检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Zhuguanyu Zhang, Jiayi Chen, Jiaxin Guo, Jinyang 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 School of Artificial Intelligence Beihang University Beijing China

Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops when quantized for practical deployment, particularly by post-training quantization (PTQ) under ultra-low bits. Recently, reconstruction-based PTQ methods have shown promising performance in quantizing Convolutional Neural Networks (CNNs). However, they fail when applied to ViTs, primarily due to the inaccurate estimation of output importance and the substantial accuracy degradation in quantizing post-GELU activations. To address these issues, we propose APHQ-ViT, a novel PTQ approach based on importance estimation with Average Perturbation Hessian (APH). Specifically, we first thoroughly analyze the current approximation approaches with Hessian loss, and propose an improved average perturbation Hessian loss. To deal with the quantization of the post-GELU activations, we design an MLP Reconstruction (MR) method by replacing the GELU function in MLP with ReLU and reconstructing it by the APH loss on a small unlabeled calibration set. Extensive experiments demonstrate that APHQ-ViT using linear quantizers outperforms existing PTQ methods by substantial margins in 3-bit and 4-bit across different vision tasks. The source code is available at https://***/GoatWu/APHQ-ViT. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

VR content creation and exploration with deep learning: A survey

引用

Computational Visual Media 2020年第1期6卷 3-28页

作者： Miao Wang Xu-Quan Lyu Yi-Jun Li Fang-Lue Zhang State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China. Peng Cheng Laboratory Shenzhen 518000China School of Engineering and Computer Science Victoria University of WellingtonNew Zealand

virtual reality(VR)offers an artificial,computer generated simulation of a real life *** originated in the 1960 s and has evolved to provide increasing immersion,interactivity,imagination,and *** deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion,they can build very powerful models which leverage large quantities of visual media *** of VR methods and applications has been significantly boosted by the recent developments in deep learning *** content creation and exploration relates to image and video analysis,synthesis and editing,so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed,designed specifically to handle panoramic images and video and virtual 3 D *** article surveys recent research that uses such deep learning methods for VR content creation and *** considers the problems involved,and discusses possible future directions in this active and emerging research area.

关键词： virtual reality deep learning neural networks 360°image and video virtual content

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

DAU-Net: A medical image segmentation network combining the Hadamard product and dual scale attention gate

引用

Mathematical Biosciences and Engineering 2024年第2期21卷 2753-2767页

作者： Zhang, Xiaoyan He, Mengmeng Li, Hongan School of Computer Science and Technology Xi’an University of Science and Technology Xi’an710054 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Medical image segmentation has an important application value in the modern medical field, it can help doctors accurately locate and analyze the tissue structure, lesion areas, and organ boundaries in the image, which provides key information support for clinical diagnosis and treatment, but there are still a large number of problems in the accuracy of the segmentation, so in this paper, we propose a medical image segmentation network combining the Hadamard product and dual-scale attention gate (DAU-Net). First, the Hadamard product is introduced in the structure of the fifth layer of the codec for element-by-element multiplication, which can generate feature representations with more representational capabilities. Second, in the jump connection module, we propose a dual scale attention gating (DSAG), which can highlight more valuable features and achieve more efficient jump connections. Finally, in the decoder feature structure, the final segmentation result is obtained by aggregating the feature information provided by each part, and decoding is achieved by up-sampling operation. Through experiments on two public datasets, Luna and Isic2017, DAU-Net is able to extract feature information more efficiently using different modules and has better segmentation results compared to classical segmentation models such as U-Net and U-Net++, and also verifies the effectiveness of the model. © 2024 American Institute of Mathematical Sciences. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Flow-aware synthesis: A generic motion model for video frame interpolation

引用

Computational Visual Media 2021年第3期7卷 393-405页

作者： Jinbo Xing Wenbo Hu Yuechen Zhang Tien-Tsin Wong Department of Computer Science and Engineering the Chinese University of Hong KongHong Kong SARChina Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesChina

A popular and challenging task in video research,frame interpolation aims to increase the frame rate of *** existing methods employ a fixed motion model,e.g.,linear,quadratic,or cubic,to estimate the intermediate warping ***,such fixed motion models cannot well represent the complicated non-linear motions in the real world or rendered ***,we present an adaptive flow prediction module to better approximate the complex motions in ***,interpolating just one intermediate frame between consecutive input frames may be insufficient for complicated non-linear *** enable multi-frame interpolation,we introduce the time as a control variable when interpolating frames between original ones in our generic adaptive flow prediction *** and quantitative experimental results show that our method can produce high-quality results and outperforms the existing stateof-the-art methods on popular public datasets.

关键词： flow-aware generic motion model video frame interpolation

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning andjoint refinement between camera localization and object detection

引用

Computational Visual Media 2024年第5期10卷 993-1011页

作者： Junyi Wang Yue Qi State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peng Cheng Laboratory Shenzhen 518052China Qingdao Research Institute of Beihang University Qingdao 266104China School of Computer Science and Technology Shandong UniversityQingdaoChina

Visual localization and object detection both play important roles in various *** many indoor application scenarios where some detected objects have fixed positions,the two techniques work closely ***,few researchers consider these two tasks simultaneously,because of a lack of datasets and the little attention paid to such *** this paper,we explore multi-task network design and joint refinement of detection and *** address the dataset problem,we construct a medium indoor scene of an aviation exhibition hall through a semi-automatic *** dataset provides localization and detection information,and is publicly available at https://***/drive/folders/1U28zk0N4_I0db zkqyIAK1A15k9oUKOjI?usp=sharing for benchmarking localization and object detection *** this dataset,we have designed a multi-task network,JLDNet,based on YOLO v3,that outputs a target point cloud and object bounding *** dynamic environments,the detection branch also promotes the perception of *** includes image feature learning,point feature learning,feature fusion,detection construction,and point cloud ***,object-level bundle adjustment is used to further improve localization and detection *** test JLDNet and compare it to other methods,we have conducted experiments on 7 static scenes,our constructed dataset,and the dynamic TUM RGB-D and Bonn *** results show state-of-the-art accuracy for both tasks,and the benefit of jointly working on both tasks is demonstrated.

关键词： visual localization object detection joint optimization multi-task learning

来源：评论

学校读者我要写书评

暂无评论

SIVP: a toolkit for integrating visualization into virtual environment

SIVP: a toolkit for integrating visualization into virtual e...

引用

16th International Conference on Artificial Reality and Telexistence - Workshops, ICAT 2006

作者： Liang, Xiaohui Che, Yinghui Wu, Xiaoxiao Key Laboratory of Virtual Reality Technology School of Computer Sciences Beihang University Beijing China

ISBN: (纸本)076952754X

None-visible data modeling and representation is one of the key topics in virtual reality, since it greatly affects the sense of the user. In this paper we present how to visualize none-visible data in the virtual environment and a toolkit called Synthetic Information Visualization Platform (SIVP) is given. This toolkit includes two processes and the main components of SIVP are describes. Finally, we demonstrate some works base on SIVP. © 2006 IEEE.

关键词： virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Redirected Walking Techniques:Taxonomy,Methods,and Future Directions

引用

Journal of computer Science & technology 2022年第3期37卷 561-583页

作者： Yi-Jun Li Frank Steinicke Miao Wang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Department of Informatics Universität HamburgHamburg 20146Germany Peng Cheng Laboratory Shenzhen 518055China

virtual reality(VR)allows users to explore and experience a computer-simulated virtual environment so that VR users can be immersed in a totally artificial virtual world and interact with arbitrary virtual ***,the limited physical tracking space usually restricts the exploration of large virtual spaces,and VR users have to use special locomotion techniques to move from one location to *** these techniques,redirected walking(RDW)is one of the most natural locomotion techniques to solve the problem based on near-natural walking *** core idea of the RDW technique is to imperceptibly guide users on virtual paths,which might vary from the paths they physically walk in the real *** a similar way,some RDW algorithms imperceptibly change the structure and layout of the virtual environment such that the virtual environment fits into the tracking *** this survey,we first present a taxonomy of existing RDW *** on this taxonomy,we compare and analyze both contributions and shortcomings of the existing methods in detail,and find view manipulation methods offer satisfactory visual effect but the experience can be interrupted when users reach the physical boundaries,while virtual environment manipulation methods can provide users with consistent movement but have limited application ***,we discuss possible future research directions,indicating combining artificial intelligence with this area will be effective and intriguing.

关键词： virtual reality locomotion redirected walking

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Detection Method for Shilling Attacks Based on Features of Automatic Extraction

引用

China Communications 2019年第8期16卷 130-146页

作者： Yaojun Hao Fuzhi Zhang Jinbo Chao School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004China Department of Computer Science and Technology Xinzhou Teachers UniversityXinzhou 034000China

Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.

关键词： shilling attack ensemble detection features of automatic extraction marginalized linear denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

3D computational modeling and perceptual analysis of kinetic depth effects

引用

Computational Visual Media 2020年第3期6卷 265-277页

作者： Meng-Yao Cui Shao-Ping Lu Miao Wang Yong-Liang Yang Yu-Kun Lai Paul L.Rosin TKLNDST CSNankai UniversityTianjinChina State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijingChina Department of Computer Science University of BathUK School of Computer Science and Informatics Cardiff UniversityWalesUK

Humans have the ability to perceive kinetic depth effects, i.e., to perceived 3 D shapes from 2 D projections of rotating 3 D objects. This process is based on a variety of visual cues such as lighting and shading effects. However, when such cues are weak or missing, perception can become faulty, as demonstrated by the famous silhouette illusion example of the spinning dancer. Inspired by this, we establish objective and subjective evaluation models of rotated3 D objects by taking their projected 2 D images as input. We investigate five different cues: ambient luminance, shading, rotation speed, perspective, and color difference between the objects and *** the objective evaluation model, we first apply3 D reconstruction algorithms to obtain an objective reconstruction quality metric, and then use quadratic stepwise regression analysis to determine weights of depth cues to represent the reconstruction quality. In the subjective evaluation model, we use a comprehensive user study to reveal correlations with reaction time and accuracy, rotation speed, and perspective. The two evaluation models are generally consistent, and potentially of benefit to inter-disciplinary research into visual perception and 3 D reconstruction.

关键词： rotation spinning rotating

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：