检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Huang, Yi-Hua He, Yue Yuan, Yu-Jie Lai, Yu-Kun Gao, Lin Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences China School of Computer and Control Engineering University of Chinese Academy of Sciences China School of Computer Science & Informatics Cardiff University United Kingdom

3D scene stylization aims at generating stylized images of the scene from arbitrary novel views following a given set of style examples, while ensuring consistency when rendered from different views. Directly applying methods for image or video stylization to 3D scenes cannot achieve such consistency. Thanks to recently proposed neural radiance fields (NeRF), we are able to represent a 3D scene in a consistent way. Consistent 3D scene stylization can be effectively achieved by stylizing the corresponding NeRF. However, there is a significant domain gap between style examples which are 2D images and NeRF which is an implicit volumetric representation. To address this problem, we propose a novel mutual learning framework for 3D scene stylization that combines a 2D image stylization network and NeRF to fuse the stylization ability of 2D stylization network with the 3D consistency of NeRF. We first pre-train a standard NeRF of the 3D scene to be stylized and replace its color prediction module with a style network to obtain a stylized NeRF. It is followed by distilling the prior knowledge of spatial consistency from NeRF to the 2D stylization network through an introduced consistency loss. We also introduce a mimic loss to supervise the mutual learning of the NeRF style module and fine-tune the 2D stylization decoder. In order to further make our model handle ambiguities of 2D stylization results, we introduce learnable latent codes that obey the probability distributions conditioned on the style. They are attached to training samples as conditional inputs to better learn the style module in our novel stylized NeRF. Experimental results demonstrate that our method is superior to existing approaches in both visual quality and long-range consistency. Copyright © 2022, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

VCSE: Time-Domain Visual-Contextual Speaker Extraction Network

arXiv

引用

arXiv 2022年

作者： Li, Junjie Ge, Meng Pan, Zexu Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Japan Advanced Institute of Science and Technology Ishikawa Japan

Speaker extraction seeks to extract the target speech in a multi-talker scenario given an auxiliary reference. Such reference can be auditory, i.e., a pre-recorded speech, visual, i.e., lip movements, or contextual, i.e., phonetic sequence. References in different modalities provide distinct and complementary information that could be fused to form top-down attention on the target speaker. Previous studies have introduced visual and contextual modalities in a single model. In this paper, we propose a two-stage time-domain visual-contextual speaker extraction network named VCSE, which incorporates visual and self-enrolled contextual cues stage by stage to take full advantage of every modality. In the first stage, we pre-extract a target speech with visual cues and estimate the underlying phonetic sequence. In the second stage, we refine the pre-extracted target speech with the self-enrolled contextual cues. Experimental results on the real-world Lip Reading Sentences 3 (LRS3) database demonstrate that our proposed VCSE network consistently outperforms other state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

MIKIDQD: Machine Intelligence and Knowledge Infused Duplicate Question Detection

MIKIDQD: Machine Intelligence and Knowledge Infused Duplicat...

引用

Augmented Intelligence and Sustainable Systems (ICAISS), International Conference on

作者： Vaibhava Lakshmi R Gerard Deepak Santhanavijayan A Radha S Department of Computer Technology Madras Institute of Technology Chennai India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Tiruchirapalli India School of Advanced Sciences Vellore Institute of Technology Chennai India

ISBN: (纸本)9781665489638

Quora is a flourishing online question answer forum where millions of users post questions and answer questions in the subjects they have knowledge. A plethora of questions are posted by users and some of them can be similarly worded. This would make it tedious for the users as answering similarly worded questions can be time consuming. Hence, there is a need to detect similarly worded questions or duplicate questions. This research work proposes a MIKIDQD framework for detecting duplicate questions in the Quora forum by using the Quora dataset. The knowledge-centric, ontologybased and semantically-driven strategy incorporated in the proposed model surpasses the other baseline models in terms of the performance measures. The proposed model yields the highest accuracy value of 98.07% and the least False Negative Rate of 0.01 indicating the best performance.

关键词： Cloud computing Computational modeling Question answering (information retrieval) Problem-solving Machine intelligence

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Curation from Text Via Ontologies

Knowledge Graph Curation from Text Via Ontologies

引用

Augmented Intelligence and Sustainable Systems (ICAISS), International Conference on

作者： Vaibhava R Lakshmi Gerard Deepak A Santhanavijayan S Radha Department of Computer Technology Madras Institute of Technology Chennai India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Tiruchirapalli India School of Advanced Sciences Vellore Institute of Technology Chennai India

ISBN: (纸本)9781665489638

Huge-scale knowledge graphs have become widespread on the web and are useful for a plethora of tasks. Knowledge graphs which are powered by machine learning use Natural Language Processing to build an extensive view of nodes, edges and labels by semantic enrichment in order to automate tasks like data structuring, text analysis and merging of data models. This research study put forth a semantically-driven and knowledge-centric strategy, which integrates machine learning and semantic inference for curating knowledge graphs from text using ontologies. The proposed framework amalgamates knowledge from the sources: Wikidata, DBpedia and Mediawiki to instill heterogeneity. The proffered framework transcends the baseline models by yielding an accuracy value of 98.22Cumulative Gain (NDCG) value of 0.97.

关键词： Knowledge engineering Text analysis Semantics Merging Machine learning Ontologies Fish

来源：评论

学校读者我要写书评

暂无评论

A transactional-behavior-based hierarchical gated network for credit card fraud detection

引用

IEEE/CAA Journal of Automatica Sinica 2025年

作者： Xie, Yu Zhou, MengChu Liu, Guanjun Wei, Lifei Zhu, Honghao De Meo, Pasquale College of Information Engineering Shanghai Maritime University Shanghai201306 China School of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou310018 China Helen and John C. Hartmann Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science Tongji University Shanghai201804 China College of Computer Science and Information Engineering Bengbu University Bengbu233030 China Department of Ancient and Modern Civilizations University of Messina Messina98166 Italy

The task of detecting fraud in credit card transactions is crucial to ensure the security and stability of a financial system, as well as to enforce customer confidence in digital payment systems. Historically, credit card companies have used rule-based approaches to detect fraudulent transactions, but these have proven inadequate due to the complexity of fraud strategies and have been replaced by much more powerful solutions based on machine learning or deep learning algorithms. Despite significant progress, the current approaches to fraud detection suffer from a number of limitations: for example, it is unclear whether some transaction features are more effective than others in discriminating fraudulent transactions, and they often neglect possible correlations among transactions, even though they could reveal illicit behaviour. In this paper, we propose a novel credit card fraud detection (CCFD) method based on a transaction behaviour-based hierarchical gated network. First, we introduce a feature-oriented extraction module capable of identifying key features from original transactions, and such analysis is effective in revealing the behavioural characteristics of fraudsters. Second, we design a transaction-oriented extraction module capable of capturing the correlation between users' historical and current transactional behaviour. Such information is crucial for revealing users' sequential behaviour patterns. Our approach, called transactional-behaviour-based hierarchical gated network model (TbHGN), extracts two types of new transactional features, which are then combined in a feature interaction module to learn the final transactional representations used for CCFD. We have conducted extensive experiments on a real-world credit card transaction dataset with an increase in average F1 between 1.42% and 6.53% and an improvement in average AUC between 0.63% and 2.78% over the state of the art. © 2025 institute of Electrical and Electronics Engineers Inc.. All right

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

CCGRID 2023: A Holistic Approach to Inclusion and Belonging

CCGRID 2023: A Holistic Approach to Inclusion and Belonging

引用

IEEE/ACM International Symposium on Cluster computing and the Grid (CCGRID)

作者： Beth Plale Preeti Malakar Meenakshi D'Souza Hemangee K. Kapoor Yogesh Simmhan Ilkay Altintas Manohar Swaminathan School of Informatics Computing and Engineering Indiana University Bloomington IN USA Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kalyanpur Kanpur India International Institute of Information Technology Bangalore Bengaluru Karnataka India Department of Computer Science and Engineering Indian Institute of Technology Guwahati Guwahati Assam India Department of Computational and Data Sciences Indian Institute of Science Bangalore India San Diego Supercomputer Center University of California San Diego MC USA Microsoft Research Lab - India Bengaluru Karnataka India

“CCGRID will act with responsibility as its primary consideration; with equity, diversity, and inclusion as its central goals.” from the CCGRID 2023 web site [1]

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vector Register Sharing Mechanism for High Performance Hardware Acceleration 30th

Vector Register Sharing Mechanism for High Performance Hard...

引用

30th International Conference on Parallel and Distributed Processing Techniques, PDPTA 2024, held as part of the World Congress in computer science, computer engineering and Applied computing, CSCE 2024

作者： Tanaka, Tomoaki Kato, Michiya Osana, Yasunori Miyoshi, Takefumi Tada, Jubee Tanaka, Kiyofumi Nakajo, Hironori Department of Electrical Engineering and Computer Science Graduate School of Engineering Tokyo University of Agriculture and Technology 2-24-16 Nakacho Tokyo Koganei-shi184-8588 Japan Research and Education Institute for Semiconductors and Informatics Kumamoto University 2-39-1 Kurokami Kumamoto Chuo-ku860-8555 Japan WasaLabo LLC. K-2 Buransyu 6-5-20 Minaminaruse Tokyo Machida-shi194-0045 Japan Graduate School of Science and Engineering Yamagata University 1-4-12 Kojirakawa-machi Yamagata Yamagata-shi990-8560 Japan Japan Advanced Institute of Science and Technology 1-1 Asahidai Ishikawa Nomi923-1292 Japan Division of Advanced Information Technology Computer Science Institute of Engineering Tokyo University of Agriculture and Technology 2-24-16 Nakacho Tokyo Koganei-shi184-8588 Japan

ISBN: (纸本)9783031856372

In recent years, demand for data-parallel processing has been growing, and this parallelism often appears in AI processes. One method to accelerate these processes is using DSA, domain-specific architecture. A common data transfer method on DSA is DMA, which is direct memory access. There are several studies on DMA-based accelerators. However, few studies focus on data transfer methods. In this paper, a vector register-sharing mechanism has been proposed as a new data transfer method. Our proposed mechanism is named "SHAVER". In this mechanism, a part of vector registers is directly shared with an accelerator. An open-source RISC-V vector co-processor is used to evaluate the mechanism’s potential. It has been implemented on an FPGA and a simulator for the evaluations. The results indicate the possibility of the proposal mechanism to achieve a maximum of 7.13% speedup over DMA transfer. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

A Survey on Brain Tumor Diagnosis and Edema Detection Based on Machine Learning

A Survey on Brain Tumor Diagnosis and Edema Detection Based ...

引用

International Laser technology and Optics Symposium in Conjunction with Photonics Meeting 2020, ILATOSPM 2020

作者： Neamah, K. Mohamed, F. Adnan, M.M. Thajeel, S.A. Faculty of Engineering School of Computing University Technology of Malaysia Johor Bahru Malaysia UTM-IRDA MaGICX Institute of Human Centered Engineering Universiti Teknologi Malaysia Johar Bahru Malaysia School of Computing Faculty of Engineering University Technology of Malaysia Johor Bahru Malaysia Islamic University Najaf Iraq Computer Science Department College of Education Mustansiriyah University Baghdad Iraq

Early brain tumor diagnosis has a significant role in reducing the risk of disease, as well as led to get better treatment results. Usually, magnetic resonance imaging (MRI) images are evaluated manually through visual inspection, which is difficult, time-consuming and often erroneous;this process is performed by radiologists or clinical experts, and its accuracy depends on their experience. Recently, computer-aided diagnosis (CAD) becomes very essential to overcome these limitations. This paper provides a comprehensive assessment of the existing techniques and methodologies for automated detection of brain tumor coupled with oedema detection methods utilisation, with an emphasis on machine learning models. Moreover, this paper provides an analysis of the integrated procedure that pertains to the retrieval of brain pictures by identifying particular data sets in the procedure to recognise the stipulated attributes. © Published under licence by IOP Publishing Ltd.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Detecting and Locating Image Forgeries with Deep Learning

Detecting and Locating Image Forgeries with Deep Learning

引用

Contemporary computing and Communications (InC4), IEEE International Conference on

作者： Kamred Udham Singh Ankur Rao Ankit Kumar Neeraj Varshney Pushpendra Singh Chundawat Teekam Singh School of Computing Graphic Era Hill University Dehradun India Geetanjali Institute of Technical Studies (GITS) Udaipur Rajashan Department of Information Technology Guru Ghasidas Vishwavidyalaya Bilaspur Chhattisgarh India Department of Computer Engineering & Applications GLA University Mathura UP India SS engineering College Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383669

It is becoming more important to have reliable methods for identifying picture forgeries, particularly passive forging techniques like copy-move and splicing, since the proliferation of digital images across a variety of platforms has raised the urgency of the situation. The purpose of this research is to explicitly target passive forgery tactics by presenting a unique strategy that makes use of deep learning approaches for the purpose of accurately identifying modified areas inside photographs. The methodology that we have suggested makes use of Mobile Net and ResNet as feature extraction networks. It does this by extracting rich representations from picture data in order to identify complicated patterns that are suggestive of possible manipulations, such as copy-move and splicing manipulations. We make use of Mask R-CNN, which is a cutting-edge instance segmentation model, in order to precisely localize and quantify forged areas. This allows us to calculate the proportion of changed material that is included inside photos.

关键词： Deep learning Instance segmentation Splicing Digital images Computational modeling Feature extraction Forgery

来源：评论

学校读者我要写书评

暂无评论

Forecasting Stock Prices with Long Short-Term Memory Networks

Forecasting Stock Prices with Long Short-Term Memory Network...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Kamred Udham Singh Umang Deep Mishra Amrita Verma Lalan Kumar Teekam Singh Neeraj Varshney School of Computing Graphic Era Hill University Dehradun India Unique Institute of Management & Technology Muradnagar Dr. C. V. Raman University Kota Bilaspur GL Bajaj Institute of Technology and Management Greater Noida Uttar Pradesh India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Engineering & Applications GLA University Mathura UP India

The discipline of forecasting stock prices via Long Short-Term Memory Networks (LSTMs) has evolved into a carefully cultivated area of study, attracting the attention of knowledgeable academics and experienced industry experts. This is because the field has developed into a meticulously nurtured area. The exact prediction of market fluctuations has captivated clever investors, who must carefully deploy their assets, heightening the importance of this endeavour. Furthermore, the need for investors to carefully distribute their assets has emphasised the importance of this endeavour. To achieve the maximum level of financial expertise, it is crucial to develop the skill of precisely forecasting the intricate dynamics of the stock market. This research aims to develop a prediction framework utilising the capabilities of the Recurrent Neural Network (RNN) architecture, with a specific focus on the Long Short-Term Memory (LSTM) paradigm. This move shows a deliberate focus on LSTM’s inherent ability to analyse and navigate the challenges that may arise in predicting future stock prices. Our main focus is deciphering the complex factors that will influence the future movements of the stock price. We aim to uncover mysteries that have been kept hidden and offer deep insights. The main objective of this endeavour is to equip investors with the essential resources to facilitate informed decision-making, considering it a crucial aspect of its purpose. We aim to utilise LSTM capabilities to gain valuable insights that will enhance the decision-making process for stakeholders. We believe that striving for this objective will empower investors to rise above uncertainty, make astute decisions, and steer their financial futures with wisdom and precision.

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：