检索结果-内蒙古大学图书馆

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Changkun Liu Yukun Zhao Tristan Braud Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Division of Integrative Systems and Design The Hong Kong University of Science and Technology Hong Kong

ISBN: (数字)9798350374490

ISBN: (纸本)9798350374506

Accurate camera relocalisation is a fundamental technology for extended reality (XR), facilitating the seamless integration and persistence of digital content within the real world. Benchmark datasets that measure camera pose accuracy have driven progress in visual re-localisation research. Despite notable progress in this field, there is a limited availability of datasets incorporating Visual Inertial Odometry (VIO) data from typical mobile AR frameworks such as ARKit or ARCore. This paper presents a new dataset, MARViN, comprising diverse indoor and outdoor scenes captured using heterogeneous mobile consumer devices. The dataset includes camera images, ARCore or ARKit VIO data, and raw sensor data for several mobile devices, together with the corresponding ground-truth poses. MARViN allows us to demonstrate the capability of ARKit and ARCore to provide relative pose estimates that closely approximate ground truth within a short timeframe. Subsequently, we evaluate the performance of mobile VIO data in enhancing absolute pose estimations in both desktop simulation and user study. MARViN is available at https://***/XRIM-Lab/MarViN.

关键词： Performance evaluation Visualization Solid modeling Three-dimensional displays Pose estimation User interfaces Cameras

来源：评论

学校读者我要写书评

暂无评论

MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile AR

MobileARLoc: On-device Robust Absolute Localisation for Perv...

引用

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

Recent years have seen significant improvement in absolute camera pose estimation, paving the way for pervasive markerless Augmented Reality (AR). However, accurate absolute pose estimation techniques are computation- and storage-heavy, requiring computation offloading. As such, AR systems rely on visual-inertial odometry (VIO) to track the device’s relative pose between requests to the server. However, VIO suffers from drift, requiring frequent absolute repositioning. This paper introduces MobileARLoc, a new framework for on-device large-scale markerless mobile AR that combines an absolute pose regressor (APR) with a local VIO tracking system. Absolute pose regressors (APRs) provide fast on-device pose estimation at the cost of reduced accuracy. To address APR accuracy and reduce VIO drift, MobileARLoc creates a feedback loop where VIO pose estimations refine the APR predictions. The VIO system identifies reliable predictions of APR, which are then used to compensate for the VIO drift. We comprehensively evaluate MobileARLoc through dataset simulations. MobileARLoc halves the error compared to the underlying APR and achieves fast (80ms) on-device inference speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inscribing or Circumscribing a Histogon to a Convex Polygon

SSRN

引用

SSRN 2024年

作者： Chung, Jaehoon Bae, Sang Won Shin, Chan-Su Yoon, Sang Duk Ahn, Hee-Kap Department of Computer Science and Engineering Pohang University of Science and Technology Pohang Korea Republic of Division of Computer Science and Engineering Kyonggi University Suwon Korea Republic of Division of Computer Engineering Hankuk University of Foreign Studies Seoul Korea Republic of Department of Service and Design Engineering SungShin Women’s University Seoul Korea Republic of Graduate School of Artificial Intelligence Department of Computer Science and Engineering Pohang University of Science and Technology Pohang Korea Republic of

We consider two optimization problems of approximating a convex polygon in the plane, one by a largest inscribed histogon and the other by a smallest circumscribed histogon. An axis-aligned histogon is an axis-aligned rectilinear polygon such that every horizontal edge has an integer length. A histogon of orientation $\theta$ is a copy of an axis-aligned histogon rotated by $\theta$ in a counterclockwise direction. Our goal is to compute a largest inscribed histogon and a smallest circumscribed histogon over all orientations in $[0,\pi)$. Depending on whether the horizontal width of a histogon is predetermined or not, we consider several different versions of the problem and present exact algorithms for these versions of the inscribed histogon problem. For the circumscribed histogon problem, we present an efficient algorithm whose running time depends on the diameter and the number of vertices of the input polygon. These optimization problems belong to shape analysis, classification, and simplification, and they have applications in various cost-optimization problems. © 2024, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Support for the Co-Evolution of Meta-Models and Grammars

arXiv

引用

arXiv 2023年

作者： Zhang, Weixing Department of Computer Science & Engineering Division of Interaction Design & Software Engineering Chalmers University of Technology University of Gothenburg Gothenburg Sweden

Blended modeling is an emerging paradigm involving seamless interaction between multiple notations for the same underlying modeling language. We focus on a model-driven engineering (MDE) approach based on meta-models to develop textual languages to improve the blended modeling capabilities of modeling tools. In this thesis, we propose an approach that can support the co-evolution of meta-models and grammars as language engineers develop textual languages in a meta-model-based MDE setting. Firstly, we comprehensively report on the challenges and limitations of modeling tools that support blended modeling, as well as opportunities to improve them. Second, we demonstrate how language engineers can extend Xtext’s generator capabilities according to their needs. Third, we propose a semi-automatic method to transform a language with a generated grammar into a Python-style language. Finally, we provide a solution (i.e., GrammarOptimizer) that can support rapid prototyping of languages in different styles and the co-evolution of meta-models and grammars of evolving languages. © 2023, CC BY-NC-ND.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Behaviour of Tree-Based Neural Networks in Regression Tasks

arXiv

引用

arXiv 2024年

作者： Samoaa, Peter Farahani, Mehrdad Longa, Antonio Leitner, Philipp Chehreghani, Morteza Haghir Data Science and AI Division Chalmers University of Technology Gothenburg Sweden Interaction Design and Software Engineering Division Chalmers University of Technology Gothenburg Sweden Department of Information Engineering and Computer Science University of Trento Trento Italy

The landscape of deep learning has vastly expanded the frontiers of source code analysis, particularly through the utilization of structural representations such as Abstract Syntax Trees (ASTs). While these methodologies have demonstrated effectiveness in classification tasks, their efficacy in regression applications, such as execution time prediction from source code, remains underexplored. This paper endeavours to decode the behaviour of tree-based neural network models in the context of such regression challenges. We extend the application of established models—tree-based Convolutional Neural Networks (CNNs), Code2Vec, and Transformer-based methods—to predict the execution time of source code by parsing it to an AST. Our comparative analysis reveals that while these models are benchmarks in code representation, they exhibit limitations when tasked with regression. To address these deficiencies, we propose a novel dual-transformer approach that operates on both source code tokens and AST representations, employing cross-attention mechanisms to enhance interpretability between the two domains. Furthermore, we explore the adaptation of Graph Neural Networks (GNNs) to this tree-based problem, theorizing the inherent compatibility due to the graphical nature of ASTs. Empirical evaluations on real-world datasets showcase that our dual-transformer model outperforms all other tree-based neural networks and the GNN-based models. Moreover, our proposed dual transformer demonstrates remarkable adaptability and robust performance across diverse datasets. © 2024, CC BY-NC-SA.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

High-Speed Optical Convolutional Neural Network Accelerator with 100 Gbaud EO-polymer/Si Hybrid Optical Modulator

High-Speed Optical Convolutional Neural Network Accelerator ...

引用

2023 Opto-Electronics and Communications Conference, OECC 2023

作者： Shinya, Akito Kida, Koji Sato, Hiromu Lu, Guo-Wei Yokoyama, Shiyoshi Fujikata, Junichi Tokushima University Graduate School of Science and Technology for Innovation Tokushima Japan Kagawa University Fuculty of Engineering and Design Takamatsu Japan Institute for Materials Chemistry and Engineering Kyushu University Kasuga Japan The University of Aizu Division of Computer Engineering Aizu Japan Institute of Post-LED Photonics Tokushima University Tokushima Japan

ISBN: (纸本)9781665462136

Convolutional neural networks are a powerful category of artificial neural networks that can extract hierarchical features of biological data to significantly reduce parametric complexity and increase prediction accuracy. In this paper, we propose high-speed optical convolutional neural network accelerator with 100Gbaud EO-polymer/Si hybrid optical modulator and demonstrated proof of concept both in simulation and experiment. © 2023 IEEE.

关键词： Light modulators

来源：评论

学校读者我要写书评

暂无评论

Sign Language Vocabulary Recognition Only with Tactile Sensing Glove

Sign Language Vocabulary Recognition Only with Tactile Sensi...

引用

IEEE International Symposium on Embedded Multicore Socs (MCSoC)

作者： Motoki Kagami Zeping Yu Sim Teck Ceng Lei Jing School of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Japan Graduate School of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Japan Department of Management and Design University of Aizu Junior College Division Aizu-Wakamatsu Japan

ISBN: (数字)9798331530471

ISBN: (纸本)9798331530488

A significant challenge in communication arises between deaf individuals and hearing individuals. Sign language recognition is expected to be an important research field for eliminating barriers. In this field, data collection is primarily conducted using two methods: sensor-based and vision-based approaches. In this study, we adopted a sensor-based approach by using a tactile sensing glove due to its portability, costeffectiveness, and ability to capture fine finger movements. Subsequently, we applied LSTM and k-NN respectively to evaluate the recognition accuracy using this method. As a result, LSTM achieved a test accuracy of approximately 76%, while k-NN demonstrated an average accuracy of 87%. These findings highlight the potential of sensor-based SLR technology in reducing communication barriers and advancing inclusively in communication tools.

关键词： Sign language Vocabulary Accuracy Multicore processing Fingers Auditory system Data collection Sensors Long short term memory

来源：评论

学校读者我要写书评

暂无评论

MarineVRS: Marine Video Retrieval System with Explainability via Semantic Understanding

MarineVRS: Marine Video Retrieval System with Explainability...

引用

OCEANS

作者： Tan-Sang Ha Hai Nguyen-Truong Tuan-Anh Vu Sai-Kit Yeung Department of Computer Science and Engineering The Hong Kong University of Science and Technology Division of Integrative Systems and Design (ISD) The Hong Kong University of Science and Technology

Building a video retrieval system that is robust and reliable, especially for the marine environment, is a challenging task due to several factors such as dealing with massive amounts of dense and repetitive data, occlusion, blurriness, low lighting conditions, and abstract queries. To address these challenges, we present MarineVRS, a novel and flexible video retrieval system designed explicitly for the marine domain. MarineVRS integrates state-of-the-art methods for visual and linguistic object representation to enable efficient and accurate search and analysis of vast volumes of underwater video data. In addition, unlike the conventional video retrieval system, which only permits users to index a collection of images or videos and search using a freeform natural language sentence, our retrieval system includes an additional Explainability module that outputs the segmentation masks of the objects that the input query referred to. This feature allows users to identify and isolate specific objects in the video footage, leading to more detailed analysis and understanding of their behavior and movements. Finally, with its adaptability, explainability, accuracy, and scalability, MarineVRS is a powerful tool for marine researchers and scientists to efficiently and accurately process vast amounts of data and gain deeper insights into the behavior and movements of marine species.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralized MIMO Systems with Imperfect CSI using LMMSE Receivers

arXiv

引用

arXiv 2024年

作者： Zhuang, Zeyan Zhang, Xin Xu, Dongfang Song, Shenghui Eldar, Yonina C. Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Division of Integrative Systems and Design The Hong Kong University of Science and Technology Hong Kong Department of Mathematics and Computer Science The Weizmann Institute of Science Rehovot7610001 Israel

Centralized baseband processing (CBP) is required to achieve the full potential of massive multiple-input multiple-output (MIMO) systems. However, due to the large number of antennas, CBP suffers from two major issues: 1) Extensive data interconnection between radio frequency (RF) circuitry and the central processing unit;and 2) high-dimensional computation. To this end, decentralized baseband processing (DBP) has been proposed, where the antennas at the base station are partitioned into clusters connected to separate RF circuits and equipped with separate computing units. However, the optimal fusion scheme that maximizes signal-to-interference-and-noise ratio (SINR) and the related performance analysis for DBP with general spatial correlation and imperfect channel state information (CSI) have not been studied. In this paper, we consider a decentralized MIMO system where all clusters adopt linear minimum mean-square error (LMMSE) receivers. We first establish an optimal linear fusion scheme that has high computational and data input/output costs. To reduce the cost, we then propose two suboptimal fusion schemes with reduced complexity. For all three schemes, we study the SINR performance by leveraging random matrix theory and demonstrate conditions under which the suboptimal schemes are optimal. Furthermore, we determine the optimal regularization parameter for the LMMSE receiver, identify the best antenna partitioning strategy, and prove that the SINR will decrease as the number of clusters increases. Numerical simulations validate the accuracy of the theoretical results. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Tuberculosis Treatment: Smart Technology Innovations for Mycobacterium tuberculosis Management

Revolutionizing Tuberculosis Treatment: Smart Technology Inn...

引用

2024 International Conference on Smart Devices, ICSD 2024

作者： Pramanik, Atreyi Singh, Ajay Rani, Gouri Dubey, Shival Aluvala, Srinivas Uttaranchal University School of Applied and Life Sciences Division of Research and Innovation Dehradun India Uttaranchal University School of Applied and Life Sciences Dehradun India Uttaranchal University India University of Leeds Institute of Design Optimization and Robotics School of Mechanical Engineering United Kingdom SR University School of Computer Science & Artificial Intelligence India

ISBN: (纸本)9798350394412

Tuberculosis remains a significant global problem. The modification in smart technology (ST) invention generates novel chances to reform tuberculosis (TB) controlling. This work explores the potential of ST for filtering MTB diagnostics and therapy. ST includes telemedicine, mobile health uses (mHealth), wearable devices (WD) and data analytical that deliver many options of improving TB control. Telemedicine licenses distant consulting thus empowering medics to access patients in remote areas, offer quick detects as well as recommend treatment. mHealth apps certify that individuals have right of entry to education materials, can remind them when it's time for medication and offers self-monitoring tools which enhance adherence to the therapy by keeping the patient involved during the course of treatment. WD support real-time (RT) monitoring of heart rates, blood pressure level, physical activity and other vital signs that are important in coming up with modified remedy plans while also detecting response to cure earlier enough. Data analytics combined with AI can examine large amounts of patient data to identify patterns, forecast drug effects and optimize treatment strategies resulting in more efficient individualized care. These novelties through intellectual technologies may be used as solutions for tasks experienced during TB management, leading to improved patient outcomes and a reduction in the TB burden. © 2024 IEEE.

关键词： Telemedicine

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：