检索结果-内蒙古大学图书馆

2025 ieee international conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Tang, Minzhe Yuan, Ruisheng Kou, Dongliang Sun, Mingyang Zhang, Lihua Academy for Engineering and Technology Fudan University Shanghai China Institute of Metaverse & Intelligent Medicine Fudan University Shanghai China Jilin Provincial Key Laboratory of Intelligence Science and Engineering Changchun China Engineering Research Center of AI and Robotics Ministry of Education Shanghai China AI and Unmanned Systems Engineering Research Center of Jilin Province Changchun China

ISBN: (纸本)9798350368741

Learning-based garment prediction presents an appealing alternative to physics-based methods owing to its high efficiency. However, the predicted garments can exhibit noticeable penetrations into the body. Many collision-handling methods operate in the point domain, which has an inherent limitation in addressing the penetration issues with the mesh faces. In light of this, we propose a local Shape-Aware, Face-based collision handling approach (SAF) that can be applied to garment prediction networks to achieve real-time collision handling. Considering the nature of garments, we design a compact formulation to model the continuity of the garment surface, and utilize neural Signed Distance Fields (SDFs) to accomplish penetration resolution. Recognizing the significant impact of the body's local shape on collision handling, we further propose using the angles between SDF gradients to characterize the sharpness of the body. Our approach can compensate for the inaccuracy of neural SDFs and preserve local smoothness and details. Extensive experiments demonstrate the outstanding performance and generalizability of our method. © 2025 ieee.

关键词： collision handling computer graphics deep learning garment simulation

来源：评论

学校读者我要写书评

暂无评论

Application of computer graphics and BIM in Three-Dimensional Visualization and Virtual Reality of Water Conservancy Buildings

Application of Computer Graphics and BIM in Three-Dimensiona...

引用

Electronics, Energy Systems and Power Engineering (EESPE), ieee international conference on

作者： Zekun Chang Shandong Vocational College of Industry Zibo China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

This paper combines computer graphics and building information modeling (BIM) technology to propose an innovative three-dimensional visualization optimization algorithm for water conservancy buildings. The algorithm combines BIM data with efficient rendering technology in graphics, and proposes a method based on multi-level model generation and detail processing optimization to improve the rendering speed and accuracy of three-dimensional models. In the experimental part, a BIM model of a large water conservancy project was used for testing. The results show that compared with the traditional rendering method, the algorithm has improved the rendering accuracy by 18.5% and the rendering speed by 30%. In practical applications, this algorithm can effectively reduce the rendering time while ensuring the details and accuracy of the model, providing more accurate and efficient visualization support for water conservancy construction projects. In addition, the visualization effect is displayed through a virtual reality platform, which further verifies the superior performance of the algorithm in a virtual reality environment. The results of this study show that the innovative algorithm based on BIM and computer graphics cannot only improve the design and construction efficiency of water conservancy buildings, but also optimize the engineering management process, and has strong application value and promotion prospects.

关键词： Solid modeling Accuracy Three-dimensional displays Computational modeling Buildings Virtual reality Water conservation Rendering (computer graphics) Optimization Water resources

来源：评论

学校读者我要写书评

暂无评论

Framework for Drug User Analysis and Prediction 4

Framework for Drug User Analysis and Prediction

引用

4th international conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Sethuraman, Dhanush Ananya, Ela Joseph Jeffrey, J. Thangavel, Senthil Kumar Rangasami, P. Somasundaram, K. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India Amrita Vishwa Vidyapeetham Department of Social Work Coimbatore India Amrita School of Physical Sciences Department of Mathematics Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

This paper provides a framework for knowledge and action related to and about substance abuse, that integrates both capacity development and data-driven analysis for drug use analysis and modeling. In line with the National Action Plan for Drug Demand Reduction (NAPDDR) the framework focuses on a multi-pronged strategy. It then gives examples of so-called capacity-building exercises, such as those carried out by Amrita Vishwa Vidyapeetham in Tamil Nadu in 2020. These programs targeted key stakeholders, including healthcare professionals, police personnel, teachers, and social workers, focusing on preventive education, medical management, psychosocial issues, and rehabilitation strategies related to substance abuse. Pre- and post-training evaluations showed a strong increase in participants knowledge and treatment skills for substance use disorders. Second, the paper presents a data-driven, quantitative analysis of drug use patterns and related factors. Using a Support Vector Machine (SVM) algorithm, the study utilizes a dataset of drug consumption patterns to determine the factors which are most important for drug consumption. Importantly, the framework also include Explainable AI (XAI) methods to increase the interpretability and tracibility of the machine learning model. XAI approaches are used to interpret the model's decision process and to identify the most important factors in predicting the use of drugs. Incorporating insights from the capacity-building program evaluation and from the XAI-aided machine learning analysis, this framework provides an integrated end-to-end framework for drug user analysis and the generation of actionable recommendations for the design of targeted interventions and prevention strategies. © 2025 ieee.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Foreword to the special section on the international conference on computer-aided design and computer graphics (CAD/graphics) 2019

引用

computerS & graphics-UK 2020年第0期86卷 A5-A6页

作者： Tong, Xin Myszkowski, Karol Huang, Jin Zhejiang Univ Hangzhou Peoples R China Zhejiang Univ State Key Lab CAD&CG Coll Comp Sci Hangzhou Peoples R China

It is our pleasure to present this special section of computers & graphics (C&G), featuring the selected papers presented at the 16th conference on CAD/graphics 2019, which was held May 5-6, 2019 in Qingdao, China. The philosophy of CAD/graphics is to bring together international researchers and developers in CAD and CG in order to support a good and sustained communication channel for exchanging new ideas. The conference assembled a larger international Program Committee (PC), with 70 world-class experts in the CAD/CG areas and most of the reviews were done among the PC members, ensuring high-quality reviews. [Extracted from the article]

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fourth international conference on computer-aided design and computer graphics

Fourth International Conference on Computer-Aided Design and...

引用

Fourth international conference on computer-aided design and computer graphics

ISBN: (纸本)0819420158

The proceedings contains 120 papers. Following topics are discussed: computer graphics;computer-aided geometric design;computational geometry;CAD/CAM technology and applications;CAD/CAPP/CAM integration;computer-aided IC design;techniques for testing, diagnosis, and fault tolerance;engineering database/knowledge base;intelligent CAD and applications;visualization in scientific computing;animation and simulation;and computer graphics hardware and engineering.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

TextHair3D: Text-driven 3D Hair Editing with Generative Priors

TextHair3D: Text-driven 3D Hair Editing with Generative Prio...

引用

international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaoxue Li Huilong Pi Yunchuan Qin Ruihui Li Kenli Li College of Computer Science and Electronic Engineering Hunan University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Text-driven hair editing on 3D heads is a challenging problem in computer vision and graphics. In this paper, we propose TextHair3D, a NeRF-based text-driven 3D hair editing method that uses 3D perception to generate priors, edit hair attributes from user-provided text, and preserve facial features. TextHair3D uses the Contrastive Language-Image Pre-training (CLIP) model to encode textual conditions. To address the complexity and roughness of local editing, we design a combined conditional mapping module to map image and text conditions into latent space for learning generative priors. This enables high-quality, photo-realistic hair editing and 3D head reproduction. Extensive experiments show Tex-tHair3D’s superiority in visual realism and attribute accuracy.

关键词： Hair Visualization Three-dimensional displays Head Space mapping Signal processing Rendering (computer graphics) Neural radiance field Speech processing Facial features

来源：评论

学校读者我要写书评

暂无评论

Proud-SLAM: Neural Point-based Hybrid RGBD Monocular Dense SLAM

Proud-SLAM: Neural Point-based Hybrid RGBD Monocular Dense S...

引用

international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wenzhi Guo Lijun Chen Department of Computer Science and Technology Nanjing University Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Neural Radiance Fields (NeRF) have shown significant potential in encoding complex 3D geometries and visual properties, making them a promising alternative to traditional dense SLAM systems. We propose Proud-SLAM, a dense SLAM framework that merges a neural point-based hybrid scene representation. Our key innovation is the HPoint method, which integrates color features into the point cloud, preserving real-world fidelity and enhancing scene rendering. Additionally, we design a hashV structure to efficiently manage and expand point clouds incrementally. Experiments on Replica and Scan-Net datasets demonstrate that Proud-SLAM excels in tracking precision, reconstruction accuracy, and scene rendering quality.

关键词： Point cloud compression Technological innovation Surface reconstruction Simultaneous localization and mapping Accuracy Three-dimensional displays Rendering (computer graphics) Neural radiance field Speech processing Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Research on Distribution Path Optimization of computer-aided Logistics Warehousing Management System

Research on Distribution Path Optimization of Computer-Aided...

引用

Electronics, Energy Systems and Power Engineering (EESPE), ieee international conference on

作者： Wei Chang Jianzhou Wang Engineering University of PAP Xi'an China Yichun Detachment of Heilongjiang Corps of PAP Yichun China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

This paper proposes a computer-aided optimization model and combines it with the Bellman-Ford algorithm for path planning, aiming to improve logistics distribution efficiency and reduce transportation time and cost. The system designs a logistics warehousing management model containing multiple warehouses and distribution points, and establishes a mathematical model for distribution path optimization. By using the Bellman-Ford algorithm, the system can calculate the shortest path under various constraints, thereby optimizing the distribution route and improving resource utilization efficiency. The Bellman-Ford algorithm can effectively handle graphs with negative weight edges and ensure the shortest path is found through an iterative process, which is suitable for complex logistics network environments. To verify the effectiveness of the system, this paper adopts a simulation test method to simulate distribution scenarios of different scales and demands. The test results show that the optimization system using the Bellman-Ford algorithm can significantly shorten the distribution time and reduce transportation costs. Compared with the traditional path optimization method, the system improves the distribution efficiency by about 12% to 18% in most test scenarios. In addition, the experiment shows that as the scale of the distribution network expands, the system can still maintain good optimization performance.

关键词： Costs Accuracy Computational modeling Warehousing Transportation Stability analysis Optimization Thermal stability System analysis and design Logistics

来源：评论

学校读者我要写书评

暂无评论

Error Correction and Detection for Analog AI Computing in Edge Systems 24

Error Correction and Detection for Analog AI Computing in Ed...

引用

Proceedings of the 43rd ieee/ACM international conference on computer-aided design

作者： Anxiao Jiang Computer Science and Engineering Texas A&M University College Station TX United States

ISBN: (纸本)9798400710773

To realize the full potential of deep neural networks (DNNs) in AI-empowered edge systems, DNNs need to be much more efficient. Analog in-memory computing can potentially improve the speed and energy efficiency of AI by multiple orders, and break the "memory wall" that is currently a major bottleneck for AI. This work explores the design of analog error-correcting codes (Analog ECCs). The codes focus on the correction of errors in vector-matrix multiplications, which are a dominant part of computation in DNNs. The codes consider small but ubiquitous noise in analog edge circuits as tolerable, and focus on the correction of large errors. It presents a linear-programming based algorithm that finds the error correction/detection capabilities of codes. It also presents a number of newly discovered codes that achieve state-of-the-art performance.

关键词： analog error-correcting code

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 13th international conference on computer-aided design and computer graphics, CAD/graphics 2013

Proceedings - 13th International Conference on Computer-Aide...

引用

13th international conference on computer-aided design and computer graphics, CAD/graphics 2013

The proceedings contain 88 papers. The topics discussed include: simulation of wave effects based on ray tracing;a data-driven approach to efficient character articulation;robust reconstruction of interior building structures with multiple rooms under clutter and occlusions;fitting multiple curves to point clouds with complicated topological structures;a new level-set-based inverse lithography algorithm for process robustness improvement with attenuated phase shift mask;bridging the gap between global routing and detailed routing: a practical congestion model;logic minimization based on dual logic;real-time multi-scale refraction under all-frequency environmental lighting;screen-space ambient occlusion using a-buffer techniques;an adapted parameterization for smooth geometry images;and high quality binocular facial performance capture from partially blurred image sequence.

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：