检索结果-内蒙古大学图书馆

Asymmetric Dual-Stream Networks for Lightweight RGB-D Salient Object Detection

Journal of Shanghai Jiaotong University (Science) 2025年 1-11页

作者： Wang, Yan Zheng, Wanlu Xia, Yaozheng Wang, Shaorong School of Information Science and Technology Beijing Forest University Beijing100083 China Engineering Research Center for Forestry-oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing100083 China Beijing Virtual Simulation and Visualization Engineering Center Beijing100871 China

Integrating image and depth information for RGB-D salient object detection has become a research hotspot in the field of saliency detection. Balancing the efficiency and performance of salient object detection models under resource constraints is a key challenge. To address this, this paper proposes an asymmetric lightweight network suitable for real-time RGB-D salient object detection tasks. The network reduces the number of network parameters by designing different lightweight feature extraction networks for different input modalities. Additionally, a multi-modal feature enhancement fusion module is designed to effectively fuse multi-modal features while compensating for the information loss caused by the lightweight backbone network. Moreover, this paper utilizes a global context module for dense decoding, aggregating local and global information of multi-scale features without significantly increasing computational complexity. The experimental results on five benchmarks show that the proposed lightweight RGB-D salient object detection network not only outperforms most mainstream models quantitatively and qualitatively, but also significantly outperforms other models in terms of efficiency, only with a parameter count of 5.1 million and a computational load of 0.77 gigaflops. This achievement validates the proposed method’s ability to achieve lightweight salient object detection while maintaining high efficiency. © Shanghai Jiao Tong University 2024.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Homography-guided stereo matching for wide-baseline image interpolation

引用

Computational Visual Media 2022年第1期8卷 119-133页

作者： Yuan Chang Congyi Zhang Yisong Chen Guoping Wang Peking University Beijing 100871China Beijiing Engineering Technology Research Center of Virtual Simulation and Visualization Peking UniversityBeijing 100871China The University of Hong Kong Hong KongChina

Image interpolation has a wide range of applications such as frame rate-up conversion and free viewpoint *** significant progresses,it remains an open challenge especially for image pairs with large *** this paper,we first propose a novel optimization algorithm for motion estimation,which combines the advantages of both global optimization and a local parametric transformation *** perform optimization over dynamic label sets,which are modified after each iteration using the prior of piecewise consistency to avoid local *** we apply it to an image interpolation framework including occlusion handling and intermediate image *** validate the performance of our algorithm experimentally,and show that our approach achieves state-of-the-art performance.

关键词： image interpolation view synthesis homo-graphy propagation belief propagation

来源：评论

学校读者我要写书评

暂无评论

Simulation of collective pursuit-evasion behavior with runtime situational awareness

Simulation of collective pursuit-evasion behavior with runti...

引用

作者： Yu, Zhenjing Tan, Junyin Li, Sheng School of Computer Science Peking University Beijing China Beijing Engineering Technology Research Center of Virtual Simulation and Visualization Beijing China

We present a simulation method of pursuit-evasion behaviors between different herds with runtime situational awareness. We model the collective movement of predators and prey in the hunting process based on an improved Boid model and the finite state machine involving multiple perception factors about the situations. Taking wolves hunting caribous as an example, our method not only simulates the collective behavior, but also realizes individual intelligent behaviors consistent with the observations. We conducted intensive experiments, and the results show that our method can simulate more realistic pursuit-evasion behavior under different testing scenarios with a variety of parameters. Our method can be easily transferred to the theoretical study of collective behaviors of other herds. © 2022 John Wiley & Sons Ltd.

关键词： collective behavior perception pursuit-evasion situational awareness

来源：评论

学校读者我要写书评

暂无评论

A homogenization method for nonlinear inhomogeneous elastic materials

引用

virtual Reality & Intelligent Hardware 2021年第2期3卷 156-170页

作者： Jing ZHAO Fei ZHU Liyou XU Yong TANG Sheng LI College of Information Science and Engineering Yanshan UniversityQinhuangdaoHebei 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei 066004China School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Beijing Engineering Research Center for Virtual Simulation and Visualization Beijing 100871China

Background Fast simulation techniques are strongly favored in computer graphics,especially for the nonlinear inhomogeneous elastic *** homogenization theory is a perfect match to simulate inhomogeneous deformable objects with its coarse discretization,as it reveals how to extract information at a fine scale and to perform efficient computation with much less *** existing homogenization method is not applicable for ubiquitous nonlinear materials with the limited input deformation *** In this paper,we have proposed a homogenization method for the efficient simulation of nonlinear inhomogeneous elastic *** approach allows for a faithful approximation of fine,heterogeneous nonlinear materials with very coarse *** analysis provides the basis of a linear deformation space and modal derivatives extend the space to a nonlinear regime;based on this,we exploited modal derivatives as the input characteristic deformations for *** also present a simple elastic material model that is nonlinear and anisotropic to represent the homogenized *** nonlinearity of material deformations can be represented properly with this *** material properties for the coarsened model were solved via a constrained optimization that minimizes the weighted sum of the strain energy deviations for all input deformation *** arbitrary number of bases can be used as inputs for homogenization,and greater weights are placed on the more important low-frequency *** Based on the experimental results,this study illustrates that the homogenized material properties obtained from our method approximate the original nonlinear material behavior much better than the existing homogenization method with linear displacements,and saves orders of magnitude of computational *** The proposed homogenization method for nonlinear inhomogeneous elastic materials is capable of capturing the nonlinear dynamics of the

关键词： Physical-based simulation Homogenization theory Heterogeneous material Modal basis

来源：评论

学校读者我要写书评

暂无评论

Object Segmentationin 3D Reconstructed Scenes Based on Gaussian Splatting

引用

Jisuanji Xuebao/Chinese Journal of Computers 2025年第5期48卷 1232-1243页

作者： Wang, Feng Yin, Ying Wang, Jia-Yan Tang, Yong Li, Sheng Zhao, Jing School ofInformation Science and Engineering Yanshan University Hebei Qinhuangdao066004 China Hebei Key Laboratory of Computer Virtual Technology and SystemIntegration Hebei Qinhuangdao066004 China School of Computer Science Peking University Beijing100871 China Beijing Engineering Technology Research Center of Virtual Simulationand Visualization Peking University Beijing100871 China

In the field of 3D reconstruction- the recent introduction of 3D Gaussian splatting has led to substantial advancements in both training efficiency and reconstruction quality, especially when compared to traditional neural radiance field-based approaches. These advancements make 3D Gaussian splatting a promising tool for reconstructing complex scenes with high accuracy and efficiency, significantly reducing the training time compared to the methods based on Neural Radiance Fields. However* challenges remain in effectively segmenting the reconstructed scenes* particularly when dealing with intricate occlusions and overlapping objects. Scene segmentation in such complcx environments becomes difficult due to the dynamic interactions between objects, subtle boundarics, and the presence of noise in the reconstruction process. These challenges hin-der the accurate identification and isolation of specific objects within the scene, which is critical for a ränge of practical applications. To address this issue, this papcr proposcs a novel, light-wcight method for 3D Gaussian-based scene segmentation that effectively Segments specific objects from a rcconstructed scene. The core innovation of this approach is the use of the differenti-able nature of 3D Gaussian splatting during the reconstruction process, which allows for the sim-ultaneous training of object dass features alongside the scene reconstruction. Specifically, a dass feature is associated with each Gaussian kernel, encoding semantic information that is crucial for object recognition and Classification within the 3D space. These dass features arc traincd to dis-tinguish between different objects and map them to specific object categories. After embcdding the dass features into the scene, a multi-layer perceptron decoder is designed and trained to map the dass features to object dass labels, allowing the System to identify and classify objects based on the features associated with each Gaussian kernel. During the ren

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

FluidPlaying: Efficient Adaptive Simulation for Highly Dynamic Fluid

FluidPlaying: Efficient Adaptive Simulation for Highly Dynam...

引用

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

作者： Sinuo Liu Xiaojuan Ban Sheng Li Haokai Zeng Xiaokun Wang Yanrui Xu Fei Zhu Guoping Wang Graphics & Interaction Lab National Biomedical Imaging Center School of Computer Science Peking University School of Intelligence Science and Technology University of Science and Technology Beijing Beijing Engineering Technology Research Center of Virtual Simulation and Visualization Peking University Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)

We present FliudPlaying, a novel dynamic level-based spatially adaptive simulation method that can handle highly dynamic fluid efficiently. To capture the subtle detail of the fluid surface, the high-resolution simulation is performed not only at the free surface but also at those regions with high vorticity levels and velocity difference levels. To minimize the density error, an online optimization scheme is used when increasing the resolution by particle splitting. We also proposed a neighbor-based splash enhancement to compensate for the loss of dynamic details. Compared with the high-resolution simulation baseline, our method can achieve over 3× speedups while consuming only less than 10% computational resources. Furthermore, our method can make up for the loss of high-frequency details caused by the spatial adaptation, and provide more realistic dynamics in particle-based fluid simulation.

关键词： Solid modeling Adaptation models Three-dimensional displays Fluid dynamics Computational modeling Conferences virtual reality

来源：评论

学校读者我要写书评

暂无评论

Temporal continuity of visual attention for future gaze prediction in immersive virtual reality

引用

virtual Reality & Intelligent Hardware 2020年第2期2卷 142-152页

作者： Zhiming HU Sheng LI Meng GAI Department of Computer Science and Technology School of Electronic Engineering and Computer SciencePeking UniversityBeijing 100871China Beijing Engineering Technology Research Center of Virtual Simulation and Visualization Peking UniversityBeijing 100871China

Background Eye tracking te chnology is receiving increased attention in the field of virtual ***,future gaze prediction is crucial in pre-computation for many applications such as gaze-contingent rendering,advertisement placement,and content-based *** explore future gaze prediction,it is necessary to analyze the temporal continuity of visual attention in immersive virtual *** In this paper,the concept of temporal continuity of visual attention is ***,an autocorrelation function method is proposed to evaluate the temporal ***,the temporal continuity is analyzed in both free-viewing and task-oriented *** Specifically,in free-viewing conditions,the analysis of a free-viewing gaze dataset indicates that the temporal continuity performs well only within a short time interval.A task-oriented game scene condition was created and conducted to collect users'gaze *** analysis of the collected gaze data finds the temporal continuity has a similar performance with that of the free-viewing *** continuity can be applied to future gaze prediction and if it is good,users'current gaze positions can be directly utilized to predict their gaze positions in the *** The current gaze's future prediction performances are further evaluated in both free-viewing and task-oriented conditions and discover that the current gaze can be efficiently applied to the task of short-term future gaze *** task of long-term gaze prediction still remains to be explored.

关键词： Temporal continuity Visual attention Autocorrelation analysis Gaze prediction virtual reality

来源：评论

学校读者我要写书评

暂无评论

ADVISor: Automatic visualization Answer for Natural-Language Question on Tabular Data

ADVISor: Automatic Visualization Answer for Natural-Language...

引用

Pacific (formerly Asia-Pacific APVIS) visualization Symposium

作者： Can Liu Yun Han Ruike Jiang Xiaoru Yuan Key Laboratory of Machine Perception (Ministry of Education) and School of EECS Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Application Peking University Beijing China Beijing Engineering Technology Research Center of Virtual Simulation and Visualization Peking University Beijing China

We propose an automatic pipeline to generate visualization with annotations to answer natural-language questions raised by the public on tabular data. With a pre-trained language representation model, the input natural language questions and table headers are first encoded into vectors. According to these vectors, a multi-task end-to-end deep neural network extracts related data areas and corresponding aggregation type. We present the result with carefully designed visualization and annotations for different attribute types and tasks. We conducted a comparison experiment with state-of-the-art works and the best commercial tools. The results show that our method outperforms those works with higher accuracy and more effective visualization.

关键词： Annotations Natural languages Pipelines Neural networks Data visualization Tools Data mining

来源：评论

学校读者我要写书评

暂无评论

Simulating unmanned aerial vehicle flight control and collision detection

引用

Visual Computing for Industry,Biomedicine,and Art 2019年第1期2卷 38-44页

作者： Mengtian Liu Meng Gai Shunnan Lai Peking University Shenzhen Graduate School Shenzhen 518055China School of EECS Peking UniversityBeijing 100871China Beijing Engineering Technology Research Center of Virtual Simulation and Visualization(Peking University) Beijing 100871China

An unmanned aerial vehicle(UAV)is a small,fast aircraft with many useful *** is widely used in military reconnaissance,aerial photography,searches,and other fields;it also has very good practical-application and development *** the UAV’s flight orientation is easily changeable,its orientation and flight path are difficult to control,leading to its high damage ***,UAV flight-control technology has become the focus of *** study focuses on simulating a UAV’s flight and orientation control,and detecting collisions between a UAV and objects in a complex virtual *** proportional-integral-derivative control algorithm is used to control the orientation and position of the UAV in a virtual environment.A version of the bounding-box method that combines a grid with a k-dimensional tree is adopted in this paper,to improve the system performance and accelerate the collision-detection *** provides a practical method for future studies on UAV flight position and orientation control,collision detection,etc.

关键词： Unmanned aerial vehicle Proportional-integral-derivative control algorithm Orientation control Position control Grid k-dimensional tree Collision detection

来源：评论

学校读者我要写书评

暂无评论

Interaction+: Interaction enhancement for web-based visualizations 10

Interaction+: Interaction enhancement for web-based visualiz...

引用

10th IEEE Pacific visualization Symposium, PacificVis 2017

作者： Lu, Min Liang, Jie Zhang, Yu Li, Guozheng Chen, Siming Li, Zongru Yuan, Xiaoru Peking University China School of Engineer and Information Technology University of Technology Sydney Australia Beijing Engineering Research Center of Virtual Simulation and Visualization China

ISBN: (纸本)9781509057382

In this work, we present Interaction+, a tool that enhances the interactive capability of existing web-based visualizations. Different from the toolkits for authoring interactions during the visualization construction, Interaction+ takes existing visualizations as input, analyzes the visual objects, and provides users with a suite of interactions to facilitate the visual exploration, including selection, aggregation, arrangement, comparison, filtering, and annotation. Without accessing the underlying data or process how the visualization is constructed, Interaction+ is application-independent and can be employed in various visualizations on the web. We demonstrate its usage in two scenarios and evaluate its effectiveness with a qualitative user study. © 2017 IEEE.

关键词： visualization

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：