检索结果-内蒙古大学图书馆

33rd Meeting of Computational Linguistics in the Netherlands, CLIN 2023

作者： Delobelle, Pieter Remy, François Department of Computer Science Leuven.AI KU Leuven Belgium Internet and Data science Lab Ghent University Belgium

Pre-training large transformer-based language models on gigantic corpora and later repurposing them as base models for finetuning on downstream tasks has proven instrumental to the recent advances in computational linguistics. However, the prohibitively high cost associated with pretraining often hampers the regular updates of base models to incorporate the latest linguistic developments. To address this issue, we present an innovative approach for efficiently producing more powerful and up-to-date versions of RobBERT, our series of cutting-edge Dutch language models, by leveraging existing language models designed for high-resource languages. Unlike the prior versions of RobBERT, which relied on the training methodology of RoBERTa but required a fresh weight initialization, our two RobBERT-2023 models (base and large) are entirely initialized using the RoBERTa-family of models. To initialize an embedding table tailored to the newly devised Dutch tokenizer, we rely on a token translation strategy introduced by Remy et al. (2023). Along with our RobBERT-2023 release, we deliver a freshly pre-trained Dutch tokenizer using the latest version of the Dutch OSCAR corpus. This corpus incorporates new high-frequency terms, such as those related to the COVID-19 pandemic, cryptocurrencies, and the ongoing energy crisis, while mitigating the inclusion of previously over-represented terms from adult-oriented content. To assess the value of RobBERT-2023, we evaluate its performance using the same benchmarks employed for the state-of-the-art RobBERT-2022 model, as well as the newly-released Dutch Model Benchmark. Our experimental results demonstrate that RobBERT-2023 not only surpasses its predecessor in various aspects but also achieves these enhancements at a significantly reduced training cost. This work represents a significant step forward in keeping Dutch language models up-to-date and demonstrates the potential of model conversion techniques for reducing the environmental

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

HFANet: Hierarchical Feature-Enhanced Aggregation Network for Camouflaged Object Detection

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Zhang, Xinchao Zhu, Hengliang Mao, Guojun Department of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China

Camouflaged object detection (COD) aims to identify target objects in complex scenes with extremely high similarity to their surroundings, and has significant applications in military, medical, and other fields. This paper proposes a hierarchical feature-enhanced aggregation network (HFANet) for COD, aiming to address the situations that the target object is highly similar to the background. First, we adopt the pyramid vision Transformer model as the backbone for feature extraction. On top of it, the object-region amplification module and deep interaction guidance module are stacked to enhance the perception of camouflaged objects in complex scenes. Second, an enhanced receptive field module is designed to improve edge perception of camouflaged objects. At last, a multi-scale interactive fusion module is designed by cross-scale connection through adjacent layers, effectively improving the accuracy of COD. The proposed method is evaluated on three challenging datasets: CAMO, CHAMELEON, and COD10K. Evaluation results demonstrate superior performance compared to the state-of-the-art methods. © Shanghai Jiao Tong University 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Low-Resource Machine Translation Systems 7

Benchmarking Low-Resource Machine Translation Systems

引用

7th Workshop on Technologies for Machine Translation of Low-Resource Languages, LoResMT 2024 at ACL 2024

作者： da Silva, Ana Alexandra Morim Srivastava, Nikit Ngoli, Tatiana Moteu Röder, Michael Moussallem, Diego Ngomo, Axel-Cyrille Ngonga DICE Group Department of Computer Science Paderborn University Germany Jusbrasil Data Science Team Rio de Janeiro Brazil

ISBN: (纸本)9798891761490

Assessing the performance of machine translation systems is of critical value, especially to languages with lower resource availability. Due to the large evaluation effort required by the translation task, studies often compare new systems against single systems or commercial solutions. Consequently, determining the best-performing system for specific languages is often unclear. This work benchmarks publicly available translation systems across 4 datasets and 26 languages, including low-resource languages. We consider both effectiveness and efficiency in our evaluation. Our results are made public through BENG-a FAIR benchmarking platform for Natural Language Generation tasks. © 2024 Association for Computational Linguistics.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Secure multimedia communication: advanced asymmetric key authentication with grayscale visual cryptography

引用

Mathematical Biosciences and Engineering 2024年第3期21卷 4762-4778页

作者： Liu, Tao Vairagar, Shubhangi Adagale, Sushadevi Karthick, T. Karunya, Catherine Esther Blesswin, A. John Mary, G. Selva Tianjin Sino-German University of Applied Sciences Tianjin300350 China Department of Artificial Intelligence and Data Science Dr. D. Y. Patil Institute of Technology Pimpri Pune411018 India Department of Computer Engineering KJEI's Trinity Academy of Engineering Pune411048 India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Computer Science and Engineering School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Directorate of Learning and Development SRM Institute of Science and Technology Kattankulathur603203 India

The secure authentication of user data is crucial in various sectors, including digital banking, medical applications and e-governance, especially for images. Secure communication protects against data tampering and forgery, thereby bolstering the foundation for informed decision-making, whether managing traffic, enhancing public safety, or monitoring environmental conditions. Conventional visual cryptographic protocols offer solutions, particularly for color images, though they grapple with challenges such as high computational demands and reliance on multiple cover images. Additionally, they often require third-party authorization to verify the image integrity. On the other hand, visual cryptography offers a streamlined approach. It divides images into shares, where each pixel represented uniquely, thus allowing visual decryption without complex computations. The optimized multi-tiered authentication protocol (OMTAP), which is integrated with the visual sharing scheme (VSS), takes secure image sharing to the next level. It reduces share count, prioritizes image fidelity and transmission security, and introduces the self-verification of decrypted image integrity through asymmetric key matrix generators, thus eliminating external validation. Rigorous testing has confirmed OMTAP's robustness and broad applicability, thereby ensuring that decrypted images maintain their quality with a peak signal-to-noise ratio (PSNR) of 40 dB and full integrity at the receiver's end. © 2024 American Institute of Mathematical sciences. All rights reserved.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

Offline Signature Forgery Detection Based on Geometric Measures Using Tensorflow Model 2

Offline Signature Forgery Detection Based on Geometric Measu...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Lakshmi, A. Anagha Reddy, G. Siddarth Reddy, M. Sowmya Kathirisetty, Nikhila Vardhaman College of Engineering Department of Information Technology Hyderabad India Vardhaman College of Engineering Department of Computer Science and Data Science Hyderabad India

ISBN: (纸本)9798350370188

The most popular method for identifying people from past signatures is through signatures. By using a TensorFlow model which is a deep learning algorithm, we created a new system to verify signatures on bank checks and other important documents. The main point is that a signature plays a crucial role in banking because it is necessary for money withdrawals. In banks there are no efficient systems to check if a signature is real or fake as it is the most frequently used bio-metric method to verify a person's identity. This can lead to bank fraud. The Project will make it easier to tell whether a signature is genuine or not. Online and offline verification are the two methods of verification. We're going to use various geometric measurements to accomplish offline verification. Python libraries were employed in this case. In the testing phase the model's performance is evaluated. To protect the integrity and legitimacy of handwritten signatures, signature forgery detection is an essential responsi-bility. The capacity to recognize forged signatures with accuracy has grown more important as a result of the rise in digital transactions and the growing reliance on electronic documents. The act of duplicating or copying another person's signature with the purpose to deceive or gain illegal access is known as signature forging. Manually spotting these forgeries can be difficult because expert forgers are adept at closely imitating the visual style and traits of real signatures. Therefore, there has been a lot of interest in the development of automated methods and algorithms to identify fake signatures. © 2024 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

A Concise and Varied Visual Features-Based Image Captioning Model with Visual Selection

引用

computers, Materials & Continua 2024年第11期81卷 2873-2894页

作者： Alaa Thobhani Beiji Zou Xiaoyan Kui Amr Abdussalam Muhammad Asim Naveed Ahmed Mohammed Ali Alshara School of Computer Science and Engineering Central South UniversityChangsha410083China Electronic Engineering and Information Science Department University of Science and Technology of ChinaHefei230026China EIAS Data Science Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia College of Computer and Information Sciences Prince Sultan UniversityRiyadh11586Saudi Arabia College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic UniversityRiyadh11432Saudi Arabia

Image captioning has gained increasing attention in recent *** characteristics found in input images play a crucial role in generating high-quality *** studies have used visual attention mechanisms to dynamically focus on localized regions of the input image,improving the effectiveness of identifying relevant image regions at each step of caption ***,providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these ***,this leads to enhanced captioning network *** light of this,we present an image captioning framework that efficiently exploits the extracted representations of the *** framework comprises three key components:the Visual Feature Detector module(VFD),the Visual Feature Visual Attention module(VFVA),and the language *** VFD module is responsible for detecting a subset of the most pertinent features from the local visual features,creating an updated visual features ***,the VFVA directs its attention to the visual features matrix generated by the VFD,resulting in an updated context vector employed by the language model to generate an informative *** the VFD and VFVA modules introduces an additional layer of processing for the visual features,thereby contributing to enhancing the image captioning model’s *** the MS-COCO dataset,our experiments show that the proposed framework competes well with state-of-the-art methods,effectively leveraging visual representations to improve *** implementation code can be found here:https://***/althobhani/VFDICM(accessed on 30 July 2024).

关键词： Visual attention image captioning visual feature detector visual feature visual attention

来源：评论

学校读者我要写书评

暂无评论

Bitcoin price prediction based on financial data, technical indicators, and news headlines sentiment analysis using CNN and GRU deep learning algorithms 3

Bitcoin price prediction based on financial data, technical ...

引用

3rd International Conference on Distributed Computing and High Performance Computing, DCHPC 2024

作者： Arjmand, Masoud Kazeminia, Saman Sajedi, Hedieh University of Tehran Kish International Campus Department of Computer Engineering Kish Iran NHL Stenden University of Applied Science Department of Computer Vision and Data Science Leeuwarden Netherlands University of Tehran Department of Mathematics Statistics and Computer Science Tehran Iran

ISBN: (纸本)9798350381580

Bitcoin is the leading cryptocurrency with the highest market value among digital currencies. Therefore, predicting the value of Bitcoin can help to understand the entire cryptocurrency market. However, Bitcoin has had a lot of price fluctuations since its inception. In this paper, we are going to forecast the price of Bitcoin using news headline analysis, technical analysis indicators, and historical financial data. The news headlines used in this article are scraped from the Cointelegraph news website, which contains 3988 news headlines related to Bitcoin between 2/7/2020 and 3/8/2021. A transformer pre-trained model on cryptocurrency-related texts called CryptoBERT, which is a BERT-based sentiment analysis model, has been used to analyze the textual data. Also, a novel hybrid 2DCNN-GRU deep learning model has been used to predict the price. To adjust the parameters of this model, a parameter tuning method based on orthogonal arrays called the Taguchi method has been employed. Finally, to examine the proposed model's efficiency, the obtained results have been compared with other deep learning models from the literature review that used text data to predict bitcoin prices. The results show that this model outperformed other models in terms of MAE criterion, while in the other three criteria, namely MSE, RMSE and MAPE, it still demonstrated good results. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An Architecture for Dynamic Load Balancing in Cloud Environment 2

An Architecture for Dynamic Load Balancing in Cloud Environm...

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Lokesh, Gudivada Baseer, K.K. Dept. of Computer Science and Engineering Tirupati India Department of Data Science Tirupati India

ISBN: (纸本)9798350347579

Clouds are highly customizable infrastructures that offer a platform as a service and let customers subscribe on a pay-as-you-go basis to their requirements. The straightforward service-oriented cloud computing model is gaining popularity around the world. The number of people using the Cloud is constantly growing. Clouds use modern data centers to manage a massive number of users. The reliability of the Cloud depends on load balancing. Balancing virtual machine loads lowers energy consumption and task rejections by optimizing resource utilization. One can increase performance while using fewer resources using load balancing, resource management, quality of service, etc. The difficulty of overloading and underloading virtual machines in cloud computing can be lessened by load balancing in the *** research study thoroughly examined the load-balancing algorithms found in the literature. First, the traditional approaches are analyzed before moving on to more recent work on load balancing with heterogeneous techniques. Along with the tools available for the current investigation, various metrics are used to evaluate the load-balancing algorithms. The proposed article will primarily serve to assist in the development of new algorithms in the future. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Diabetes Prediction Models for Enhanced Health data Processing 5th

Optimizing Diabetes Prediction Models for Enhanced Health Da...

引用

5th International Symposium on Signal and Image Processing, ISSIP 2024

作者： Chatterjee, Soham Gupta, Ritwika Das Ramadani, Lauresha Department of Statistics and Data Science CHRIST Deemed to be University Bangalore India Department of Computer Science AAB College Pristina Kosovo

ISBN: (纸本)9789819795147

Diabetes prediction is crucial for early intervention and personalized treatment. This study uses a multimodal strategy, including prediction algorithms, downsampling, feature engineering, exploratory data analysis (EDA), cross-validation, and classification techniques. EDA is used to understand diabetes-specific features, while downsampling ensures fair representation of instances with and without diabetes. Classification algorithms categorize people into appropriate diabetes risk groups using machine learning. Cross-validation evaluates predictive models in various data scenarios. The study emphasizes the value of specialized methods and domain-specific expertise in diabetes prediction, emphasizing the need for accurate risk assessment in healthcare decision-making and the potential for proactive interventions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： data reduction

来源：评论

学校读者我要写书评

暂无评论

Novel Spectral Algorithms for the Partial Credit Model 41

Novel Spectral Algorithms for the Partial Credit Model

引用

41st International Conference on Machine Learning, ICML 2024

作者： Nguyen, Duc Zhang, Anderson Ye Department of Computer & Information Science University of Pennsylvania United States Department of Statistics & Data Science Wharton School University of Pennsylvania United States

The Partial Credit Model (PCM) of Andrich (1978) and Masters (1982) is a fundamental model within the psychometric literature with wide-ranging modern applications. It models the integer-valued response that a subject gives to an item where there is a natural notion of monotonic progress between consecutive response values, such as partial scores on a test and customer ratings of a product. In this paper, we introduce a novel, time-efficient and accurate statistical spectral algorithm for inference under the PCM model. We complement our algorithmic contribution with in-depth non-asymptotic statistical analysis, the first of its kind in the literature. We show that the spectral algorithm enjoys the optimal error guarantee under three different metrics, all under reasonable sampling assumptions. We leverage the efficiency of the spectral algorithm to propose a novel EM-based algorithm for learning mixtures of PCMs. We perform comprehensive experiments on synthetic and real-life datasets covering education testing, recommendation systems, and financial investment applications. We show that the proposed spectral algorithm is competitive with previously introduced algorithms in terms of accuracy while being orders of magnitude faster. Copyright 2024 by the author(s)

关键词：

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：