style-Consistent Multi-Texture Recommendation for Cartoon Illustrations

ACM Transactions on Multimedia Computing, Communications and Applications 2024年第7期20卷 1-26页

作者： Wu, Huisi Wang, Zhaoze Li, Yifan Liu, Xueting Lee, Tong-Yee College of Computer Science and Software Engineering Shenzhen University No. 3688 Nanhai Road Nanshan District Guangdong Shenzhen518060 China Dept. of Computer Science and Information Engineering National Cheng-Kung University No. 1 University Road Tainan70101 Taiwan

Texture plays an important role in cartoon illustrations to display object materials and enrich visual experiences. Unfortunately, manually designing and drawing an appropriate texture is not easy even for proficient artists, let alone novice or amateur people. While there exist tons of textures on the Internet, it is not easy to pick an appropriate one using traditional text-based search engines. Although several texture pickers have been proposed, they still require the users to browse the textures by themselves, which is still labor-intensive and time-consuming. In this article, an automatic texture recommendation system is proposed for recommending multiple textures to replace a set of user-specified regions in a cartoon illustration with visually pleasant look. Two measurements, the suitability measurement and the style-consistency measurement, are proposed to make sure that the recommended textures are suitable for cartoon illustration and at the same time mutually consistent in style. The suitability is measured based on the synthesizability, cartoonity, and region fitness of textures. The style-consistency is predicted using a learning-based solution since it is subjective to judge whether two textures are consistent in style. An optimization problem is formulated and solved via the genetic algorithm. Our method is validated on various cartoon illustrations, and convincing results are obtained. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

MIND YOUR AUGMENTATION: THE KEY TO DECOUPLING DENSE SELF-SUPERVISED LEARNING 12

MIND YOUR AUGMENTATION: THE KEY TO DECOUPLING DENSE SELF-SUP...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Qiu, Congpei Zhang, Tong Wu, Yanhao Ke, Wei Salzmann, Mathieu Süsstrunk, Sabine School of Software Engineering Xi'an Jiaotong University China School of Computer and Communication Sciences EPFL Switzerland

Dense Self-Supervised Learning (SSL) creates positive pairs by building positive paired regions or points, thereby aiming to preserve local features, for example of individual objects. However, existing approaches tend to couple objects by leaking information from the neighboring contextual regions when the pairs have a limited overlap. In this paper, we first quantitatively identify and confirm the existence of such a coupling phenomenon. We then address it by developing a remarkably simple yet highly effective solution comprising a novel augmentation method, Region Collaborative Cutout (RCC), and a corresponding decoupling branch. Importantly, our design is versatile and can be seamlessly integrated into existing SSL frameworks, whether based on Convolutional Neural Networks (CNNs) or Vision Transformers (ViTs). We conduct extensive experiments, incorporating our solution into two CNN-based and two ViT-based methods, with results confirming the effectiveness of our approach. Moreover, we provide empirical evidence that our method significantly contributes to the disentanglement of feature representations among objects, both in quantitative and qualitative terms. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of software Security Vulnerabilities from Source Code Using Machine Learning Methods

Prediction of Software Security Vulnerabilities from Source ...

引用

2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023

作者： Mandal, Dilek Kosesoy, Irfan Kocaeli University Computer Engineering Kocaeli Turkey Kocaeli University Software Engineering Kocaeli Turkey

ISBN: (纸本)9798350306590

One of the most significant problems in software engineering is the presence of security vulnerabilities in software. Attackers can exploit these vulnerabilities to gain unauthorized access to systems, leak information, corrupt data, and cause service interruptions. Therefore, in addition to developing secure software, the detection of existing security vulnerabilities in software is also considered as an important research topic. In this study, security vulnerabilities in the source code of software were predicted using machine learning methods. The OWASP Benchmark Test pocket was used as the dataset. This dataset consisted of Java codes and was utilized for training machine learning models Logistic Regression, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Random Forest. TF-IDF and Doc2Vec methods were employed to extract feature vectors from the source code. In the conducted experimental study, the highest prediction accuracy (0.97) was achieved using the TF-IDF feature extraction method and the Decision Tree, SVM and Logistic Regression algorithms. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Classification of Skin Lesions using Squeeze and Excitation Attention based Hybrid Model of DenseNet and EfficientNet

Classification of Skin Lesions using Squeeze and Excitation ...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Armaǧan, Senanur Gündoǧan, Esra Kaya, Mehmet Firat University Dept. of Computer Engineering Elaziǧ Turkey Firat University Dept. of Software Engineering Elaziǧ Turkey

ISBN: (纸本)9798350369106

Skin cancer, like all other types of cancer, is a health problem where early diagnosis saves the patient's life. Successful detection of skin lesions in dermoscopic images enables this process to be managed more quickly. Deep learning architectures have advanced significantly in recent years, particularly in the classification of medical images. For the multi-class classification of skin lesions, a hybrid model was developed in this study utilizing the convolutional neural network architectures of DenseNet and EfficientNet. In addition, SE (Squeeze and Excitation) attention mechanism is integrated into both models. Experimental results show that the inclusion of SE attention mechanism provides a noticeable improvement in classification accuracy. This study not only contributes to the development of effective skin lesion classification systems, but also It also provides valuable insights into the synergistic effects of combining neural network architectures with attention mechanisms. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Academic Use of ChatGPT: Examining the Trends According to Disciplines 8

Academic Use of ChatGPT: Examining the Trends According to D...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Bircan, Abdullah Mandal, Dilek Kosesoy, Irfan Kocaeli University Dept. of Computer Engineering Kocaeli Turkey Kocaeli University Dept. of Software Engineering Kocaeli Turkey

ISBN: (纸本)9798331531492

With the rapid advancement of large language models, particularly ChatGPT, have had a profound impact both in the academic world and in commercial applications. The innovative solutions offered by this technology in areas such as natural language processing, data analysis, and human-computer interaction have led to the emergence of new research domains across various disciplines. However, there has been no comprehensive examination in the literature of which academic disciplines focus on ChatGPT and which areas have attracted more *** study aims to systematically examine academic publications related to ChatGPT and to identify the disciplines in which this technology is more widely adopted, as well as the areas where intensive research is conducted. To this end, a specially developed tool was utilized to scan all academic publications pertaining to ChatGPT, allowing for a comprehensive interdisciplinary analysis. The results of the analysis reveal the academic fields in which ChatGPT is most intensively utilized, highlighting the differences among these fields. Notably, there is a concentration in categories such as 'Medical Sciences,' 'computer Sciences,' and 'Education Sciences,' which also stand out among the most cited publications. Our findings indicate that ChatGPT has gained broad acceptance within the academic community, with certain disciplines leading the way in this regard. Furthermore, the interactions among categories sharing common keywords demonstrate how ChatGPT facilitates interdisciplinary knowledge flow. © 2024 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification Method Based on Global Space-Spectral Attention Mechanism

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-11页

作者： Qin, Rui Wu, Benze Liu, Xinfu Wu, Yirui College of Computer Science and Software Engineering Hohai University Nanjing211100 China Nangjing Research Institute of Electronic Engineering Nanjing210007 China College of Artificial Intelligence and Automation Hohai University Jiangsu Changzhou213200 China

In hyperspectral remote sensing imagery, pixel interactions within defined spatial extents result in the mixing of adjacent pixels. Additionally, the high similarity of adjacent spectra leads to information redundancy, which hinders the extraction of global spatial and spectral correlations. In order to solve the problems of mixed adjacent pixels and redundant adjacent spectra, this work offers a hyperspectral image classification approach that uses a global space-spectral attention mechanism. First, the proposed method’s global spatial attention module uses multi-scale dilated convolution to produce a bigger receptive field to be capable of capturing global spatial correlation and obtain unmixed pixel information. Then, the global spectral attention module designs a spectral domain partition algorithm, using the combination of regional density as well as information entropy as the threshold to divide spectrum into dispersed subsets and eliminate redundant information. The global context information for entire spectral band is fully exploited, and correlation of the global spectral information is extracted. Finally, the two modules combine to provide a global correlation of space and spectrum. Experiments demonstrate that the suggested method obtains overall accuracies of 97.28%, 94.73%, and 95.76% on the three WHU-Hi hyperspectral datasets, surpassing comparison methods. © Shanghai Jiao Tong University 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Dysarthric Speech Recognition: A Comparative Study 12

Dysarthric Speech Recognition: A Comparative Study

引用

12th International Conference on Speech Technology and Human-computer Dialogue, SpeD 2023

作者： Shah, Dhvani Lal, Vanshika Zhong, Zihan Wang, Qianli Shahamiri, Seyed Reza The University of Auckland Faculty of Engineering Department of Electrical Computer and Software Engineering Auckland New Zealand

ISBN: (纸本)9798350327977

Automatic Speech Recognition (ASR) systems are designed to convert spoken words into written text. These systems have the potential to greatly benefit individuals with speech impairments like dysarthria, improving their overall quality of life. However, there are significant challenges that researchers must address in order to develop an effective ASR system for atypical speech, specifically dysarthric speech. Among these challenges are the limited availability of dysarthric speech data and the need for an accurate interpretation model. In this study, we explored the development of dysarthric ASR systems, starting from traditional approaches that were specifically designed to recognize dysarthric speech. We then delve into deep-learning-based ASR systems and modern ASR engines that utilize transformers. Additionally, we highlighted the notable dysarthric speech collections and identified the key factors that impede the performance of dysarthric ASR systems. The findings indicate that although researchers have achieved gradual improvements in performance, further research is required to achieve practical performance levels. Likewise, it is important to establish guidelines and standards to accurately measure and benchmark the performance of dysarthric ASR systems in order to ensure their usefulness and effectiveness in real-world applications. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

SeerahGPT: Retrieval Augmented Generation based Large Language Model 18

SeerahGPT: Retrieval Augmented Generation based Large Langua...

引用

18th International Conference on Open Source Systems and Technologies, ICOSST 2024

作者： Obaid, Surayya Bawany, Narmeen Zakaria Center for Computing Research Department of Computer Science and Software Engineering Jinnah Univesity for Women Karachi Pakistan

ISBN: (纸本)9798331508692

Large Language Models(LLMs) have become widely recognized in recent years for their exceptional performance in language generation capabilities. As a result, an unprecedented rise is seen in its use cases in various domains specifically involving Natural Language Processing(NLP). These models however perform suboptimally when exploited in the field of studies where authenticity of the generated content is a critical aspect. One such domain is usage of LLM for exploration of the life of Prophet Muhammad S.A.W(commonly referred to as Seerah). It is of utmost significance to ensure the authenticity and reliability in the sources used and reported by the LLM due to the sensitive nature of the domain. The contemporary LLMs, however, lack the explainability in their response due to their inherent black-box nature. In our study, we have presented a novel LLM named SeerahGPT that addresses this challenge with the help of retrieval-augmented generation (RAG). This technique enables the model to utilize both parametric and nonparametric memories for generating response of queries. Our model, built on the Llama-2-7b architecture, employs Sentence Transformer embedding to effectively retrieve relevant information. The model's capabilities are augmented by integrating it with a corpus having Islamic texts such as the Quranic translation and Hadith collections, and historical accounts. The model's performance is benchmarked against its base model using both quantitative and qualitative metrics. The comparative analysis with Llama-2-7b revealed that SeerahGPT incorporation with external knowledge sources, provided more authentic and verifiable responses, despite the others exhibiting greater fluency. Performance metrics such as BLEU, ROUGE, and METEOR indicated SeerahGPT's better accuracy and contextual handling. This study paves way for analysis of such sensitive domains in more efficient way that can be utilized in other complex domains such as Islamic theology and Fiqh or legal

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

TrafficNet: A Hybrid CNN-FNN Model for Analysis of Traffic Accidents in Seoul

引用

Journal of Computing Science and engineering 2023年第4期17卷 182-194页

作者： Mustafa, Ghulam Cho, Seong-je Hwang, Youngsup Department of Computer Engineering Sun Moon University Asan Korea Republic of Department of Software Science Dankook University Yongin Korea Republic of

The escalating global trend of traffic accidents with subsequent loss of lives is a matter of grave concern that requires immediate attention. Extensive efforts have been made to mitigate accidents and develop effective prevention strategies. This research paper focuses on a comprehensive analysis of traffic accidents in Seoul, aiming to identify factors and accident types that contribute to increased severity. To achieve this, we introduced a new approach called "TrafficNet: A Hybrid CNN-FNN Model" to evaluate effects of various parameters on the severity of traffic accidents in Seoul. Our main objective was to classify accidents into four distinct levels of severity: minor injuries, slander, fatalities, and injury reports. To assess the effectiveness of our proposed model, we conducted comprehensive experiments using publicly available traffic accident data provided by Seoul Metropolitan Government. These experiments involved six different models, including five machine learning models (decision tree, random forest, k-nearest neighbor, gradient boosting, and support vector machine) and one deep learning model (multilayer perceptron). The proposed model demonstrated exceptional performance, surpassing all other models and previous research findings using the same dataset. On the test dataset, TrafficNet achieved an impressive accuracy of 93.98% with a precision of 94.31%, a recall of 93.98%, and an F1-score of 93.89%. Copyright 2023. The Korean Institute of Information Scientists and Engineers

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Cutting-Edge AI-Driven Higher Educational and Career Advisory Platform

Cutting-Edge AI-Driven Higher Educational and Career Advisor...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Dewasurendra, S.V. Udunuwara, U.K.C. Wanniarachchi, T.T. Panditharathne, P.D.R.L. Thelijjagoda, Samantha Dissanayaka, Kapila Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798331543617

Sri Lankan students, especially those from rural and low-income backgrounds, face significant challenges in accessing higher education, including university applications, career planning, and financial aid. This research introduces an AI-powered platform designed to provide personalized assistance through university course recommendations, career guidance, financial aid information, and AI-generated mock aptitude tests. The platform employs Graph Neural Networks (GNNs) for course recommendations, Recurrent Neural Networks (RNNs) for career guidance, and a Retrieval-Augmented Generation (RAG) model for financial aid navigation. Additionally, AI-driven algorithms with Optical Character Recognition (OCR) technology support exam preparation. Data from students and universities informed model training, and evaluations showed high accuracy and user satisfaction across components. Results indicated that the platform effectively aligns educational resources with students' academic and career goals, promoting greater educational accessibility and support for underserved Sri Lankan students. © 2024 IEEE.

关键词： Graph neural networks

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：