检索结果-内蒙古大学图书馆

PcdGS: A point cloud densification method for Gaussian Splatting

computers & Graphics 2025年

作者： Jing Zhao Chenxi Li Shuhui Zhang Feng Wang Ying Yin Yuhan Liu School of Information Science and Engineering Yanshan University Qinhuangdao 066000 Hebei China Hebei Key Laboratory of Computer Virtual Technology and System Integration Qinhuangdao Hebei China

Novel view synthesis (NVS) from limited observations continues to be an important and persistent challenge. Currently, methods based on Neural Radiance Fields (NeRF) are not very efficient, and although methods based on 3D Gaussian Splatting (3DGS) outperform NeRF in terms of rendering quality and speed, they still lack sufficient details. To tackle these issues, we introduce a new method for densifying the point cloud, which enhances the rendering effect of 3DGS-based techniques under sparse view conditions. First, we introduce a mask-based densification technique to improve rendering details under limited input views. Second, We propose a monocular pixel depth-based mapping method that leverages a pre-trained model to predict depth, effectively normalizing point locations within the resulting point cloud. Lastly, we implement a filtering method based on depth and RGB color to minimize noise introduced by the additional data. We conduct comparative experiments on the LLFF, Mip-NeRF 360, and Blender datasets, demonstrating that our method outperforms existing approaches in both evaluation metrics and visual quality, thereby validating its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Data Collection Scheme Using Denoising Autoencoder in Wireless Sensor Networks

引用

Tsinghua Science and technology 2019年第1期24卷 86-96页

作者： Guorui Li Sancheng Peng Cong Wang Jianwei Niu Ying Yuan School of Computer Science and Engineering Northeastern University School of Information Science and Technology Guangdong University of Foreign Studies State Key Laboratory of Virtual Reality Technology and Systems Beihang University

As one of the key operations in Wireless Sensor Networks(WSNs), the energy-efficient data collection schemes have been actively explored in the literature. However, the transform basis for sparsifing the sensed data is usually chosen empirically, and the transformed results are not always the sparsest. In this paper, we propose a Data Collection scheme based on Denoising Autoencoder(DCDA) to solve the above problem. In the data training phase, a Denoising AutoEncoder(DAE) is trained to compute the data measurement matrix and the data reconstruction matrix using the historical sensed data. Then, in the data collection phase, the sensed data of whole network are collected along a data collection tree. The data measurement matrix is utilized to compress the sensed data in each sensor node, and the data reconstruction matrix is utilized to reconstruct the original data in the ***, the data communication performance and data reconstruction performance of the proposed scheme are evaluated and compared with those of existing schemes using real-world sensed data. The experimental results show that compared to its counterparts, the proposed scheme results in a higher data compression rate, lower energy consumption, more accurate data reconstruction, and faster data reconstruction speed.

关键词： wireless sensor networks data collection neural networks autoencoder data reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards self-interpretable review spammer group detection

引用

Information Sciences 2025年 716卷

作者： Huo, Chenghang Zhang, Fuzhi School of Information Science and Engineering Yanshan University Hebei Province Qinhuangdao China Hebei Key Laboratory of Computer Virtual Technology and System Integration Hebei Province Qinhuangdao China

Due to data imbalance, existing spammer group detection methods often yield suboptimal performance. Moreover, many of these approaches operate as black boxes, offering little to no interpretability for their detection results. To address these issues, we propose a self-interpretable approach for detecting review spammer groups. Our method begins by constructing a user-product bipartite graph with edge attributes. We integrate user review information with a novel fitness function to develop an adaptive genetic algorithm that effectively identifies high-quality candidate groups. Next, we introduce a hybrid graph neural network enhanced with active learning to generate vector representations of these candidate groups. We then design and construct a prototype layer and a group classification layer to detect spammer groups accurately. To provide interpretability, we incorporate prototype learning to create an interpretation mechanism that explains detection outcomes. Experimental results demonstrate that our method achieves substantial improvements in Precision@k and Recall@k at the top-1000 ranking, outperforming state-of-the-art solutions on the Amazon, YelpChi, YelpNYC, and YelpZip datasets by [11.53 %, 97.36 %, 51.37 %, 32.06 %] and [12.65 %, 54.65 %, 64.19 %, 47.37 %], respectively. Additionally, the Fidelity of our interpretability results under varying Sparsity levels is approximately 4 %, 9 %, 8 %, and 8 % higher than those of existing methods on the same datasets. © 2025 Elsevier Inc.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Interactive texture design and synthesis from mesh sketches

引用

Frontiers of computer Science 2014年第2期8卷 330-341页

作者： Lili WANG Qinglin QI Yi CHEN Wei KE Aimin HAO State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing 100191 China Macao Polytechnic Institute Macao China

Geometry mesh introduces user control into tex- ture synthesis and editing, and brings more variations in the synthesized results. But still two problems related remain in need of better solutions. One problem is generating the meshes with desired size and pattern efficiently from easier user inputs. The other problem is improving the quality of synthesized results with mesh information. We present a new two-step texture design and synthesis method that addresses these two problems. Besides example texture, a small piece of mesh sketch drawn by hand or detected from example texture is input to our algorithm. And then a mesh synthesis method of geometry space is provided to avoid optimizations cell by cell. Distance and orientation features are introduced to im- prove the quality of mesh rasterization. Results show that with our method, users can design and synthesize textures from mesh sketches easily and interactively.

关键词： texture synthesis texture design feature-basedmethod structural texture

来源：评论

学校读者我要写书评

暂无评论

A survey on image and video stitching

引用

virtual Reality & Intelligent Hardware 2019年第1期1卷 55-83页

作者： Wei LYU Zhong ZHOU Lang CHEN Yi ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Image/video stitching is a technology for solving the field of view(FOV)limitation of images/*** stitches multiple overlapping images/videos to generate a wide-FOV image/video,and has been used in various fields such as sports broadcasting,video surveillance,street view,and *** survey reviews image/video stitching algorithms,with a particular focus on those developed in recent *** stitching first calculates the corresponding relationships between multiple overlapping images,deforms and aligns the matched images,and then blends the aligned images to generate a wide-FOV image.A seamless method is always adopted to eliminate such potential flaws as ghosting and blurring caused by parallax or objects moving across the overlapping *** stitching is the further extension of image *** usually stitches selected frames of original videos to generate a stitching template by performing image stitching algorithms,and the subsequent frames can then be stitched according to the *** stitching is more complicated with moving objects or violent camera movement,because these factors introduce jitter,shakiness,ghosting,and *** detection technique is usually combined into stitching to eliminate ghosting and blurring,while video stabilization algorithms are adopted to solve the jitter and *** paper further discusses panoramic stitching as a special-extension of image/video *** stitching is currently the most widely used application in *** survey reviews the latest image/video stitching methods,and introduces the fundamental principles/advantages/weaknesses of image/video stitching ***/video stitching faces long-term challenges such as wide baseline,large parallax,and low-texture problem in the overlapping *** technologies may present new opportunities to address these issues,such as deep learning-based semantic correspondence,and 3D image ***,

关键词： Image stitching Video stitching Panoramic stitching Registration Alignment Mesh optimization Deep learning 3D stitching

来源：评论

学校读者我要写书评

暂无评论

3D scene graph prediction from point clouds

引用

virtual Reality & Intelligent Hardware 2022年第1期4卷 76-88页

作者： Fanfan WU Feihu YAN Weimin SHI Zhong ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Background In this study,we propose a novel 3D scene graph prediction approach for scene understanding from point *** It can automatically organize the entities of a scene in a graph,where objects are nodes and their relationships are modeled as *** specifically,we employ the DGCNN to capture the features of objects and their relationships in the scene.A Graph Attention Network(GAT)is introduced to exploit latent features obtained from the initial estimation to further refine the object arrangement in the graph structure.A one loss function modified from cross entropy with a variable weight is proposed to solve the multi-category problem in the prediction of object and *** Experiments reveal that the proposed approach performs favorably against the state-of-the-art methods in terms of predicate classification and relationship prediction and achieves comparable performance on object classification *** The 3D scene graph prediction approach can form an abstract description of the scene space from point clouds.

关键词： Scene understanding 3D scene graph Point cloud DGCNN GAT

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal consistency-based adaptive hand-held video stabilization

引用

Science China(Information Sciences) 2020年第1期63卷 226-228页

作者： Xiao LI Shuai LI Hong QIN Aimin HAO State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beihang University Qingdao Research Institute Department of Computer Science Stony Brook University

This study develops a novel, joint optimization method to successively respect spatial structure consistency and temporal feature constraints. Our method is more flexible and adaptive as we regard the camera multitrack motion to be noisy signals and adaptively suppress the noise without manual intervention. In addition, our method can achieve stabilization effects similar to that obtained by 3D

关键词： IMF EMD red frame Spatiotemporal consistency-based adaptive hand-held video stabilization

来源：评论

学校读者我要写书评

暂无评论

Image Tagging by Semantic Neighbor Learning Using User-Contributed Social Image Datasets

引用

Tsinghua Science and technology 2017年第6期22卷 551-563页

作者： Feng Tian Xukun Shen Xianmei Liu Maojun Cao the School of Computer and Information Technology Northeast Petroleum University Daqing 163318 China Xukun Shen is with State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China.

The explosive increase in the number of images on the Internet has brought with it the great challenge of how to effectively index, retrieve, and organize these resources. Assigning proper tags to the visual content is key to the success of many applications such as image retrieval and content mining. Although recent years have witnessed many advances in image tagging, these methods have limitations when applied to high-quality and large-scale training data that are expensive to obtain. In this paper, we propose a novel semantic neighbor learning method based on user-contributed social image datasets that can be acquired from the Web＇s inexhaustible social image content. In contrast to existing image tagging approaches that rely on high-quality image-tag supervision, we acquire weak supervision of our neighbor learning method by progressive neighborhood retrieval from noisy and diverse user-contributed image collections. The retrieved neighbor images are not only visually alike and partially correlated but also semantically related. We offer a step-by-step and easy-to-use implementation for the proposed method. Extensive experimentation on several datasets demonstrates that the performance of the proposed method significantly outperforms others.

关键词： image tag social image tagging user-contributed datasets semantic neighbor learning

来源：评论

学校读者我要写书评

暂无评论

Multiscale Convolutional Transformer with Diverse-aware Feature Learning for Motor Imagery EEG Decoding

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hang, Wenlong Wang, Junliang Liang, Shuang Lei, Baiying Wang, Qiong Li, Guanglin Chen, Badong Qin, Jing Nanjing Tech University College of Computer Nanjing211816 China Nanjing Tech University Information Engineering Nanjing211816 China Nanjing University of Posts and Telecommunications School of Internet of Things Nanjing210023 China Shenzhen University School of Biomedical Engineering Shenzhen518060 China Guangdong Provincial Key Laboratory of Computer Vision Shenzhen518055 China Virtual Reality Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Shenzhen Institute of Advanced Technology Shenzhen518055 China Chinese Academy of Sciences Shenzhen518055 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China Hong Kong Polytechnic University School of Nursing Hung Hom Hong Kong

Electroencephalogram (EEG)-based motor imagery (MI) brain-computer interfaces (BCIs) have significant potential in improving motor function for neurorehabilitation. Despite recent advancements, learning diversified EEG features across different frequency ranges remains a significant challenge, as the homogenization of feature representations often limits the generalization capabilities of EEG decoding models for BCIs. In this paper, we propose a novel multiscale convolutional transformer framework for EEG decoding that integrates multiscale convolution, transformer, and diverse-aware feature learning scheme (MCTD) to tackle the above challenge. Specifically, we first capture multiple frequency features using dynamic one-dimensional temporal convolution with different kernel lengths. Subsequently, we incorporate convolutional layers and transformers with a contrastive learning scheme to extract discriminative local and global EEG features within a single frequency range. To mitigate the homogenization of features extracted from different frequency ranges, we propose a novel decorrelation regularization. It enables multiscale convolutional transformers produce less correlated features with each other, thereby enhancing the overall expressiveness of EEG decoding model. The performance of MCTD is evaluated on four public MI-based EEG datasets, including the BCI competition III 3a and IV 2a, the BNCI 2015- 001, and the OpenBMI. For the average Kappa/Accuracy scores, MCTD obtains improvements of 3.58%/2.68%, 3.09%/2.20%, 2.33%/1.54%, and 4.44%/2.22%, over the state-of-the-art method on four EEG datasets, respectively. Experimental results demonstrate that our method exhibits superior performance. © 2016 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Fast Smallest Lowest Common Ancestor Computation Based on Stable Match

引用

Journal of computer Science & technology 2013年第2期28卷 366-381页

作者：周军锋蓝国翔陈子阳汤显 School of Information Science and Engineering Yanshan University Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University School of Economics and Management Yanshan University

In this paper, we focus on efficient processing of XML keyword queries based on smallest lowest common ancestor （SLCA） semantics. For a given query Q with m keywords, we propose to use stable matches as the basis for SLCA computation, where each stable match M consists of m nodes that belong to the m distinct keyword inverted lists of Q. M satisfies that no other lowest common ancestor （LCA） node of Q can be found to be located after the first node of M and be a descendant of the LCA of M, based on which the operation of locating a stable match can skip more useless nodes. We propose two stable match based algorithms for SLCA computation, i.e., BSLCA and HSLCA. BSLCA processes two keyword inverted lists each time from the shortest to the longest, while HSLCA processes all keyword inverted lists in a holistic way to avoid the problem of redundant computation invoked by BSLCA. Our extensive experimental results verify the performance advantages of our methods according to various evaluation metrics.

关键词： XML keyword search smallest lowest common ancestor

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：