检索结果-内蒙古大学图书馆

Frequency enhanced vector quantized variational autoencoder for structural vibration response compression

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2025年 224卷

作者： Xue, Zhilin An, Yonghui Ou, Jinping Dalian Univ Technol Dept Civil Engn Dalian 116023 Peoples R China State Key Lab Featured Met Mat & Life Cycle Safety Nanning 530004 Guangxi Peoples R China

The structural health monitoring system has been widely installed on large civil structures, generating a significant amount of structural vibration response data over their long-term service life, which poses challenges for data transmission and storage. The compression method for structural vibration responses based on the traditional deep autoencoder (AE) can only compress the original data into low-dimensional floating-point features and not into low-dimensional integer features, which limits its compression capability. To address this issue, this paper proposes a frequency enhanced vector quantized variational autoencoder (FEVQVAE) method for compressing structural vibration responses with higher compression ratios. The proposed method has three key innovations. Firstly, the proposed time-domain and frequency-domain dual-branch block enhances the feature extraction capability of both the encoder and decoder, to some extent mitigating the challenge for neural networks to extract high-frequency features. Secondly, the proposed frequency block separates the extraction of features for a single resonant band and multiple resonant bands, enabling the encoder and decoder to more effectively extract frequencydomain features of the vibration responses. Thirdly, by introducing sensor position encoding, compression of multiple sensor data can be achieved with only one model. The effectiveness of the proposed method is validated using acceleration responses from a Dowling Hall Footbridge under normal operating conditions and a long-span suspension bridge subjected to non-stationary excitations such as wind and vehicle loads. Experimental results demonstrate that the compression performance of the proposed FEVQVAE method is significantly improved compared to the AE method and the vector quantized variational autoencoder method. Modal parameter identification results of the original and reconstructed responses show excellent consistency at a compression ratio of 19.2, with a

关键词： Vibration response compression Deep learning Structural health monitoring vector quantized variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Quaternion vector quantized variational autoencoder

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 151-155页

作者： Luo, Hui Liu, Xin Sun, Jian Zhang, Yang Macau Univ Sci & Technol Fac Innovat Engn Macau 999078 Peoples R China Univ Manitoba Dept Math Winnipeg MB R3T 2N2 Canada

vector quantized variational autoencoders, as variants of variational autoencoders, effectively capture discrete representations by quantizing continuous latent spaces and are widely used in generative tasks. However, these models still face limitations in handling complex image reconstruction, particularly in preserving high-quality details. Moreover, quaternion neural networks have shown unique advantages in handling multi-dimensional data, indicating that integrating quaternion approaches could potentially improve the performance of these autoencoders. To this end, we propose QVQ-VAE, a lightweight network in the quaternion domain that introduces a quaternion-based quantization layer and training strategy to improve reconstruction precision. By fully leveraging quaternion operations, QVQ-VAE reduces the number of model parameters, thereby lowering computational resource demands. Extensive evaluations on face and general object reconstruction tasks show that QVQ-VAE consistently outperforms existing methods while using significantly fewer parameters.

关键词： Quaternions vectors Image reconstruction Convolution Neural networks Face recognition Quantization (signal) Decoding Training Indexes quaternion generative models quaternion neural networks vector quantized variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Attention-based vector quantized variational autoencoder for anomaly detection constraints

引用

PATTERN RECOGNITION 2025年 164卷

作者： Yu, Qien Dai, Shengxin Dong, Ran Ikuno, Soichiro Chongqing Jiaotong Univ Sch Informat Sci & Engn Chongqing 400074 Peoples R China Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Chukyo Univ Sch Engn Toyota Aichi 4700393 Japan Tokyo Univ Technol Sch Comp Sci Hachioji Tokyo 1920982 Japan

This paper introduces a new framework that uses a vector quantized variational autoencoder (VQVAE) enhanced by orthogonal subspace constraints (OSC) and pyramid criss-cross attention (PCCA). The framework was designed for anomaly detection in industrial product image datasets. Previous studies on modeling low- dimensional feature distributions have been unable to effectively distinguish between normal features and noisy/abnormal information, which is effectively addressed using OSC in this study. Then, the vector quantized mechanism is embodied in these two complementary subspaces to obtain normal and abnormal embedding subspaces and discrete representations for normal and noisy information, respectively. The proposed approach robustly represents low-dimensional discrete manifolds to present the information from normal data using a limited number of feature vectors. Additionally, two PCCA modules are proposed to capture feature maps from different layers in the encoder and decoder, benefitting the low-dimensional mapping and reconstruction process. The features of different layers are treated as the query (Q), key (K), and value (V), which could capture both low-level and high-level features, incorporating comprehensive contextual information. The effectiveness of the proposed framework for anomaly detection is assessed by comparing its performance with those of the state-of-the-art approaches on various publicly available industrial product image datasets.

关键词： Industrial image Anomaly detection Subspace projection Attention mechanism vector quantized variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Predictive vector quantized variational autoencoder for Spectral Envelope Quantization

Predictive Vector Quantized Variational AutoEncoder for Spec...

引用

19th International Conference on Electronics, Information, and Communication (ICEIC)

作者： Srikotr, Tanasan Mano, Kazunori Shibaura Inst Technol Grad Sch Engn & Sci Div Funct Control Syst Tokyo Japan

ISBN: (纸本)9781728162898

The Predictive vector quantized variational autoencoder is proposed to improve the reconstruction error of the conventional VQ-VAE. The proposed model can predict the current data from the previous data. The performance of the quantized spectral envelope parameters of the high-quality 48 kHz WORLD vocoder is evaluated. The results indicate that the Predictive vector quantized variational autoencoder has a lower distortion with four target bitrates in term of log-spectral distortion, compared with the conventional VQ-VAE.

关键词： predictive vector quantization spectral envelope vector quantized variational autoencoder WORLD vocoder

来源：评论

学校读者我要写书评

暂无评论

Sub-band vector quantized variational autoencoder for Spectral Envelope Quantization

Sub-band Vector Quantized Variational AutoEncoder for Spectr...

引用

IEEE Region 10 Conference on Technology, Knowledge, and Society (TENCON)

作者： Srikotr, Tanasan Mano, Kazunori Shibaura Inst Technol Div Funt Control Syst Tokyo Japan

ISBN: (纸本)9781728118956

Recently, a lot of deep learning model successful in taking over conventional methods in speech processing fields. vector quantization is a popular technique to reduce the amount of speech data before transmitting. The conventional vector quantization method is based on the mathematical model. Last few years, the vector quantized variational autoencoder has been proposed for an end-to-end vector quantization based on deep learning techniques. In this paper, we investigate the sub-band quantization in the vector quantized variational autoencoder. This model can concentrate on specific frequency bands to assign more bits and leave the unnecessary band with few bits. Experimental results show the efficiency of the proposed quantization method for the spectral envelope parameters of the high-quality vocoder that operates at 48 kHz sampling frequency named WORLD vocoder. At the same four target bit rates, the sub-band vector quantized variational autoencoder can reduce the Log Spectral Distortion around 0.93 dB in average.

关键词： vector quantization autoencoder vector quantized variational autoencoder sub-band coding

来源：评论

学校读者我要写书评

暂无评论

Stochastic human motion prediction using a quantized conditional diffusion model

引用

KNOWLEDGE-BASED SYSTEMS 2025年 309卷

作者： Huang, Biaozhang Li, Xinde Hu, Chuanfei Li, Heqing Southeast Univ Sch Automat Key Lab Measurement & Control CSE Minist Educ Nanjing 210096 Peoples R China Nanjing Ctr Appl Math Nanjing 211135 Peoples R China Southeast Univ Shenzhen Res Inst Shenzhen 518063 Peoples R China

Human motion prediction is a fundamental task in computer vision, aiming to forecast future human poses based on observed motion sequences. Existing deterministic methods generate a single future motion sequence, neglecting the inherent stochasticity and diversity of human behaviors. To address this limitation, we propose a novel two-stage stochastic human motion prediction framework, termed the quantized Conditional Diffusion Model (QCDM), which combines a Discrete Motion Quantization Module and a Conditional Motion Generation Module. Specifically, we first design a discrete motion quantization module that leverages Graph Convolutional Networks (GCNs) and one-dimensional temporal convolutions to encode motion sequences into continuous latent representations. These representations are then quantized into discrete latent variables using a learnable codebook. A decoder reconstructs the motion sequence from these discrete variables, preserving key motion patterns while eliminating redundancies. Next, we develop a conditional motion generation module that integrates GCNs and Transformers for denoising spatio-temporal features. The diffusion process iteratively refines noisy motion data by reversing a gradual noising procedure, modeling the distribution of plausible future motions. Action category information and observed historical motion segments are incorporated as conditions into the denoising process, enabling controllable generation of specific motions. Additionally, we introduce a diversity enhancement strategy by penalizing overly similar samples. This encourages the model to explore a wider range of plausible motions and thereby improving the diversity and richness of the prediction results. Extensive experiments demonstrate that the QCDM framework outperforms state-of-the-art methods in stochastic human motion prediction tasks, offering both accuracy and diversity in generated motion sequences.

关键词： Human motion prediction vector quantized variational autoencoder Conditional diffusion model

来源：评论

学校读者我要写书评

暂无评论

MQVAE: Capturing Metastable Dynamics from EEG for Brain-computer Interfaces

MQVAE: Capturing Metastable Dynamics from EEG for Brain-comp...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： He, Yihang Ye, Chenfei Cai, Guoqing Liao, Jiahui Ma, Ting Shenzhen China Shenzhen China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798350368741

Research on neural dynamics indicates that cognitive processes are driven by metastable state transitions in the brain, which highlights the temporally discontinuous nature of brain activity. However, many existing methods fail to account for this discontinuity, limiting their effectiveness in modeling the brain's temporal dynamics. To address this, we propose the Metastability quantized variational autoencoder (MQVAE), a neurologically inspired neural network designed to capture metastable dynamics from electroencephalography (EEG) for brain-computer interface (BCI). In MQVAE, EEG signals are quantized into a time series of discrete latent variables using vector quantization. This quantization facilitates the identification of metastable states and the construction of a latent state space. To model state transition patterns, we incorporate a transformer module to capture global temporal dependencies among the discrete latent variables. Furthermore, a multi-scale spatial convolution layer is embedded within the encoder to extract hierarchical spatial patterns. Experiments on two public datasets demonstrate that MQVAE outperforms state-of-the-art methods in both emotion recognition and motor imagery classification tasks. Interpretability analyses further confirm that the features learned by MQVAE are neurophysiologically meaningful. © 2025 IEEE.

关键词： deep learning electroencephalography Metastable vector quantized variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Latent space improved masked reconstruction model for human skeleton-based action recognition (vol 19, 1482281, 2025)

引用

FRONTIERS IN NEUROROBOTICS 2025年 19卷 1482281页

作者： Chen, E. Wang, X. Guo, X. Zhu, Y. Li, D. School of Electrical and Information Engineering Zhengzhou University Zhengzhou China. State Grid Henan Electric Power Company Information and Communication Branch Zhengzhou China.

Human skeleton-based action recognition is an important task in the field of computer vision. In recent years, masked autoencoder (MAE) has been used in various fields due to its powerful self supervised learning ability and has achieved good results in masked data reconstruction tasks. However, in visual classification tasks such as action recognition, the limited ability of the encoder to learn features in the autoencoder structure results in poor classification performance. We propose to enhance the encoder's feature extraction ability in classification tasks by leveraging the latent space of variational autoencoder (VAE) and further replace it with the latent space of vector quantized variational autoencoder (VQVAE). The constructed models are called SkeletonMVAE and SkeletonMVQVAE, respectively. In SkeletonMVAE, we constrain the latent variables to represent features in the form of distributions. And in SkeletonMVQVAE, we discretize the latent variables. These help the encoder learn deeper data structures and more discriminative and generalized feature representations. The experiment results on the NTU-60 and NTU-120 datasets demonstrate that our proposed method can effectively improve the classification accuracy of the encoder in classification tasks and its generalization ability in the case of few labeled data. SkeletonMVAE exhibits stronger classification ability, while SkeletonMVQVAE exhibits stronger generalization in situations with fewer labeled data.

关键词： human skeleton-based action recognition variational autoencoder vector quantized variational autoencoder masked reconstruction model self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Cross Attention Transformers for Multi-modal Unsupervised Whole-Body PET Anomaly Detection 2nd

Cross Attention Transformers for Multi-modal Unsupervised Wh...

引用

2nd MICCAI Workshop on Deep Generative Models for Medical Image Computing and Computer Assisted Intervention (DGM4MICCAI)

作者： Patel, Ashay Tudosiu, Petru-Daniel Pinaya, Walter Hugo Lopez Cook, Gary Goh, Vicky Ourselin, Sebastien Cardoso, M. Jorge Kings Coll London London WC2R 2LS England

ISBN: (纸本)9783031185755;9783031185762

Cancers can have highly heterogeneous uptake patterns best visualised in positron emission tomography. These patterns are essential to detect, diagnose, stage and predict the evolution of cancer. Due to this heterogeneity, a general-purpose cancer detection model can be built using unsupervised learning anomaly detection models;these models learn a healthy representation of tissue and detect cancer by predicting deviations from healthy appearances. This task alone requires models capable of accurately learning long-range interactions between organs, imaging patterns, and other abstract features with high levels of expressivity. Such characteristics are suitably satisfied by transformers, and have been shown to generate state-of-the-art results in unsupervised anomaly detection by training on healthy data. This work expands upon such approaches by introducing multi-modal conditioning of the transformer via cross-attention, i.e. supplying anatomical reference information from paired CT images to aid the PET anomaly detection task. Using 83 whole-body PET/CT samples containing various cancer types, we show that our anomaly detection method is robust and capable of achieving accurate cancer localisation results even in cases where healthy training data is unavailable. Furthermore, the proposed model uncertainty, in conjunction with a kernel density estimation approach, is shown to provide a statistically robust alternative to residual-based anomaly maps. Overall, a superior performance is demonstrated against leading alternatives, drawing attention to the potential of these approaches.

关键词： Transformers Unsupervised anomaly detection Cross-attention Multi-modal vector quantized variational autoencoder Whole-body Kernel density estimation

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Anomaly Detection from Anomalous Training Data via Iterative Latent Token Masking

Self-Supervised Anomaly Detection from Anomalous Training Da...

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Patel, Ashay Tudosiu, Petru-Daniel Pinaya, Walter H. L. Graham, Mark S. Adeleke, Olusola Cook, Gary Goh, Vicky Ourselin, Sebastien Cardoso, M. Jorge Kings Coll London London England

ISBN: (纸本)9798350307443

Anomaly detection and segmentation pose an important task across sectors ranging from medical imaging analysis to industry quality control. However, current unsupervised approaches require training data to not contain any anomalies, a requirement that can be especially challenging in many medical imaging scenarios. In this paper, we propose Iterative Latent Token Masking, a self-supervised framework derived from a robust statistics point of view, translating an iterative model fitting with M-estimators to the task of anomaly detection. In doing so, this allows the training of unsupervised methods on datasets heavily contaminated with anomalous images. Our method stems from prior work on using Transformers, combined with a vector quantized-variational autoencoder, for anomaly detection, a method with state-of-the-art performance when trained on normal (non-anomalous) data. More importantly, we utilise the token masking capabilities of Transformers to filter out suspected anomalous tokens from each sample's sequence in the training set in an iterative self-supervised process, thus overcoming the difficulties of highly anomalous training data. Our work also highlights shortfalls in current state-of-the-art self-supervised, self-trained and unsupervised models when faced with small proportions of anomalous training data. We evaluate our method on whole-body PET data in addition to showing its wider application in more common computer vision tasks such as the industrial MVTec Dataset. Using varying levels of anomalous training data, our method showcases a superior performance over several state-of-the-art models, drawing attention to the potential of this approach. [GRAPHICS] .

关键词： Kernel Density Estimation Robust Statistics Self Supervised Anomaly Detection Token Masking Transformers vector quantized variational autoencoder

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：