检索结果-南通市图书馆

Double-branch fusion network with a parallel attention selection mechanism for camouflaged object detection

Science China(Information Sciences) 2023年第6期66卷 258-266页

作者： Junjiang XIANG Qing PAN Zhengrong ZHANG Songnian FU Yuwen QIN Advanced Institute of Photonics Technology School of Information EngineeringGuangdong University of Technology Guangdong Provincial Key Laboratory of Photonics Information Technology Guangdong University of Technology Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronics and InformationGuangxi University

To meet the challenge of camouflaged object detection (COD),which has a high degree of intrinsic similarity between the object and background,this paper proposes a double-branch fusion network(DBFN)with a parallel attention selection mechanism (PASM).In detail,a schismatic receptive field block(SRF)combined with an attention mechanism for low-level information is performed to learn texture features in one branch,and an integration of the SRF,a hybrid attention mechanism (HAM),and a depth feature polymerization module (DFPM)is employed for high-level information to extract detection features in the other branch.Then,both texture features and detection features are input into the PASM to acquire selective expression matrices.Eventually,the final result is obtained after further selective matrix optimization with atrous spatial pyramid pooling (ASPP)and a residual channel attention block (RCAB)being applied serially.Experimental results on three public datasets verify that our method outperforms the state-of-the-art methods in terms of four evaluation metrics,i.e.,mean absolute error (MAE),weighted F βmeasure (Fβω),structural measure (Sα),and E-measure (Eφ)

关键词： camouflaged object detection attention mechanism feature extraction feature aggregation texture information fuzzy boundary

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Adequate alignment and interaction for cross-modal retrieval

引用

Virtual Reality & Intelligent Hardware 2023年第6期5卷 509-522页

作者： Mingkang WANG Min MENG Jigang LIU Jigang WU School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510006China Ping An Life Insurance of China Shenzhen 518033China

Background Cross-modal retrieval has attracted widespread attention in many cross-media similarity search applications,particularly image-text retrieval in the fields of computer vision and natural language processing.Recently,visual and semantic embedding(VSE)learning has shown promising improvements in image text retrieval tasks.Most existing VSE models employ two unrelated encoders to extract features and then use complex methods to contextualize and aggregate these features into holistic embeddings.Despite recent advances,existing approaches still suffer from two limitations:(1)without considering intermediate interactions and adequate alignment between different modalities,these models cannot guarantee the discriminative ability of representations;and(2)existing feature aggregators are susceptible to certain noisy regions,which may lead to unreasonable pooling coefficients and affect the quality of the final aggregated features.Methods To address these challenges,we propose a novel cross-modal retrieval model containing a well-designed alignment module and a novel multimodal fusion encoder that aims to learn the adequate alignment and interaction of aggregated features to effectively bridge the modality gap.Results Experiments on the Microsoft COCO and Flickr30k datasets demonstrated the superiority of our model over state-of-the-art methods.

关键词： Cross-modal retrieval Visual semantic embedding feature aggregation Transformer

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

Deeper Attention-Based Network for Structured Data

引用

国际计算机前沿大会会议论文集 2020年第1期 259-267页

作者： Xiaohua Wu Youping Fan Wanwan Peng Hong Pang Yu Luo School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China

Deep learning methods are applied into structured data and in typical methods,low-order features are discarded after combining with high-order featuresfor prediction tasks.However,in structured data,ignorance of low-order features may cause the low prediction rate.To address this issue,in this paper,deeper attention-based network(DAN)is proposed.With DAN method,to keep both low-and high-order features,attention average pooling layer was utilized to aggregate features of each order.Furthermore,by shortcut connections from each layer to attention average pooling layer,DAN can be built extremely deep to obtain enough capacity.Experimental results show DAN has good performance and works effectively.

关键词： Structured data DeepLearning feature aggregation

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

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

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

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：