检索结果-内蒙古大学图书馆

20th International conference on Information Security and Cryptology, Inscrypt 2024

ISBN: (纸本)9789819647309

The proceedings contain 23 papers. The special focus in this conference is on Information Security and Cryptology. The topics include: TA-DPDP: Dynamic Provable data Possession for Online Collaborative System with Tractable Anonymous;on the Relationship Between Public Key Primitives via Indifferentiability;lattice-Based Succinct Mercurial Functional Commitment for Boolean Circuits: Definitions, and Constructions;from Signature with Re-randomizable Keys: Generic Construction of PDPKS;SIMD Optimizations of White-Box Block Cipher Implementations with the Self-equivalence Framework;when Is Multi-channel Better Than Single-Channel: A Case Study of Product-Based Multi-channel Fusion Attacks;privacy-Preserving Certificate-Less Authenticated Key Exchange with Key Registration Privacy;An Improved Signal Leakage Attack Against DXL Key Exchange Protocol;srCPace: Universally Composable PAKE with Subversion-Resilience;Analyzing Decentralized Applications Traffic: A Multimodal Approach Based on GNN and BERT;EditPSM: A New Password Strength Meter Based on Password Reuse via Deep Learning;a Binary Code Similarity Detection Method Based on Multi-source Contrastive Learning;malware Detection Method Based on image Sample reconstruction and Feature Enhancement;attention-Based Decompilation Through Neural Machine Translation;DBridger: Discovering Vulnerable data Sharing Paths in Embedded Firmware;efficient Privacy-Preserving data Sharing Mechanisms Against Malicious Senders in Smart Grid;NEST: Strong Key-Insulated Password-Based Shared-Custodial Blockchain Wallets;clustering Coefficient Estimating of Distributed Graph data Based on Shuffled Differential Privacy;Public-Key Watermarkable PRFs with Dynamic Bounded Collusion;a Lossless Relational data Watermarking Scheme Based on Uneven Partitioning;CNNOVZKP: Convolutional Neural Network Model Ownership Verification with Zero-Knowledge Proof.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Phase Retrieval from Quantized and Noisy Measurements

Robust Phase Retrieval from Quantized and Noisy Measurements

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International conference on

作者： Yihong Gao Luteng Zhu Zhuoyang An Mingjie Shao Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong SAR China School of Information Science and Engineering Shandong University Qingdao China Computer School Beijing Information Science and Technology University Beijing China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331519315

ISBN: (纸本)9798331519322

The phase retrieval (PR) problem involves recovering a signal from amplitude-only measurements and has been extensively studied in various physical measurement and signal processing systems. Recently, there has been increasing interest in the quantized phase retrieval (QPR) problem, where the observed amplitude is quantized to binary values. The existing studies have focused on the noiseless case. In this paper, we address a robust QPR problem that accounts for both quantization and noise. We formulate the robust QPR problem using maximum-likelihood estimation (MLE), which results in a non-convex and challenging optimization problem due to the complexity of its likelihood function. To obtain a high-quality solution, we develop an expectation-maximization (EM) algorithm combined with the Wirtinger flow, allowing us to convert the problem into a more manageable form at each iteration. Our method is implemented on both randomly generated synthetic data and image reconstruction tasks. The results demonstrate that our approach significantly enhances signal recovery performance under the combined effects of quantization and noise. Additionally, the proposed method exhibits better runtime efficiency compared to existing approaches.

关键词： Maximum likelihood estimation Phase measurement Quantization (signal) Runtime Noise Signal processing algorithms Noise measurement Speech processing Optimization Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Dynamic Point Cloud Geometric Compression Based on Bidirectional Recurrent Scene Flow*

Multi-modal Dynamic Point Cloud Geometric Compression Based ...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Fangzhe Nan Frederick Li Zhuoyue Wang Gary K.L. Tam Zhaoyi Jiang DongZheng DongZheng Bailin Yang School of Statistics and Mathematics Zhejiang Gongshang University School of Computer Science and Technolgy Zhejiang Gongshang University University of Durham University of California Berkeley Swansea University Universal Ubiquitous Technology Co. LTD

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Deep learning methods have recently shown significant promise in compressing the geometric features of point clouds. However, challenges arise when consecutive point clouds contain holes, resulting in incomplete information that complicates motion estimation. To our knowledge, most existing dynamic point cloud compression methods have largely overlooked this critical issue. Moreover, these methods typically employ a multi-scale single-pass approach for motion estimation, performing only one estimation at each scale. This limits accuracy and adversely impacts compression performance. To address these challenges, we propose a dynamic point cloud compression model called M2BR-DPCC (Multi-Modal Multi-Scale Bidirectional Recursion for Dynamic Point Cloud Compression). Our method introduces two key innovations. First, we integrate both point cloud and image data as inputs, leveraging a multi-modal feature representation completion (MFRepC) approach to align information across modalities. This addresses the issue of missing data in point clouds by using complementary information from images. Second, we implement a multi-scale bidirectional recursive (MSBR) motion estimation method. This module iteratively refines motion flows in both forward and backward directions, progressively enhancing point cloud features and improving motion estimation accuracy. Experimental results on widely used datasets, including MVUB and 8iVFB, demonstrate the effectiveness of our approach. Compared to existing methods, M2BR-DPCC achieves superior performance, with an average BD-rate improvement of 95.23% over V-PCC, 12.92% over D-DPCC, and 16.16% over patchDPCC. These results underscore the potential of leveraging multi-modal data and bidirectional refinement for dynamic point cloud compression.

关键词： Point cloud compression Technological innovation image coding Accuracy Limiting Motion estimation Dynamics Estimation Filling Speech processing

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Arbitrary Super-Resolution Considering Consistency and Realness

Few-Shot Arbitrary Super-Resolution Considering Consistency ...

引用

International conference on Electronics, Information and Communications (ICEIC)

作者： Joonhee Lee Junseo Bang Se Young Chun Department of Electrical and Computer Engineering INMC & IPAI Seoul National University Seoul Republic of Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

Super-resolution (SR) is the task of reconstructing visually natural high-resolution (HR) images from low-resolution (LR) images. This field has made significant advancements with the development of deep learning, and recent research has focused on arbitrary-scale super-resolution, where a single model performs upsampling across continuous scales. However, most existing studies on arbitrary-scale super-resolution have relied on supervised learning models, which require large amounts of data and annotations. We propose a novel approach that demonstrates performance equal to or better than existing methods while utilizing fewer data, thus opening up new possibilities in this domain. This method also presents the potential for personalization, allowing the model to be adjusted according to individual user preferences or requirements. Specifically, we propose a method that integrates a few-shot arbitrary super-resolution upsampler trained with limited data into a zero-shot learning framework for super-resolution based on existing Diffusion Posterior Sampling (DPS) techniques. Additionally, this approach addresses the issues of insufficient detail representation in traditional regression-based SR methods and the lack of fidelity to the original images observed in generative-based SR methods. To achieve this, we employ a parallel diffusion model that uses DPS in both spatial and Fourier domains to simultaneously generate two types of images while maintaining consistency and realness. As a result, our method achieves performance in both PSNR and LPIPS that is competitive with supervised learning-based regression and generative SR methods.

关键词： Visualization Annotations Superresolution Zero shot learning Supervised learning Diffusion models data models Spatial resolution Few shot learning image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Novel Self-Supervised Contrastive Learning Framework for Masked EEG Motor imagery Modeling

A Novel Self-Supervised Contrastive Learning Framework for M...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kunkun Zhang Qianwei Zhou Haigen Hu College of Computer Science and Technology Zhejiang University of Technology Hangzhou PR China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Electroencephalography (EEG) is vital for brain-computer interfaces (BCIs) due to its non-invasive approach and high temporal resolution data capabilities, amid challenges such as data scarcity and the need for extensive labeling. Significant inter-individual variability in EEG signals further limits model generalization. Concurrently, the use of self-supervised pre-training, particularly through masked modeling, is gaining traction in time series analysis to mitigate labeling costs. Although this method involves reconstructing masked signal from unmasked series, random masking can disrupt critical temporal variations, complicating effective representation learning. We thus introduce SSL-MEMI, a novel self-supervised contrastive learning framework for masked EEG motor imagery modeling, integrating Domain Adaptive Alignment (DAA) and Multi-View Temporal-spatial Attention module (MTSA) to effectively handle EEG variability. This framework utilizes manifold-based masking to reconstruct original sequences from masked series, thereby enhancing classification accuracy. When tested on the BCI Competition IV and High Gamma datasets, SSL-MEMI outperforms existing methods, achieving top accuracies and demonstrating superior domain adaptation through reduced Global ${\mathcal{A}}$-distance scores. This study advances EEG classification and indicates broader applications for self-supervised learning in biomedical signal processing. The source code is available at https://***/KunKun-Zhang/***.

关键词： Manifolds Adaptation models Accuracy Time series analysis Contrastive learning Brain modeling Motors Electroencephalography Labeling image reconstruction

来源：评论

学校读者我要写书评

暂无评论

BioNet and NeFF: Crop Biomass Prediction from Point Clouds to Drone imagery

BioNet and NeFF: Crop Biomass Prediction from Point Clouds t...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Xuesong Li Zeeshan Hayder Ali Zia Connor Cassidy Shiming Liu Warwick Stiller Eric Stone Warren Conaty Lars Petersson Vivien Rolland CSIRO Agriculture and Food Australian National University CSIRO Data61 Australia

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Crop biomass offers crucial insights into plant health and yield, making it essential for crop science, farming systems, and agricultural research. However, current measurement methods, which are labor-intensive, destructive, and imprecise, hinder large-scale quantification of this trait. To address this limitation, we present a biomass prediction network (BioNet), designed for adaptation across different data modalities, including point clouds and drone imagery. Our BioNet, utilizing a sparse 3D convolutional neural network (CNN) and a transformer-based prediction module, processes point clouds and other 3D data representations to predict biomass. To further extend BioNet for drone imagery, we integrate a neural feature field (NeFF) module, enabling 3D structure reconstruction and the transformation of 2D semantic features from vision foundation models into the corresponding 3D surfaces. For the point cloud modality, BioNet demonstrates superior performance on two public datasets, with an approximate 6.1% relative improvement (RI) over the state-of-the-art. In the RGB image modality, the combination of BioNet and NeFF achieves a 7.9% RI. Additionally, the NeFF-based approach utilizes inexpensive, portable drone-mounted cameras, providing a scalable solution for large field applications.

关键词： Point cloud compression Three-dimensional displays Accuracy Crops Transformers Biomass Convolutional neural networks Surface treatment Biomedical imaging Drones

来源：评论

学校读者我要写书评

暂无评论

Toward Visual Pronunciation Learning: A Speech-to-Articulatory Animation Pipeline Leveraging wav2vec 2.0 and rtMRI Landmarks

Toward Visual Pronunciation Learning: A Speech-to-Articulato...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mushaffa Rasyid Ridha Shinobu Hasegawa Sakriani Sakti Grad. School of Adv. Science & Tech. Japan Adv. Inst. of Science & Tech. Nomi Japan Center of IDER Japan Adv. Inst. of Science & Tech. Nomi Japan Grad. School of Science & Tech. Nara Inst. of Science & Tech. Ikoma Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Most computer-assisted pronunciation training (CAPT) systems for second language (L2) learners focus on detecting mispronunciation based on predefined phonemes and assigning pronunciation scores. However, these systems often lack visual feedback or detailed corrective guidance, limiting learners’ opportunities for significant improvement. This paper presents a key advance toward developing a CAPT system that offers detailed visual feedback on articulatory movements using real-time magnetic resonance imaging (rtMRI) articulatory landmarks. The limited availability of paired speech and articulatory landmark data, typically involving only a few speakers, poses a challenge for generalizing across diverse speech patterns. To address this, we propose leveraging pretrained wav2vec 2.0 embeddings, fine-tuned to generate articulatory contours mapped to xy coordinates based on rtMRI landmark data. As evaluated with the rtMRI USC-TIMIT dataset, our system effectively reconstructs visual articulatory movements from speech, marking a significant step toward enhanced visual pronunciation learning.

关键词： Training Visualization Limiting Magnetic resonance imaging Pipelines Neural networks Speech enhancement Feature extraction Real-time systems image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Compressive sensing-based inverse synthetic radar imaging imaging from incomplete data

引用

IET RADAR SONAR AND NAVIGATION 2016年第2期10卷 386-397页

作者： Tomei, Sonia Bacci, Alessio Giusti, Elisa Martorella, Marco Berizzi, Fabrizio Univ Pisa Dept Informat Engn Pisa Italy CNIT Radar & Surveillance Syst RaSS Pisa Italy

The applicability of compressive sensing (CS) to radar imaging has been recently proven and its capability to construct reliable radar images from a limited set of measurements demonstrated. In this study, a common framework for inverse synthetic aperture radar (ISAR) imaging via CS is provided and a CS-based ISAR imaging method is proposed. The proposed method is tested for application such as image reconstruction from compressed data, resolution enhancement and image reconstruction from gapped data. The effectiveness of the proposed method is demonstrated on real datasets and the performance evaluated by means of image contrast.

关键词： synthetic aperture radar radar imaging image reconstruction compressed sensing image enhancement image resolution compressive sensing-based inverse synthetic radar imaging imaging CS-based ISAR imaging method incomplete data image reconstruction compressed data resolution enhancement gapped data image contrast performance evaluation

来源：评论

学校读者我要写书评

暂无评论

MAXIMUM-ENTROPY image-reconstruction from PHASELESS FOURIER data

引用

OPTICA ACTA 1986年第3期33卷 287-299页

作者： BRYAN, RK SKILLING, J DEPT APPL MATH & THEORET PHYS CAMBRIDGEENGLAND

The application of the maximum entropy method of image processing to the problem of reconstructing an image from the intensities of its Fourier transform is discussed. We present modifications required for this application to a numerical algorithm previously used for linear reconstruction problems. Two examples of its use with incomplete and noisy data are given.

关键词： image PROCESSING

来源：评论

学校读者我要写书评

暂无评论

MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications

MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estima...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Gasser Elazab Torben Gräber Michael Unterreiner Olaf Hellwich CARIAD SE Technische Universität Berlin

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Self-supervised monocular depth estimation (MDE) has gained popularity for obtaining depth predictions directly from videos. However, these methods often produce scaleinvariant results, unless additional training signals are provided. Addressing this challenge, we introduce a novel selfsupervised metric-scaled MDE model that requires only monocular video data and the camera's mounting position, both of which are readily available in modern vehicles. Our approach leverages planar-parallax geometry to reconstruct scene structure. The full pipeline consists of three main networks, a multi-frame network, a singleframe network, and a pose network. The multi-frame network processes sequential frames to estimate the structure of the static scene using planar-parallax geometry and the camera mounting position. Based on this reconstruction, it acts as a teacher, distilling knowledge such as scale information, masked drivable area, metric-scale depth for the static scene, and dynamic object mask to the singleframe network. It also aids the pose network in predicting a metric-scaled relative pose between two subsequent images. Our method achieved state-of-the-art results for the driving benchmark KITTI for metric-scaled depth prediction. Notably, it is one of the first methods to produce self-supervised metric-scaled depth prediction for the challenging Cityscapes dataset, demonstrating its effectiveness and versatility. Project page: https://***/

关键词： Geometry Training Computer vision Depth measurement Automotive applications Cameras Vehicle dynamics image reconstruction Videos Visual perception

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：