检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Guiwei Zhang, Yongfei Tan, Zichang Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang Univerisity Beijing China Beijing Key Laboratory of Digital Media State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang Univerisity Beijing China Baidu Inc. Beijing China

Visible-Infrared person re-identification is challenging due to the large modality gap. To bridge the gap, most studies heavily rely on the correlation of visible-infrared holistic person images, which may perform poorly under severe distribution shifts. In contrast, we find that some cross-modal correlated high-frequency components contain discriminative visual patterns and are less affected by variations such as wavelength, pose, and background clutter than holistic images. Therefore, we are motivated to bridge the modality gap based on such high-frequency components, and propose Prototype-guided High-frequency Patch Enhancement (ProtoHPE) with two core designs. First, to enhance the representation ability of cross-modal correlated high-frequency components, we split patches with such components by Wavelet Transform and exponential moving average vision Transformer (ViT), then empower ViT to take the split patches as auxiliary input. Second, to obtain semantically compact and discriminative high-frequency representations of the same identity, we propose Multimodal Prototypical Contrast. To be specific, it hierarchically captures comprehensive semantics of different modal instances, facilitating the aggregation of high-frequency representations belonging to the same identity. With it, ViT can capture key high-frequency components during inference without relying on ProtoHPE, thus bringing no extra complexity. Extensive experiments validate the effectiveness of ProtoHPE. Copyright © 2023, The Authors. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Access Authentication for Mega-Constellation based on Hierarchical Consensus

Access Authentication for Mega-Constellation based on Hierar...

引用

Satellite Computing (Satellite), IEEE International Conference on

作者： Xin Lai Zhiyuan Wang Shan Zhang Qingkai Meng Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems State Key Laboratory of Software Development Environment Institute of Artificial Intelligence Beihang University Beijing China

Low earth orbit (LEO) constellation has the potential to provide low-latency Internet services with the global coverage. However, LEO satellite networks with open channels and dynamic topology are faced with crucial security issue on authenticating terrestrial users. In this paper, we propose an access authentication method for LEO satellite networks based on consensus protocol PBFT, aiming to achieve small communication overhead and high authentication accuracy. The PBFT consensus protocol tolerates Byzantine nodes with the ratio 1/3, but incurs a tremendous communication overhead, therefore, it is not deployable in mega-constellation. To address this challenge, we propose to divide the LEO constellation into multiple consensus groups and present the design of hierarchical PBFT (H-PBFT). We analytically derive the communication overhead incurred by PBFT and our proposed H - PBFT and analyze the authentication accuracy achieved by these two protocols given the faulty satellite probability. The analytical results allow us to properly optimize the scale of the consensus groups and attain the desired tradeoff between small communication overhead and high authentication accuracy. Simulation results show that our proposed access authentication method based on H - PBFT outperforms state-of-the-art consensus protocols (i.e., PBFT and double-layer PBFT) in terms of communication overhead and authentication accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CR-Famba: A Frequency-Domain Assisted Mamba for Thin Cloud Removal in Optical Remote Sensing Imagery

引用

IEEE Transactions on Multimedia 2025年

作者： Liu, Jiao Pan, Bin Shi, Zhenwei Nankai University TKLNDST College of Computer Science Tianjin300350 China Nankai University School of Statistics and Data Science KLMDASR LEBPS LPMC Tianjin300071 China Beihang University Image Processing Center School of Astronautics the State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China

Optical remote sensing images are inevitably affected by cloud cover. To remove clouds from optical remote sensing images, a series of deep learning-based thin cloud removal methods have been developed. However, these methods have not explored the long-range modeling ability of state space models in optical remote sensing image thin cloud removal. In this paper, we propose a frequency-domain assisted Mamba for thin cloud removal, which is called CR-Famba. In CR-Famba, to better extract global and local features of images, we design a frequency-domain assisted state space layer (FDA-SSL). The FDA-SSL consists of two core components: residual state space block (RSSB) and frequency domain detail enhancement block (FDDEB). The RSSB utilizes the visual state space module (VSSM) to extract long-range dependencies of images from a spatial perspective while adding convolutional layers to overcome local pixel forgetting. Due to the rich detailed information of remote sensing images, we present FDDEB equipped with discrete wavelet transform (DWT) to supplement the extracted local information from the frequency domain perspective. We conduct experiments on different types of cloud-containing datasets, and the results show that our method can recover images with clearer texture details compared to other methods. https://***/Lab-PANbin/ © 2025 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment

arXiv

引用

arXiv 2024年

作者： Zhou, Kanglei Li, Junlin Cai, Ruizhi Wang, Liyuan Zhang, Xingxing Liang, Xiaohui Department of Computer Science and Technology Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China Zhongguancun Laboratory China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China China Three Gorges University China

Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost performance on smaller AQA datasets. However, this common strategy yields suboptimal results due to the inherent struggle of these backbones to capture the subtle cues essential for AQA. Moreover, fine-tuning on smaller datasets risks overfitting. To address these issues, we propose Coarse-to-Fine Instruction Alignment (CoFInAl). Inspired by recent advances in large language model tuning, CoFInAl aligns AQA with broader pre-trained tasks by reformulating it as a coarse-to-fine classification task. Initially, it learns grade prototypes for coarse assessment and then utilizes fixed sub-grade prototypes for fine-grained assessment. This hierarchical approach mirrors the judging process, enhancing interpretability within the AQA framework. Experimental results on two long-term AQA datasets demonstrate CoFInAl achieves state-of-the-art performance with significant correlation gains of 5.49% and 3.55% on Rhythmic Gymnastics and Fis-V, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model

Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via...

引用

International Conference on computer vision (ICCV)

作者： Yin Wang Zhiying Leng Frederick W. B. Li Shun-Cheng Wu Xiaohui Liang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Technical University of Munich Germany Department of Computer Science University of Durham U.K. Zhongguancun Laboratory Beijing China

Text-driven human motion generation in computer vision is both significant and challenging. However, current methods are limited to producing either deterministic or imprecise motion sequences, failing to effectively control the temporal and spatial relationships required to conform to a given text description. In this work, we propose a fine-grained method for generating high-quality, conditional human motion sequences supporting precise text description. Our approach consists of two key components: 1) a linguistics-structure assisted module that constructs accurate and complete language feature to fully utilize text information; and 2) a context-aware progressive reasoning module that learns neighborhood and overall semantic linguistics features from shallow and deep graph neural networks to achieve a multi-step inference. Experiments show that our approach outperforms text-driven motion generation methods on HumanML3D and KIT test sets and generates better visually confirmed motion to the text conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Class A Bézier curves with monotone curvature

引用

CAD computer Aided Design 2023年 159卷

作者： Wang, Aizeng He, Chuan Zheng, Jianmin Zhao, Gang School of Mechanical Engineering & Automation Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology & Systems Beihang University Beijing100191 China School of Computer Science and Engineering Nanyang Technological University Singapore

This paper introduces a special class of 3D Bézier curves that are defined by their degree, a starting point, the first leg of their control polygons, and a 3D affine transformation composing of a uniform scaling and a rotation. We present new formulas for the curvature of such Bézier curves and based on the new formulas we derive sufficient conditions for the curves to have monotonic curvature. The conditions are expressed by a simple constraint on the rotation angle and the scaling factor. This facilitates constructing 3D Class A Bézier curves that are a generalization of planar typical curves proposed by Mineur et al. (1998), which are often used in automotive and other design applications. Some examples are provided to demonstrate the effectiveness of our construction. © 2023 Elsevier Ltd

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

DG-CNN:Introducing Margin Information into Convolutional Neural Networks for Breast Cancer Diagnosis in Ultrasound Images

引用

Journal of computer Science & technology 2022年第2期37卷 277-294页

作者： Xiao-Zheng Xie Jian-Wei Niu Senior Member Xue-Feng Liu Qing-Feng Li Yong Wang Jie Han Shaojie Tang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityHangzhou 310051China Department of Diagnostic Ultrasound National Cancer CenterChinese Academy of Medical SciencesPeking Union Medical CollegeBeijing 100021China Naveen Jindal School of Management The University of Texas at DallasRichardsonTX 75080-3021U.S.A.

Although using convolutional neural networks(CNNs)for computer-aided diagnosis(CAD)has made tremendous progress in the last few years,the small medical datasets remain to be the major bottleneck in this *** address this problem,researchers start looking for information out of the medical *** efforts mainly leverage information from natural images via transfer *** recent research work focuses on integrating knowledge from medical practitioners,either letting networks resemble how practitioners are trained,how they view images,or using extra *** this paper,we propose a scheme named Domain Guided-CNN(DG-CNN)to incorporate the margin information,a feature described in the consensus for radiologists to diagnose cancer in breast ultrasound(BUS)*** DG-CNN,attention maps that highlight margin areas of tumors are first generated,and then incorporated via different approaches into the *** have tested the performance of DG-CNN on our own dataset(including 1485 ultrasound images)and on a public *** results show that DG-CNN can be applied to different network structures like VGG and ResNet to improve their *** example,experimental results on our dataset show that with a certain integrating mode,the improvement of using DG-CNN over a baseline network structure ResNet 18 is 2.17%in accuracy,1.69%in sensitivity,2.64%in specificity and 2.57%in AUC(Area Under Curve).To the best of our knowledge,this is the first time that the margin information is utilized to improve the performance of deep neural networks in diagnosing breast cancer in BUS images.

关键词： medical consensus domain knowledge breast cancer diagnosis margin map deep neural network

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Decouple Learning for Image Compression Artifacts Reduction

arXiv

引用

arXiv 2024年

作者： Ma, Li Zhao, Yifan Peng, Peixi Tian, Yonghong Huawei Technologies Company Ltd Shenzhen518129 China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China School of Electronics and Computer Engineering School of Computer Science Peking University Beijing100871 China PengCheng Laboratory Shenzhen518055 China

With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed image to the original one but ignore the intrinsic attributes of the given compressed images, which greatly harms the performance of downstream parsing tasks. Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, i.e., the compression-insensitive features to regularize the high-level semantic representations during training and the compressionsensitive features to be aware of the compression degree. To achieve this, we first employ adversarial training to regularize the compressed and original encoded features for retaining high-level semantics, and we then develop the compression quality-aware feature encoder for compression-sensitive features. Based on these dual complementary features, we propose a Dual Awareness Guidance Network (DAGN) to utilize these awareness features as transformation guidance during the decoding phase. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features by fusing compression-insensitive features into the artifacts reduction baseline. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods, and only requires 29.7 ms to process one image on BSD500. Besides, the experimental results on LIVE1 and LIU4K also demonstrate the efficiency, effectiveness, and superiority of the proposed method in terms of quantitative metrics, visual quality, and downstream machine vision tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

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

Why Go Full? Elevating Federated Learning Through Partial Network Updates

arXiv

引用

arXiv 2024年

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024, CC BY.

关键词： Federated learning

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：