检索结果-内蒙古大学图书馆

***: Advancing education and research in nanotechnology

computing IN SCIENCE & ENGINEERING 2008年第5期10卷 17-23页

作者： Klimeck, Gerhard McLennan, Michael Brophy, Sean B. Adams, George B., III Lundstrom, Mark S. Purdue Univ Network Computat Nanotechnol W Lafayette IN 47907 USA Purdue Univ Rosen Ctr Adv Comp W Lafayette IN 47907 USA Purdue Univ Sch Engn Educ W Lafayette IN 47907 USA

Through the Network for Computational Nanotechnology Web site, ***, tens of thousands of users from 172 countries collaborate, share resources, and solve real nanotechnology problems. The authors share their experienc... 详细信息

关键词： HPC Web-based services and enhancement and visualization computer applications computer graphics computer-aided design computer-aided engineering computing methodologies distribution education environments evolving Internet applications graphics systems

来源：评论

学校读者我要写书评

暂无评论

Intermediary-Generated Bridge Network for RGB-D Cross-Modal Re-Identification

引用

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 2024年第6期15卷 1-25页

作者： Wu, Jingjing Hong, Richang Tang, Shengeng Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Hefei Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Minist Educ Hefei Peoples R China

RGB-D cross-modal person re-identification (re-id) targets at retrieving the person of interest across RGB and depth image modalities. To cope with the modal discrepancy, some existing methods generate an auxiliary mode with either inherent properties of input modes or extra deep networks. However, such useful intermediary role included in generated mode is often overlooked in these approaches, leading to insufficient exploitation of crucial bridge knowledge. By contrast, in this article, we propose a novel approach that constructs an intermediary mode through the constraints of self-supervised intermediary learning, which is freedom from modal prior knowledge and additional module parameters. We then design a bridge network to fully mine the intermediary role of generated modality through carrying out multi-modal integration and decomposition. For one thing, this network leverages a multi-modal transformer to integrate the information of three modes via fully exploiting their heterogeneous relations with the intermediary mode as the bridge. It conducts the identification consistency constraint to promote cross-modal associations. For another, it employs circle contrastive learning to decompose the cross-modal constraint process into several subprocedures, which provides the intermediate relay during pulling two original modalities closer. Experiments on two public datasets demonstrate that the proposed method exceeds the state-of-the-arts. The effectiveness of each component in this method is verified through numerous ablation studies. Additionally, we have demonstrated the generalization ability of the proposed method through experiments.

关键词： computing methodologies Object identification

来源：评论

学校读者我要写书评

暂无评论

Dynamic Programming and Graph Algorithms in Computer Vision

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2011年第4期33卷 721-740页

作者： Felzenszwalb, Pedro F. Zabih, Ramin Univ Chicago Dept Comp Sci Chicago IL 60637 USA Cornell Univ Dept Comp Sci Ithaca NY 14853 USA

Optimization is a powerful paradigm for expressing and solving problems in a wide range of areas, and has been successfully applied to many vision problems. Discrete optimization techniques are especially interesting since, by carefully exploiting problem structure, they often provide nontrivial guarantees concerning solution quality. In this paper, we review dynamic programming and graph algorithms, and discuss representative examples of how these discrete optimization techniques have been applied to some classical vision problems. We focus on the low-level vision problem of stereo, the mid-level problem of interactive object segmentation, and the high-level problem of model-based recognition.

关键词： Combinatorial algorithms vision and scene understanding artificial intelligence computing methodologies

来源：评论

学校读者我要写书评

暂无评论

Feature-Preserving Surface Reconstruction From Unoriented, Noisy Point Data

引用

COMPUTER GRAPHICS FORUM 2013年第1期32卷 164-176页

作者： Wang, J. Yu, Z. Zhu, W. Cao, J. Univ Wisconsin Dept Comp Sci Milwaukee WI 53201 USA Zhejiang Univ Dept Mech Engn Hangzhou 310003 Zhejiang Peoples R China Dalian Univ Technol Sch Math Sci Dalian Peoples R China

We propose a robust method for surface mesh reconstruction from unorganized, unoriented, noisy and outlier-ridden 3D point data. A kernel-based scale estimator is introduced to estimate the scale of inliers of the input data. The best tangent planes are computed for all points based on mean shift clustering and adaptive scale sample consensus, followed by detecting and removing outliers. Subsequently, we estimate the normals for the remaining points and smooth the noise using a surface fitting and projection strategy. As a result, the outliers and noise are removed and filtered, while the original sharp features are well preserved. We then adopt an existing method to reconstruct surface meshes from the processed point data. To preserve sharp features of the generated meshes that are often blurred during reconstruction, we describe a two-step approach to effectively recover original sharp features. A number of examples are presented to demonstrate the effectiveness and robustness of our method.

关键词： unoriented noisy point data surface reconstruction robust statistics feature-preserving reconstruction computing methodologies Computer graphics Shape modeling Point-based models

来源：评论

学校读者我要写书评

暂无评论

Real-Time Seamless Multi-Projector Displays on Deformable Surfaces

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2024年第5期30卷 2527-2537页

作者： Ibrahim, Muhammad Twaha Gopi, M. Majumder, Aditi Univ Calif Irvine Irvine CA 92697 USA

Prior works on multi-projector displays have focused primarily on static rigid objects, some focusing on dynamic rigid objects. However, works on projection based displays on deformable dynamic objects have focused only on small scale single projector displays. Tracking a deformable dynamic surface and updating projections precisely in real time on it is a significantly challenging task, even for a single projector system. In this paper, we present the first end-to-end solution for achieving a real-time, seamless display on deformable surfaces using mutliple unsychronized projectors without requiring any prior knowledge of the surface or device parameters. The system first accurately calibrates multiple RGB-D cameras and projectors using the deformable display surface itself, and then using those calibrated devices, tracks the continuous changes in the surface shape. Based on the deformation and projector calibration, the system warps and blends the image content in real-time to create a seamless display on a surface that continuously changes shape. Using multiple projectors and RGB-D cameras, we provide the much desired aspect of scale to the displays on deformable surfaces. Most prior dynamic multi-projector systems assume rigid objects and depend critically on the constancy of surface normals and non-existence of local shape deformations. These assumptions break in deformable surfaces making prior techniques inapplicable. Point-based correspondences become inadequate for calibration, exacerbated with no synchronization between the projectors. A few works address non-rigid objects with several restrictions like targeting semi-deformable surfaces (e.g. human face), or using single coaxial (optically aligned) projector-camera pairs, or temporally synchronized cameras. We break loose from such restrictions and handle multiple projector systems for dynamic deformable fabric-like objects using temporally unsynchronized devices. We devise novel methods using ray and pla

关键词： Cameras Calibration Three-dimensional displays Shape Surface reconstruction Real-time systems Surface fitting computing methodologies Artificial Intelligence Computer Vision Image and Video Acquisition

来源：评论

学校读者我要写书评

暂无评论

Interactive 3D Force-Directed Edge Bundling

引用

COMPUTER GRAPHICS FORUM 2016年第3期35卷 51-60页

作者： Zielasko, D. Weyers, B. Hentschel, B. Kuhlen, T. W. Rhein Westfal TH Aachen JARA High Performance Comp Visual Comp Inst Aachen Germany

Interactive analysis of 3D relational data is challenging. A common way of representing such data are node-link diagrams as they support analysts in achieving a mental model of the data. However, naive 3D depictions of complex graphs tend to be visually cluttered, even more than in a 2D layout. This makes graph exploration and data analysis less efficient. This problem can be addressed by edge bundling. We introduce a 3D cluster-based edge bundling algorithm that is inspired by the force-directed edge bundling (FDEB) algorithm [HvW09b] and fulfills the requirements to be embedded in an interactive framework for spatial data analysis. It is parallelized and scales with the size of the graph regarding the runtime. Furthermore, it maintains the edge's model and thus supports rendering the graph in different structural styles. We demonstrate this with a graph originating from a simulation of the function of a macaque brain.

关键词： Categories and Subject Descriptors (according to ACM CCS) Data Structures [E.1]: Graphs and networks&mdash computing methodologies [I.3.8]: Computer Graphics&mdash Applications

来源：评论

学校读者我要写书评

暂无评论

Scalable Reactive Molecular Dynamics Simulations for Computational Synthesis

引用

computing IN SCIENCE & ENGINEERING 2019年第5期21卷 64-75页

作者： Li, Ying Nomura, Ken-Ichi Insley, Joseph A. Morozov, Vitali Kumaran, Kalyan Romero, Nichols A. Goddard, William A., III Kalia, Rajiv K. Nakano, Aiichiro Vashishta, Priya Argonne Natl Lab 9700 S Cass Ave Argonne IL 60439 USA Univ Southern Calif Chem Engn & Mat Sci Los Angeles CA USA CALTECH Chem Mat Sci & Appl Phys Pasadena CA 91125 USA Univ Southern Calif Phys & Astron Chem Engn & Mat Sci & Comp Sci Los Angeles CA USA Univ Southern Calif Comp Sci Phys & Astron Chem Engn & Mat Sci & Biol Los Angeles CA USA Univ Southern Calif Chem Engn & Mat Sci Phys & Astron & Comp Sci Los Angeles CA USA

Reactive molecular dynamics (MD) simulation is a powerful research tool for describing chemical reactions. We eliminate the speed-limiting charge iteration in MD with a novel extended-Lagrangian scheme. The extended-Lagrangian reactive MD (XRMD) code drastically improves energy conservation while substantially reducing time-to-solution. Furthermore, we introduce a new polarizable charge equilibration (PQEq) model to accurately predict atomic charges and polarization. The XRMD code based on hybrid message passing+multithreading achieves a weak-scaling parallel efficiency of 0.977 on 786 432 IBM Blue Gene/Q cores for a 67.6 billion-atom system. The performance is portable to the second-generation Intel Xeon Phi, Knights Landing. Blue Gene/Q simulations for the computational synthesis of materials via novel exfoliation mechanisms for synthesizing atomically thin transition metal dichalcogenide layers will dominate nanomaterials science in this century.

关键词： Charge Exchange Coulomb Blockade Decomposition Energy Conservation Iterative Methods Lagrangian Field Theory Message Passing Molecular Dynamics Method Multi Threading Potential Energy Functions Atomically Thin Transition Metal Dichalcogenide Layers Billion Atom System Weak Scaling Parallel Efficiency XRMD Code Polarization Atomic Charges Polarizable Charge Equilibration Model Time To Solution Energy Conservation Extended Lagrangian Reactive MD Code Novel Extended Lagrangian Scheme Speed Limiting Charge Chemical Reactions Powerful Research Tool Reactive Molecular Dynamics Simulation Computational Synthesis Scalable Reactive Molecular Dynamics Simulations Computational Modeling Multithreading Mathematical Model Materials Science And Technology Numerical Models Computer Science Predictive Models computing methodologies Simulation Modeling And Visualization Simulation Theory Types Of Simulation Super Very Large Computers Large And Medium X 201 C Mainframe X 201 D Computers Computer System Implementation Mathematics Of computing Numerical Analysis General Parallel Algorithms Software Software Engineering Operating Systems Performance Modeling And Prediction Theory Of Computation General Data General System Applications And Experience

来源：评论

学校读者我要写书评

暂无评论

A Resistant Strain: Revealing the Online Grassroots Rise of the Antivaccination Movement

引用

COMPUTER 2017年第11期50卷 60-67页

作者： Bandari, Roja Zhou, Zicong Qian, Hai Tangherlini, Timothy R. Roychowdhury, Vwani P. Univ Calif Los Angeles Elect Engn Los Angeles CA 90024 USA Univ Calif Los Angeles Los Angeles CA 90024 USA Univ Calif Los Angeles Folklore Los Angeles CA 90024 USA Univ Calif Los Angeles Elect & Comp Engn Los Angeles CA 90024 USA

An analysis of more than eight years of data from vaccination forums on *** shows that the antivaccination movement is well-organized and widely dispersed, and that it emerged long before concerns about immunity were ... 详细信息

关键词： machine learning AI artificial intelligence computing methodologies web text analysis natural language processing computing methodologies human safety public policy issues computers and society social media vaccination antivaccination movement herd immunity immunity vaccines healthcare mothering com

来源：评论

学校读者我要写书评

暂无评论

Genomic Machine Learning Meta-regression: Insights on Associations of Study Features With Reported Model Performance

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第1期21卷 169-177页

作者： Barnett, Eric J. Onete, Daniel G. Salekin, Asif Faraone, Stephen V. SUNY Upstate Med Univ Dept Psychiat & Behav Sci Syracuse NY 13210 USA SUNY Upstate Med Univ Coll Med MD Program Syracuse NY 13210 USA Syracuse Univ Dept Elect Engn & Comp Sci Lab Ubiquitous & Intelligent Sensing Syracuse NY 13210 USA

Many studies have been conducted with the goal of correctly predicting diagnostic status of a disorder using the combination of genomic data and machine learning. It is often hard to judge which components of a study led to better results and whether better reported results represent a true improvement or an uncorrected bias inflating performance. We extracted information about the methods used and other differentiating features in genomic machine learning models. We used these features in linear regressions predicting model performance. We tested for univariate and multivariate associations as well as interactions between features. Of the models reviewed, 46% used feature selection methods that can lead to data leakage. Across our models, the number of hyperparameter optimizations reported, data leakage due to feature selection, model type, and modeling an autoimmune disorder were significantly associated with an increase in reported model performance. We found a significant, negative interaction between data leakage and training size. Our results suggest that methods susceptible to data leakage are prevalent among genomic machine learning research, resulting in inflated reported performance. Best practice guidelines that promote the avoidance and recognition of data leakage may help the field avoid biased results.

关键词： Data models Predictive models Training Genomics Bioinformatics Machine learning Computational modeling learning artificial intelligence computing methodologies biology and genetics life and medical sciences computer applications

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning CNN Image Retrieval with No Human Annotation

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2019年第7期41卷 1655-1668页

作者： Radenovic, Filip Tolias, Giorgos Chum, Ondrej Czech Tech Univ Fac Elect Engn Dept Cybernet Visual Recognit Grp Prague 16636 6 Czech Republic

Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant in image retrieval due to their discriminative power, compactness of representation, and search efficiency. Training of CNNs, either from scratch or fine-tuning, requires a large amount of annotated data, where a high quality of annotation is often crucial. In this work, we propose to fine-tune CNNs for image retrieval on a large collection of unordered images in a fully automated manner. Reconstructed 3D models obtained by the state-of-the-art retrieval and structure-from-motion methods guide the selection of the training data. We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval. CNN descriptor whitening discriminatively learned from the same training data outperforms commonly used PCA whitening. We propose a novel trainable Generalized-Mean (GeM) pooling layer that generalizes max and average pooling and show that it boosts retrieval performance. Applying the proposed method to the VGG network achieves state-of-the-art performance on the standard benchmarks: Oxford Buildings, Paris, and Holidays datasets.

关键词： Image representation processing and computer vision computing methodologies neural nets pattern recognition applications

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：