检索结果-南通市图书馆

Augmented Deep Multi-Granularity Pose-Aware feature Fusion Network for Visible-Infrared Person Re-Identification

Computers, Materials & Continua 2023年第12期77卷 3467-3488页

作者： Zheng Shi Wanru Song Junhao Shan Feng Liu School of Educational Science and Technology Nanjing University of Posts and TelecommunicationsNanjing210013China

Visible-infrared Cross-modality Person Re-identification(VI-ReID)is a critical technology in smart public facilities such as cities,campuses and *** aims to match pedestrians in visible light and infrared images for video surveillance,which poses a challenge in exploring cross-modal shared information accurately and ***,multi-granularity feature learning methods have been applied in VI-ReID to extract potential multi-granularity semantic information related to pedestrian body structure ***,existing research mainly uses traditional dual-stream fusion networks and overlooks the core of cross-modal learning networks,the fusion *** paper introduces a novel network called the Augmented Deep Multi-Granularity Pose-Aware feature Fusion Network(ADMPFF-Net),incorporating the Multi-Granularity Pose-Aware feature Fusion(MPFF)module to generate discriminative *** efficiently explores and learns global and local features with multi-level semantic information by inserting disentangling and duplicating blocks into the fusion module of the backbone ***-Net also provides a new perspective for designing multi-granularity learning *** incorporating the multi-granularity feature disentanglement(mGFD)and posture information segmentation(pIS)strategies,it extracts more representative features concerning body structure *** Local Information Enhancement(LIE)module augments high-performance features in VI-ReID,and the multi-granularity joint loss supervises model training for objective feature *** results on two public datasets show that ADMPFF-Net efficiently constructs pedestrian feature representations and enhances the accuracy of VI-ReID.

关键词： Visible-infrared person re-identification multi-granularity feature learning modality

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Texture image classification with discriminative neural networks

引用

Computational Visual Media 2016年第4期2卷 367-377页

作者： Yang Song Qing Li Dagan Feng Ju Jia Zou Weidong Cai School of Information Technologies the University of Sydney School of Computing Engineering and MathematicsWestern Sydney University

Texture provides an important cue for many computer vision applications, and texture image classification has been an active research area over the past years. Recently, deep learning techniques using convolutional neural networks(CNN) have emerged as the state-of-the-art: CNN-based features provide a significant performance improvement over previous handcrafted features. In this study, we demonstrate that we can further improve the discriminative power of CNN-based features and achieve more accurate classification of texture images. In particular, we have designed a discriminative neural network-based feature transformation(NFT) method, with which the CNN-based features are transformed to lower dimensionality descriptors based on an ensemble of neural networks optimized for the classification objective. For evaluation, we used three standard benchmark datasets(KTH-TIPS2, FMD, and DTD)for texture image classification. Our experimental results show enhanced classification performance over the state-of-the-art.

关键词： texture classification neural networks feature learning feature transformation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

learning Noise-Assisted Robust Image features for Fine-Grained Image Retrieval

引用

Computer Systems Science & Engineering 2023年第9期46卷 2711-2724页

作者： Vidit Kumar Hemant Petwal Ajay Krishan Gairola Pareshwar Prasad Barmola Department of Computer Science and Engineering Graphic Era Deemed to be UniversityDehradun248002India School of Computer Science Engineering and Technology Bennett UniversityGreater Noida201310Uttar PradeshIndia

Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query *** key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding *** works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,***,training via these approaches takes a long training time,and they have poor ***,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen *** paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these *** the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class *** other instances are treated as negatives within the same *** a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded *** proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.

关键词： Convolutional network zero-shot learning fine-grained image retrieval image representation image retrieval intra-class diversity feature learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Structural Sparse Representation for Object Detection

引用

Wuhan University Journal of Natural Sciences 2017年第4期22卷 318-322页

作者： FANG Wenhua CHEN Jun HU Ruimin National Engineering Research Center for Multimedia Software Wuhan UniversityWuhan 430072HubeiChina

Classic sparse representation, as one of prevalent feature learning methods, is successfully applied for different computer vision tasks. However it has some intrinsic defects in object detection. Firstly, how to learn a discriminative dictionary for object detection is a hard problem. Secondly, it is usually very time-consuming to learn dictionary based features in a traditional exhaustive search manner like sliding window. In this paper, we propose a novel feature learning framework for object detection with the structure sparsity constraint and classification error minimization constraint to learn a discriminative dictionary. For improving the efficiency, we just learn sparse representation coefficients from object candidate regions and feed them to a kernelized SVM classifier. Experiments on INRIA Person Dataset and Pascal VOC 2007 challenge dataset clearly demonstrate the effectiveness of the proposed approach compared with two state-of-the-art baselines.

关键词： feature learning structural sparse coding SVM object detection

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Proposal of Equivalent Porosity Indicator for Foam Aluminum Based on GRNN

引用

Journal of Harbin Institute of Technology(New Series) 2024年第5期31卷 16-31页

作者： Wenhao Da Lucai Wang Yanli Wang Xiaohong You Wenzhan Huang Fang Wang School of Material Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China

To gain a more comprehensive understanding and evaluate foam aluminum's performance,researchers have introduced various characterization ***,the current understanding of the significance of these indicators in analyzing foam aluminum's performance is *** study employs the Generalized Regression Neural Network(GRNN)method to establish a model that links foam aluminum's microstructure characterization data with its mechanical *** the GRNN model,researchers extracted four of the most crucial features and their corresponding weight values from the 13 pore characteristics of foam ***,a new characterization formula,called“Wang equivalent porosity”(WEP),was developed by using residual weights assigned to the feature weights,and four parameter coefficients were *** formula aims to represent the relationship between foam aluminum's microstructural features and its mechanical ***,the researchers conducted model verification using compression data from 11 sets of foam *** validation results showed that among these 11 foam aluminum datasets,the Gibson-Ashby formula yielded anomalous results in two cases,whereas WEP exhibited exceptional stability without any *** comparison to the Gibson-Ashby formula,WEP demonstrated an 18.18%improvement in evaluation accuracy.

关键词： aluminum foam characterization index importance analysis feature learning

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A saliency and Gaussian net model for retinal vessel segmentation

引用

Frontiers of Information Technology & Electronic Engineering 2019年第8期20卷 1075-1087页

作者： Lan-yan XUE Jia-wen LIN Xin-rong CAO Shao-hua ZHENG Lun YU College of Physics and Information Engineering Fuzhou UniversityFuzhou350108China Institute of Computer and Information Fujian Agriculture and Forestry UniversityFuzhou350002China

Retinal vessel segmentation is a significant problem in the analysis of fundus images.A novel deep learning structure called the Gaussian net(GNET)model combined with a saliency model is proposed for retinal vessel segmentation.A saliency image is used as the input of the GNET model replacing the original *** GNET model adopts a bilaterally symmetrical *** the left structure,the first layer is upsampling and the other layers are *** the right structure,the final layer is max-pooling and the other layers are *** proposed approach is evaluated using the DRIVE *** results indicate that the GNET model can obtain more precise features and subtle details than the UNET *** proposed algorithm performs well in extracting vessel networks,and is more accurate than other deep learning *** vessel segmentation can help extract vessel change characteristics and provide a basis for screening the cerebrovascular diseases.

关键词： Retinal vessel segmentation Saliency model Gaussian net(GNET) feature learning

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Novel Person Re-ID Method based on Multi-Scale feature Fusion

A Novel Person Re-ID Method based on Multi-Scale Feature Fus...

引用

第三十九届中国控制会议

作者： Yuanyuan Li Xiaofei Wang Zhiqin Zhu Xinghua Huang Penghua Li Guanqiu Qi Yujun Rong Chongqing University of Posts and Telecommunications Key Laboratory of Complex System Safety and Control Ministry of EducationChongqing University Computer Information Systems Department Buffalo State College China Mobile (Hangzhou) Information Technology Co. Ltd.

Person re-identification（Re-ID） is a challenging but significant research topic. Previous methods based on global features are not pay much attention to the fine-grained feature information. While the methods based on local features strictly rely on the accurate pedestrian detection bounding-boxes to align the image pairs. In this paper, the Multi-Scale feature Fusion Network is proposed which can extract global and local features simultaneously and to learn jointly. The network structure consists of two branches. One is a global branch for global feature learning, in this branch, we extract the whole body feature information of human body to express the pedestrian image as a whole. The other is a local branch for local feature learning. In the local branch, according to the characteristics of pedestrian’s human structure, we segment the image into 6 horizontal strips to bring the local feature representation of the pedestrian image. In addition, we use a novel integration of multiple loss functions to further improve the recognition accuracy of the network. Experiments on Market-1501 and DukeMTMC-reID datasets show that our proposed method can achieve state-of-the-art results.

关键词： Person re-identification Multi-scale feature fusion feature learning Multiple loss functions

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Research of Human Visual Perception Mechanisms for Object Tracking

Research of Human Visual Perception Mechanisms for Object Tr...

引用

第13届中国系统仿真技术及其应用学术年会

作者：赵宇宙陈宗海 Department of Automation University of Science and Technology of China

The theories and models of human visual perception are aim to understand and emulate the intelligent properties of human vision system,and have important reference value to traditional computer vision research. In this paper,based on mechanisms of visual attention,we discuss the problem of object tracking in the perspective of visual attention. A framework of attention based tracking strategy is proposed and implemented,and the advantages and lacks are discussed after experiments. We hope to provide a reference for the further research of biologically motivated object tracking.

关键词： visual perception visual attention mechanism object tracking feature selection feature learning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Deep Boltzmann Machines based Vehicle Recognition

Deep Boltzmann Machines based Vehicle Recognition

引用

第26届中国控制与决策会议

作者： Aiqin HU Hong LI Fan ZHANG Wei ZHANG School of Information Science and Engineering Central South University School Of Architecture Hunan University

We address the problem of image-based vehicle *** problem is formulated as a manifold-feature learning algorithm such that the expected object distribution is evaluated based on the appearance,shape and contours that take into account variational poses and *** propose to learn manifold hierarchical features where the high-level discriminative features are obtained by capturing correlations among the learned low-level generic features,via a deep learning model,called Deep Boltzmann Machines（DBM）,a powerful hierarchical generative model for feature *** has been proved to be able to explore underlying manifold knowledge of given objects by appropriately describing highly nonlinear complicated functions with novel training ***,we also present a novel application of deep learning to feature representations,rather than provide the model input with raw image pixels,we instead utilize the human-engineered descriptors such as Log-Gabor,HoG and Gist,as the source data of deep learning ***,we evaluate our deep model on PASCAL VOC2012 benchmark dataset,extensive experiments show that our DBM-based model enables to learn useful hierarchical feature representations from few training ***,by feeding the DBM-based deep network with prior-described features such as Log-Gabor,HoG and Gist,we get a significant improvement on performance in comparison with the state-of-art results and the best performance is achieved by using a fusion form of the three descriptors as source material for learning deep ***,experiments with prior-extracted features as input layer demonstrate that the deep learning networks have provided a perspective of potential ability to learn critical representation of given data,and have presented favorable vehicle recognition performance.

关键词： Vehicle Recognition Deep Boltzmann Machines feature learning VOC 2012 Dataset

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：