检索结果-内蒙古大学图书馆

44th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2023

作者： Nikolov, I. Computer Graphics Group Faculty of Architecture Design and Media Technology Aalborg University Denmark

ISBN: (纸本)9783038682110

Generating 3D object variations through style transfer models applied to their textures is an easy way for creating content for games and XR applications. Most workflows focus on either generating albedo textures only without changing the underlying surface and not touching the underlying surface or transforming the 3D object directly, which is computationally and resource-heavy. In this paper, we present an initial exploration of an in-between solution that aims to combine the style transfer of albedo textures with the generation of additional maps, such as normal, displacement, and roughness. The results show that the pipeline can generate variations based on different styles, which would enable the addition of smaller 3D-style surface features to objects without transforming their meshes. The project code and generated textures will be available at https://***/IvanNik17/3D-Assets-From-2D-Style-Transfer. © 2023 The Authors.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

When Do Neuromorphic Sensors Outperform cameras? Learning from Dynamic Features 57

When Do Neuromorphic Sensors Outperform cameras? Learning fr...

引用

57th Annual Conference on Information Sciences and Systems, CISS 2023

作者： Deniz, Daniel Ros, Eduardo Fermller, Cornelia Barranco, Francisco University of Granada Dep. of Computer Architecture and Technology Spain University of Maryland Perception and Robotics Group United States

ISBN: (纸本)9781665451819

Visual event sensors only output data when changes in the scene happen at very high frequency. This allows for smartly compressing the scene and thus, enabling real-time operation. Despite these advantages, works in the literature have struggled to show a niche for these event-driven approaches compared to conventional sensors, especially when focusing on accuracy performance. In this work, we show a case that fully exploits event sensor advantages: for manipulation action recognition, learning events achieves superior accuracy and time performance. The recognition of manipulation actions requires extracting and learning features from the hand pose and trajectory and the interaction with the object. As shown in our work, approaches based on event sensors are the best fit for extracting these dynamic features contrarily to conventional approaches based on full frames, which mostly extract spatial features and need to reconstruct the dynamics from sequences of frames. Finally, we show how using a tracker to extract the features to be learned only around the hand, we obtain an approach that is scene- and almost object-agnostic and achieves good time performance with a very limited impact in accuracy. © 2023 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Effect of Environment Size on Spatial Perception in Virtual Reality 6

Effect of Environment Size on Spatial Perception in Virtual ...

引用

6th International Conference on computer-Human Interaction Research and Applications, CHIRA 2022

作者： Bach, Morten Trier Jensen, Poul Anker Lucaci, Andrei Iuliu Pupczyk, Damian Grzegorz Madsen, Claus Brøndgaard Computer Graphics Group Department of Architecture and Media Technology Aalborg University Aalborg Denmark

ISBN: (纸本)9789897586095

A trend of distance underestimations in Virtual Reality (VR) is well documented, but the reason still remains unclear. Therefore, this paper investigates the effect of differently sized Virtual Environments (VEs) on egocentric distance perception in VR as a potential influence. Verbal assessment, blind walking, and our own proposed method: walk and assess, were compared in an experiment, and blind walking was found to be the most accurate. A virtual replica of a real-life location was created as a transitional environment, while small (15m2), medium (35m2) and large (95m2) rooms were created to investigate the effect of VE size on spatial perception in VR. To establish the differences in estimations between the real world and VR when using blind walking, a study was conducted with the virtual replica and its real life counterpart at distances between 1 and 10 meters. Following this, the three distinct room sizes were used in an experiment to investigate the effect of the size of rooms on spatial perception in VR. The findings showed consistent underestimates of distances, and a trend for underestimation to grow as the distance grows was observed. Similarly, underestimates grew with the size of the environment. Copyright © 2022 by SCITEPRESS - Science and technology Publications, Lda. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Detecting Android Malware with Convolutional Neural Networks and Hilbert Space-Filling Curves

引用

SN computer Science 2024年第7期5卷 810页

作者： Mbungang, Benedict Ngaibe Ali Wacka, Joan Beri Tchakounte, Franklin Polatidis, Nikolaos Nlong II, Jean Michel Tieudjo, Daniel Department of Mathematics and Computer Science University of Ngaoundere Ngaoundere Cameroon Cybersecurity with Computational and Artificial Intelligence Research Group University of Ngaoundere Ngaoundere Cameroon Department of Computer Science University of Buea Buea Cameroon School of Architecture Technology and Engineering University of Brighton Brighton United Kingdom

computer vision techniques have advanced greatly in recent years through deep learning, achieving unprecedented performance. This has motivated applying deep learning to malware detection through image-based approaches to circumvent extensive feature engineering for diverse threats. However, existing work converting Android binaries to rectangular images neglects the intrinsic byte sequence structure, introducing spurious spatial relationships that weaken detection accuracy. To address this, space-filling curves have mapped binaries to images while preserving ordering. This paper proposes a novel method using Hilbert space-filling curves to visualize and classify Android apps. Bytecode is extracted from Dalvik Executable (DEX) files and transformed to grayscale images via Hilbert coding for model training. Additionally, a novel and balanced image dataset is proposed consisting of Hilbert transformations for 4995 benign and 4995 malicious Android apps randomly sampled from the AndroZoo repository. Experiments using this dataset evaluated pre-trained InceptionV3, VGG16, ResNet50 and EfficientNetB0 via transfer learning. A custom Convolutional Neural Network (CNN) was also trained from scratch. InceptionV3 achieved the highest performance at 97.99% accuracy, 98.50% precision, 97.50% recall and 97.99% F1-score. Comparative assessment with previous image-based malware detection research indicates our approach outperforms state-of-the-art approaches. By leveraging Hilbert space-filling curves to map binaries to images while preserving sequential relationships, detection accuracy is improved over methods introducing extraneous spatial representations. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Android Hilbert space-filling curve Image Malware detection

来源：评论

学校读者我要写书评

暂无评论

Light the Sprite: Pixel Art Dynamic Light Map Generation

Light the Sprite: Pixel Art Dynamic Light Map Generation

引用

46th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2025

作者： Nikolov, I. Computer Graphics Group Department of Architecture Design and Media Technology Aalborg University Denmark

ISBN: (纸本)9783038682684

Correct lighting and shading are vital for pixel art design. Automating texture generation, such as normal, depth, and occlusion maps, has been a long-standing focus. We extend this by proposing a deep learning model that generates point and directional light maps from RGB pixel art sprites and specified light vectors. Our approach modifies a UNet architecture with CIN layers to incorporate positional and directional information, using ZoeDepth for training depth data. Testing on a popular pixel art dataset shows that the generated light maps closely match those from depth or normal maps, as well as from manual programs. The model effectively relights complex sprites across styles and functions in real time, enhancing artist workflows. The code and dataset are here - https://***/IvanNik17/light-sprite. © 2025 The Authors.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Autonomous Artificial Intelligence Systems for Fraud Detection and Forensics in Dark Web Environments

引用

Informatica (Slovenia) 2023年第9期47卷 51-62页

作者： Rawat, Romil Oki, Olukayode A. Chakrawarti, Rajesh Kumar Adekunle, Temitope Samson Lukose, Jose Manappattukunnel Ajagbe, Sunday Adeola Department of Computer Architecture and Communications University of Extremadura Badajoz06006 Spain Department of Information Technology East London Walter Sisulu University South Africa Department of Computer Science and Engineering Sushila Devi Bansal College Bansal Group of Institutions Indore India Colorado State University United States Department of Information Technology Walter Sisulu University South Africa Department of Computer & Industrial Production Engineering First Technical University Ibadan200255 Nigeria

Artificial Intelligence (AI) influenced technical aspects of research for generating automated intelligent behaviors covering divergent domains but has shown appreciable results when used in cyber forensic technology for crime analysis and detection. AI experts warned about possible security risks associated with algorithms and training data, as AI inherits computing features dealing with IoT-based Smart applications and autonomous transportation, and may be found to be susceptible to vulnerability and threats. The present work discusses models for analyzing terrorists related information and categorizing malicious events by covering the literature review on security risks and AI-related criminality by presenting a taxonomy of criminal behavior and signatures covering tools and criminal targets used in fraudulent activities using AI features by digital forensic techniques. We've also shown how AI may make existing crimes more potent, and that new sorts of crimes could emerge that haven't been identified previously. This study has presented a systematic structure for AI crime and dealing strategies. Furthermore, we have proposed AI forensics, a unique strategy for combating AI crime. We discovered that several concepts of DF are still not preferred in AI-based forensics after conducting a comparative examination of forensics. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Intelligent Detection of Stratigraphy Boundary Based on Deep Learning 3rd

Intelligent Detection of Stratigraphy Boundary Based on Deep...

引用

3rd China Intelligent Robotics Annual Conference, CCF CIRAC 2022

作者： Zhao, Qin Wang, Tilin Liu, Yanming Yang, Mingsong Ning, Xiaojuan Hei, Xinhong School of Civil Engineering and Architecture Xi’an University of Technology Xi’an China China Railway First Survey and Design Institute Group Ltd. Xi’an China School of Computer Science and Engineering Xi’an University of Technology Xi’an China

ISBN: (纸本)9789819903009

Robotic exploration technology is widely used in various fields such as information acquisition and topographic photography. Due to dimensional transformation and data loss in data transmission, an additional manual pre-processing is required, which is very time consuming and difficult to ensure the data accuracy. In this paper, we propose an intelligent recognition method of stratigraphy boundaries of engineering geological images based on the Hough prior deep learning network (HT-LCNN). We annotate geological drawing datasets manually at first. And then improve the binary matrix size of the original network, retrain the network on a self-constructed dataset. Finally we design experiments to compare and analyze model learning capabilities so that the optimal model can be adopted to detect negligible gaps on graphical junctions. Experimental results demonstrate that our method outform HT-LCNN in recognizing strata features. It gives the robot the capability to intelligently recognize geological images and can accurately identify over 96% of stratigraphy boundaries and junctions location, thus improving the fluidity of data in the design process and reducing time costs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stratigraphy

来源：评论

学校读者我要写书评

暂无评论

SDQ: SPARSE DECOMPOSED QUANTIZATION FOR LLM INFERENCE

arXiv

引用

arXiv 2024年

作者： Jeong, Geonhwa Tsai, Po-An Keckler, Stephen W. Krishna, Tushar School of Computer Science Georgia Institute of Technology United States Architecture Research Group NVIDIA United States

Recently, large language models (LLMs) have shown surprising performance in task-specific workloads as well as general tasks with the given prompts. However, to achieve unprecedented performance, recent LLMs use billions to trillions of parameters, which hinder the wide adaptation of those models due to their extremely large compute and memory requirements. To resolve the issue, various model compression methods are being actively investigated. In this work, we propose SDQ (Sparse Decomposed Quantization) to exploit both structured sparsity and quantization to achieve both high compute and memory efficiency. From our evaluations, we observe that SDQ can achieve 4× effective compute throughput with © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Employment Data Acquiring Method Based on WeChat Scan Code 10

Employment Data Acquiring Method Based on WeChat Scan Code

引用

10th International Conference on Systems and Informatics, ICSAI 2024

作者： Su, Bianping Wang, Yunsong He, Yantao Zhang, Longqing He, Jiayu Lin, Jieming School of Computer Guangdong University of Science & Technology Guangdong Dongguan China Xi'an International Inland Port Investment and Development Group Co. Ltd. Xi'an Chan-Ba International Port Management Committee Xi'an China School of Science Xi'an University of Architecture and Technology Xi'an China

ISBN: (纸本)9798331510138

Based on the current employment situation and methods for obtaining unemployment and employment data in China, a new method for obtaining unemployment and employment data was constructed using the Naive Bayes classification principle in machine learning by WeChat scan data of travelers. This method divides the unemployment or employment status of individuals using prior and posterior probabilities. The evaluation index values of the experimental results on the dataset demonstrate the effectiveness of the method, and the accuracy of determining the employment status of travelers through mobile phone calls has increased by 22.9%. A strategy of data preprocessing combined with this method was proposed for large-scale data and preliminary discussions were conducted. The new method of obtaining unemployment and employment data has opened up new avenues for traditional statistical data acquisition, providing strong intelligent support for the government to dynamically grasp the employment situation in real time. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Ambient intelligence for self-care and self-management

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第1期14卷 1-3页

作者： Hervás, Ramón Baños, Oresti Villalonga, Claudia Department of Technologies and Information Systems Modelling Ambient Intelligence Research Group University of Castilla-La Mancha Paseo de La Universidad 4 Ciudad Real Spain Department of Computer Architecture and Computer Technology Research Center for Information and Communication Technologies University of Granada Calle Periodista Rafael Gomez Montero 2 Granada Spain

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：