检索结果-内蒙古大学图书馆

Multi-granularity sequence generation for hierarchical image classification

Computational Visual Media 2024年第2期10卷 243-260页

作者： Xinda Liu Lili Wang State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China Peng Cheng Laboratory Shengzhen 518000China

Hierarchical multi-granularity image classification is a challenging task that aims to tag each given image with multiple granularity labels *** methods tend to overlook that different image regions contribute differently to label prediction at different granularities,and also insufficiently consider relationships between the hierarchical multi-granularity *** introduce a sequence-to-sequence mechanism to overcome these two problems and propose a multi-granularity sequence generation(MGSG)approach for the hierarchical multi-granularity image classification ***,we introduce a transformer architecture to encode the image into visual representation ***,we traverse the taxonomic tree and organize the multi-granularity labels into sequences,and vectorize them and add positional *** proposed multi-granularity sequence generation method builds a decoder that takes visual representation sequences and semantic label embedding as inputs,and outputs the predicted multi-granularity label *** decoder models dependencies and correlations between multi-granularity labels through a masked multi-head self-attention mechanism,and relates visual information to the semantic label information through a crossmodality attention *** this way,the proposed method preserves the relationships between labels at different granularity levels and takes into account the influence of different image regions on labels with different *** on six public benchmarks qualitatively and quantitatively demonstrate the advantages of the proposed *** project is available at https://***/liuxindazz/mgs.

关键词： hierarchical multi-granularity classification vision and text transformer sequence generation fine-grained image recognition cross-modality attenti

来源：评论

学校读者我要写书评

暂无评论

Extremum seeking control for UAV close formation flight via improved pigeon-inspired optimization

引用

Science China(Technological Sciences) 2024年第2期67卷 435-448页

作者： YUAN GuangSong DUAN HaiBin State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical EngineeringBeihang University(BUAA)Beijing 100083China

This paper proposes a comprehensive design scheme for the extremum seeking control(ESC)of the unmanned aerial vehicle(UAV)close formation *** proposed design scheme combines a Newton-Raphson method with an extended Kalman filter(EKF)to dynamically estimate the optimal position of the following UAV relative to the leading *** reflect the wake vortex effects reliably,the drag coefficient induced by the wake vortex is considered as a performance ***,the performance function is parameterized by the first-order and second-order terms of its Taylor series *** the excellent performance of nonlinear estimation,the EKF is used to estimate the gradient and the Hessian matrix of the parameterized performance *** output feedback of the proposed scheme is determined by iterative calculation of the Newton-Raphson *** with the traditional ESC and the classic ESC,the proposed design scheme avoids the slow continuous time integration of the *** allows a faster convergence of relative position ***,the proposed method can provide a smoother command during the seeking process as the second-order term of the performance function is taken into *** convergence analysis of the proposed design scheme is accomplished by showing that the output feedback is a supermartingale *** improve estimation performance of the EKF,a improved pigeon-inspired optimization(IPIO)is proposed to automatically tune the noise covariance *** Carlo simulations for a three-UAV close formation show that the proposed design scheme is robust to the initial position of the following UAV.

关键词： unmanned aerial vehicle close formation extremum seeking control Newton-Raphson method improved pigeon-inspired optimization

来源：评论

学校读者我要写书评

暂无评论

AR assistance for efficient dynamic target search

引用

Computational Visual Media 2023年第1期9卷 177-194页

作者： Zixiang Zhao Jian Wu Lili Wang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijingChina

When searching for a dynamic target in an unknown real world scene,search efficiency is greatly reduced if users lack information about the spatial structure of the *** target search studies,especially in robotics,focus on determining either the shortest path when the target’s position is known,or a strategy to find the target as quickly as possible when the target’s position is ***,the target’s position is often known intermittently in the real world,e.g.,in the case of using surveillance *** goal is to help user find a dynamic target efficiently in the real world when the target’s position is intermittently *** order to achieve this purpose,we have designed an AR guidance assistance system to provide optimal current directional guidance to users,based on searching a prediction *** assume that a certain number of depth cameras are fixed in a real scene to obtain dynamic target’s *** system automatically analyzes all possible meetings between the user and the target,and generates optimal directional guidance to help the user catch up with the target.A user study was used to evaluate our method,and its results showed that compared to free search and a top-view method,our method significantly improves target search efficiency.

关键词： augmented reality(AR) search guidance

来源：评论

学校读者我要写书评

暂无评论

FDCPNet:feature discrimination and context propagation network for 3D shape representation

引用

虚拟现实与智能硬件(中英文) 2025年第1期7卷 83-94页

作者： Weimin SHI Yuan XIONG Qianwen WANG Han JIANG Zhong ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Background Three-dimensional(3D)shape representation using mesh data is essential in various applications,such as virtual reality and simulation *** methods for extracting features from mesh edges or faces struggle with complex 3D models because edge-based approaches miss global contexts and face-based methods overlook variations in adjacent areas,which affects the overall *** address these issues,we propose the Feature Discrimination and Context Propagation Network(FDCPNet),which is a novel approach that synergistically integrates local and global features in mesh *** FDCPNet is composed of two modules:(1)the Feature Discrimination Module,which employs an attention mechanism to enhance the identification of key local features,and(2)the Context Propagation Module,which enriches key local features by integrating global contextual information,thereby facilitating a more detailed and comprehensive representation of crucial areas within the mesh *** Experiments on popular datasets validated the effectiveness of FDCPNet,showing an improvement in the classification accuracy over the baseline ***,even with reduced mesh face numbers and limited training data,FDCPNet achieved promising results,demonstrating its robustness in scenarios of variable complexity.

关键词： 3D shape representation Mesh model MeshNet Feature discrimination Context propagation

来源：评论

学校读者我要写书评

暂无评论

Web-based mixed reality video fusion with remote rendering

引用

virtual reality & Intelligent Hardware 2023年第2期5卷 188-199页

作者： Qiang ZHOU Zhong ZHOU State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China

Background Mixed reality(MR)video fusion systems merge video imagery with 3D scenes to make the scene more realistic and help users understand the video content and temporal–spatial correlation between them,reducing the user′s cognitive *** video fusion are used in various applications;however,video fusion systems require powerful client machines because video streaming delivery,stitching,and rendering are computationally ***,huge bandwidth usage is another critical factor that affects the scalability of video-fusion *** Our framework proposes a fusion method for dynamically projecting video images into 3D models as *** Several experiments on different metrics demonstrate the effectiveness of the proposed *** The framework proposed in this study can overcome client limitations by utilizing remote ***,the framework we built is based on ***,the user can test the MR video fusion system with a laptop or tablet without installing any additional plug-ins or application programs.

关键词： Mixed reality Video fusion WebRTC Remote rendering

来源：评论

学校读者我要写书评

暂无评论

Model-guided 3D stitching for augmented virtual environment

引用

Science China(Information Sciences) 2023年第1期66卷 115-130页

作者： Zhong ZHOU Ming MENG Yi ZHOU Zhe ZHU Jingdi YOU State Key Laboratory of Virtual Reality Technology and Systems Beihang University Department of Radiology Duke University Beijing Big View Technology Co. Ltd.

Image and video stitching have made tremendous progress in the construction of wide field-of-view(FOV). However, some long-term challenges still exist, including wide baselines between cameras,large parallaxes, and low texture in overlapping areas. The augmented virtual environment(AVE) captures videos as live textures of 3D models in a virtual environment, and provides another 3D solution to overcome the aforementioned challenges. Existing AVE methods primarily follow from video projection, and cannot produce satisfactory stitching results compared with image stitching. In this paper, we propose a novel model-guided 3D stitching algorithm for AVE. The algorithm recovers an approximate 3D model for each video streaming and optimizes the warping of the models to meet the requirements of feature point matching of the 3D models from adjacent videos. Compared with previous state-of-the-art methods, experiment results illustrate that our method significantly improves the stitching quality.

关键词： 3D stitching video model multiple video visualization augmented virtual environment

来源：评论

学校读者我要写书评

暂无评论

kLCRNet: Fast Road Network Extraction Via keypoint-Driven Local Connectivity Exploration

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12074-12089页

作者： Zhang, Mingming Wang, Bin Yang, Shuai Liu, Qingjie Wang, Yunhong Beihang University Hangzhou Innovation Institute Hangzhou310051 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China

Road network extraction from remote sensing images has been extensively studied in recent decades. While many approaches output road networks in vector format, most are not fully end-to-end, requiring time-consuming post-processing steps. Additionally, challenges like isomorphic encoding limit the flexibility of these methods. In this paper, we present kLCRNet, an efficient road network extraction framework that overcomes these limitations by leveraging keypoint-driven local connectivity exploration. kLCRNet consists of two key components: a keypoint detection (KPD) module that identifies road keypoints via heatmap-based detection and refines them using bipartite matching, and a local connectivity exploration (LCE) module that samples local connection relationships to directly construct connectivity between detected keypoints. Experiments on the CityScale and SpaceNet datasets demonstrate that kLCRNet outperforms state-of-the-art (SOTA) methods in topological accuracy and connectivity. Additionally, kLCRNet significantly improves inference speed by up to 25 times, highlighting its efficiency and effectiveness. © 2008-2012 IEEE.

关键词： Roads Accuracy Remote sensing Feature extraction Vectors Iterative methods Image segmentation Semantic segmentation Encoding Decoding

来源：评论

学校读者我要写书评

暂无评论

From animal collective behaviors to swarm robotic cooperation

引用

National Science Review 2023年第5期10卷 82-99页

作者： Haibin Duan Mengzhen Huo Yanming Fan State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical EngineeringBeihang University Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng Laboratory AVIC Shenyang Aircraft Design and Research Institute

The collective behaviors of animals,from schooling fish to packing wolves and flocking birds,display plenty of fascinating phenomena that result from simple interaction rules among *** emergent intelligent properties of the animal collective behaviors,such as self-organization,robustness,adaptability and expansibility,have inspired the design of autonomous unmanned swarm *** article reviews several typical natural collective behaviors,introduces the origin and connotation of swarm intelligence,and gives the application case of animal collective *** this basis,the article focuses on the forefront of progress and bionic achievements of aerial,ground and marine robotics swarms,illustrating the mapping relationship from biological cooperative mechanisms to cooperative unmanned cluster ***,considering the significance of the coexisting-cooperative-cognitive human-machine system,the key technologies to be solved are given as the reference directions for the subsequent exploration.

关键词： collective behaviors swarm intelligence cooperative robotics swarm human-machine system

来源：评论

学校读者我要写书评

暂无评论

Saliency Based Data Augmentation for Few-Shot Video Action Recognition 31st

Saliency Based Data Augmentation for Few-Shot Video Action ...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Kong, Yongqiang Wang, Yunhong Li, Annan The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

ISBN: (纸本)9789819620630

Despite the progress made in few-shot video action recognition, existing methods still struggle to achieve satisfactory performance when support samples are limited (e.g., 1-shot task). This paper proposes to augment training samples without relying on additional supervision and labor costs, aiming at improving generalizability of learned representations. We introduce a novel self-supervised salient object detection model which results in frame-level saliency and background features of videos. A shared encoder is employed to fuse saliency and background information from different videos. Both intra- and inter-class fusion are performed, in which the latter is controlled by prior probability to avoid semantic ambiguities. This way actually corresponds to augment training data in feature space. The saliency-background representations formed from query and support videos are used to construct class prototypes through Temporal-Relational CrossTransformers. Experimental results on four standard benchmarks demonstrate that the proposed method outperforms state-of-the-arts under various few-shot settings, particularly excelling in the 1-shot case. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wages

来源：评论

学校读者我要写书评

暂无评论

How to Use Diffusion Priors under Sparse Views? 38

How to Use Diffusion Priors under Sparse Views?

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Wang, Qisen Zhao, Yifan Ma, Jiawei Li, Jia State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University China

Novel view synthesis under sparse views has been a long-term important challenge in 3D reconstruction. Existing works mainly rely on introducing external semantic or depth priors to supervise the optimization of 3D representations. However, the diffusion model, as an external prior that can directly provide visual supervision, has always underperformed in sparse-view 3D reconstruction using Score Distillation Sampling (SDS) due to the low information entropy of sparse views compared to text, leading to optimization challenges caused by mode deviation. To this end, we present a thorough analysis of SDS from the mode-seeking perspective and propose Inline Prior Guided Score Matching (IPSM), which leverages visual inline priors provided by pose relationships between viewpoints to rectify the rendered image distribution and decomposes the original optimization objective of SDS, thereby offering effective diffusion visual guidance without any fine-tuning or pre-training. Furthermore, we propose the IPSM-Gaussian pipeline, which adopts 3D Gaussian Splatting as the backbone and supplements depth and geometry consistency regularization based on IPSM to further improve inline priors and rectified distribution. Experimental results on different public datasets show that our method achieves state-of-the-art reconstruction quality. The code is released at https://***/iCVTEAM/IPSM. © 2024 Neural information processing systems foundation. All rights reserved.

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：