检索结果-内蒙古大学图书馆

1st MICCAI Challenge on Ultra-Widefield Fundus Imaging for Diabetic Retinopathy, UWF4DR 2024, Held in Conjunction with 27th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2024

作者： Sun, Junfeng Wang, Xinliang Gu, Yunchao State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

ISBN: (纸本)9783031893872

Ultra-widefield fundus images provide a broad view and play an important role in the integration of deep learning and healthcare. Therefore, it is important to obtain high-quality ultra-widefield fundus image data. We participated in Task 1 of the Ultra-Widefield Fundus Imaging for Diabetic Retinopathy Challenge, focusing on ultra-widefield fundus image quality assessment. The performance of the image quality assessment can be improved by tricks in the training and inference procedure, such as data augmentation, label smoothing, image resizing, and integration of deep learning models. We employ the bag of tricks to enhance the performance of ultra-widefield fundus image quality assessment. In this paper, we examine a series of such tricks and empirically assess their impact on the final model through experiments. The experiments demonstrate that by combining these improvements, significant improvements in prediction performance can be achieved. We achieve a test score of 0.9644 in the image quality assessment task of the challenge. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Robust and efficient edge-based visual odometry

引用

Computational Visual Media 2022年第3期8卷 467-481页

作者： Feihu Yan Zhaoxin Li Zhong Zhou State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China Institute of Computing Technology Chinese Academy ofSciencesBeijing 100190China

Visual odometry,which aims to estimate relative camera motion between sequential video frames,has been widely used in the fields of augmented reality,virtual reality,and autonomous ***,it is still quite challenging for stateof-the-art approaches to handle low-texture *** this paper,we propose a robust and efficient visual odometry algorithm that directly utilizes edge pixels to track camera *** contrast to direct methods,we choose reprojection error to construct the optimization energy,which can effectively cope with illumination *** distance transform map built upon edge detection for each frame is used to improve tracking efficiency.A novel weighted edge alignment method together with sliding window optimization is proposed to further improve the *** on public datasets show that the method is comparable to stateof-the-art methods in terms of tracking accuracy,while being faster and more robust.

关键词： visual odometry(VO) edge structure distance transform low-texture

来源：评论

学校读者我要写书评

暂无评论

Identification of Gingival Inflammation Surface Image Features Using Intraoral Scanning and Deep Learning

引用

International Dental Journal 2025年第3期75卷 2104-2114页

作者： Li, Wei Li, Linlin Xu, Wenchong Guo, Yuting Xu, Min Huang, Shengyuan Dai, Dong Lu, Chang Li, Shuai Lin, Jiang Department of Stomatology Beijing Tongren Hospital Capital Medical University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

Introduction and aim: The assessment of gingival inflammation surface features mainly depends on subjective judgment and lacks quantifiable and reproducible indicators. Therefore, it is a need to acquire objective identification information for accurate monitoring and diagnosis of gingival inflammation. This study aims to develop an automated method combining intraoral scanning (IOS) and deep learning algorithms to identify the surface features of gingival inflammation and evaluate its accuracy and correlation with clinical indicators. Methods: The study included the periodontal probing data and intraoral scan images of 120 patients with periodontitis. The deep learning model GC-U-Net was used to automatically segment and identify the gingival inflammation regions. The performance of the model was evaluated by the Dice coefficient (Dice), intersection over union (IoU), and pixel accuracy (PA), and the correlation between the identification performance and the periodontal examination index was analysed. Results: The GC-U-Net model showed high recognition accuracy, with a Dice of 77.8%, an IoU of 65.4%, and a PA of 93.7%. This model demonstrated a strong positive correlation with the sulcus bleeding index (SBI;r = 0.836, P < .001), a moderately strong positive correlation with the bleeding index (BI;r = 0.618, P < .001), and a negative correlation with the probe depth (PD;r = - 0.425, P < .001). Conclusion: The study has successfully developed an automatic identification method for surface characteristics of gingival inflammation based on deep learning and IOS technology, providing a standardised and automated auxiliary tool for clinical gingival inflammation examination with high accuracy and significant correlation with clinical indicators. Clinical Relevance: This method can reduce subjective judgment in the clinical assessment of gingival inflammation, improve the consistency and reliability of identification, and play an important auxiliary role in clinical diagn

关键词： Artificial intelligence Deep learning Gingival inflammation Intraoral scanning Periodontitis

来源：评论

学校读者我要写书评

暂无评论

Foveated rendering:A state-of-the-art survey

引用

Computational Visual Media 2023年第2期9卷 195-228页

作者： Lili Wang Xuehuai Shi Yi Liu State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100000China Peng Cheng Laboratory Shengzhen 518000China Beijing Advanced Innovation Center for Biomedical Engineering Beihang UniversityBeijing 100000China.

Recently,virtual reality(VR)technology has been widely used in medical,military,manufacturing,entertainment,and other *** applications must simulate different complex material surfaces,various dynamic objects,and complex physical phenomena,increasing the complexity of VR *** computing devices cannot efficiently render these complex scenes in real time,and delayed rendering makes the content observed by the user inconsistent with the user’s interaction,causing *** rendering is a promising technique that can accelerate *** takes advantage of human eyes’inherent features and renders different regions with different qualities without sacrificing perceived visual *** rendering research has a history of 31 years and is mainly focused on solving the following three *** first is to apply perceptual models of the human visual system into foveated *** second is to render the image with different qualities according to foveation *** third is to integrate foveated rendering into existing rendering paradigms to improve rendering *** this survey,we review foveated rendering research from 1990 to *** first revisit the visual perceptual models related to foveated ***,we propose a new foveated rendering taxonomy and then classify and review the research on this ***,we discuss potential opportunities and open questions in the foveated rendering *** anticipate that this survey will provide new researchers with a high-level overview of the state-of-the-art in this field,furnish experts with up-to-date information,and offer ideas alongside a framework to VR display software and hardware designers and engineers.

关键词： foveated rendering virtual reality(VR) real-time rendering

来源：评论

学校读者我要写书评

暂无评论

Subthreshold Depression Recognition and Correlation Study from Pulse Condition via Stacking Ensemble Algorithm 1st

Subthreshold Depression Recognition and Correlation Study f...

引用

1st International Conference on Extended reality, ICXR 2024

作者： Jiang, Han Li, Ming Gao, Yang Li, Peiru State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9789819636785

Subthreshold depression, a transition state to depression, seriously hinders the early diagnosis of depression. Current studies mostly use heterogeneous definitions of subthreshold depression, making the results of such meta-analyses questionable. Therefore, it is of vital significance to develop an objective method for the diagnosis of subthreshold depression based on objective criteria. In traditional Chinese medicine (TCM), symptoms similar to subthreshold depression have been extensively explored. However, diagnostic methods in TCM still depend heavily on the experience of doctors and lack integration with modern diagnostic techniques, which makes it challenging to explain the pathogenesis of subthreshold depression. Consequently, we propose an explainable framework, based on a stacking ensemble algorithm, for subthreshold depression recognition from biomarkers in the pulse waveform and concepts of pulse in TCM. In this method, Naive Bayes, Random Forest, Extremely Randomized Trees, Categorical Boosting and Logistic Regression are chosen as basic learners, and XGBoost is selected as the meta-classifier. Based on the five-fold cross-validation method, grid search method and repetition of training, the stacking ensemble model shows superiority on most performance evaluation metrics including AUC, F1 scores, MCC, precision and sensitivity. Besides, by analyzing the Adjusted Odds Ratio of features in the pulse waveform, we obtained four features that have a high correlation with the occurrence of subthreshold depression and derived physiological changes in patients with subthreshold depression based on their physiological significance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Reborn of the White Bone Demon: Role-Playing Game Design Using Generative AI in XR 24

Reborn of the White Bone Demon: Role-Playing Game Design Usi...

引用

2024 SIGGRAPH Asia 2024 Posters, SA 2024

作者： Liang, Xiaozhan Wang, Yu Yan, Fengyi Ouyang, Zehong Hu, Yong Luo, Siyu Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Tsinghua University China

ISBN: (纸本)9798400711381

This paper explores the application of Generative Artificial Intelligence (GenAI) techniques to the design of Role Playing Games (RPGs) in Extended reality (XR) environments. We developed the game Reborn of the White Bone Demon, which utilizes AI speech emotion recognition technology to generate story lines and game assets in real-time based on the player's conversations with NPCs, enhancing the player's immersion and personalized experience, demonstrating the potential of GenAI in enhancing the XR gaming experience. © 2024 Copyright held by the owner/author(s).

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Discriminative feature encoding for intrinsic image decomposition

引用

Computational Visual Media 2023年第3期9卷 597-618页

作者： Zongji Wang Yunfei Liu Feng Lu Key Laboratory of Network Information System Technology(NIST) Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peng Cheng Laboratory Shenzhen 518000China

Intrinsic image decomposition is an important and long-standing computer vision *** an input image,recovering the physical scene properties is *** physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image *** work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high *** focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input *** achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding *** define feature distribution divergence to efficiently separate the feature vectors of different intrinsic *** feature distributions are also constrained to fit the real ones through a feature distribution *** addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image *** method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent *** results indicate that our proposed network structure can outperform the existing state-of-the-art.

关键词： intrinsic image decomposition deep learning feature distribution data refinement

来源：评论

学校读者我要写书评

暂无评论

Active electronic skin:an interface towards ambient haptic feedback on physical surfaces

引用

npj Flexible Electronics 2024年第1期8卷 684-710页

作者： Yuan Guo Yun Wang Qianqian Tong Boxue Shan Liwen He Yuru Zhang Dangxiao Wang State Key Lab of Virtual Reality Technology and Systems BeijingChina School of Mechanical Engineering and Automation Beihang UniversityBeijingChina Department of Strategic and Advanced Interdisciplinary Research Peng Cheng LaboratoryShenzhenChina

In the era of ubiquitous computing with flourished visual displays in our surroundings,the application of haptic feedback technology still remains in its *** the gap between haptic technology and the real world to enableambient haptic feedback on various physical surfaces is a grand challenge in the field of human-computer *** paper presents the concept of an active electronic skin,characterized by three features:richness(multi-modal haptic stimuli),interactivity(bi-directional sensing and actuation capabilities),and invisibility(transparent,ultra-thin,flexible,and stretchable).By deploying this skin on physical surfaces,dynamic and versatile multi-modal haptic display,as well as tactile sensing,can be *** potential applications of this skin include two categories:skin for the physical world(such as intelligent home,intelligent car,and intelligent museum),and skin for the digital world(such as haptic screen,wearable device,and bare-hand device).Furthermore,existing skin-based haptic display technologies including texture,thermal,and vibrotactile feedback are surveyed,as well as multidimensional tactile sensing *** analyzing the gaps between current technologies and the goal of ambient haptics,future research topics are proposed,encompassing fundamental theoretical research on the physiological and psychological perception mechanisms of human skin,spatial-temporal registration among multimodal haptic stimuli,integration between sensing and actuation,and spatial-temporal registration between visual and haptic *** concept of active electronic skin is promising for advancing the field of ambient haptics,enabling seamless integration of touch into our digital and physical surroundings.

关键词： Active ambient electronic

来源：评论

学校读者我要写书评

暂无评论

Adaptive multiscale microscope with fast zooming,extended working distance,and large field of view

引用

Light(Advanced Manufacturing) 2024年第1期5卷 60-72页

作者： Yi Zheng Xin Wang Zhao Jiang Jinbo Xu Rongying Yuan Youran Zhao Haoran Zhang Chao Liu Qionghua Wang School of Instrumentation and Optoelectronic Engineering Beihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China

The field-of-view(FOV),depth of field,and resolution of conventional microscopes are constrained by each other;therefore,a zoom function is *** zoom methods lose real-time performance and have limited information throughput,severely limiting their application,especially in three-dimensional dynamic imaging and large-amount or large-size sample ***,an adaptive multiscale(AMS)imaging mechanism combining the benefits of liquid lenses and multiscale imaging techniques is proposed to realize the functions of fast zooming,wide working distance(WD)range and large FOV on a self-developed AMS *** design principles were ***,a nonuniform-distortion-correction algorithm and a composite patching algorithm were designed to improve image *** continuous tunable magnification range of the AMS microscope is from 9×to 18×,with the corresponding FOV diameters and resolution ranging from 2.31 to 0.98 mm and from 161 to 287 line-pairs/mm,*** extended WD range is 0.8 mm and the zoom response time is 38 *** demonstrated the advantages of the proposed microscope in pathological sample scanning,thick-sample imaging,microfluidic process monitoring,and the observation of living *** proposed microscope is the first step towards zoom multiscale imaging technology and is expected to be applied in life sciences,medical diagnosis,and industrial detection.

关键词： Microscope Multiscale Liquid lens Zoom

来源：评论

学校读者我要写书评

暂无评论

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning 38

Transforming Vision Transformer: Towards Efficient Multi-Tas...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zhong, Hanwen Chen, Jiaxin Zhang, Yutong Huang, Di Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University China School of Computer Science and Engineering Beihang University Beijing China

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://***/Yewen1486/EMTAL. © 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：