检索结果-内蒙古大学图书馆

HC-GCN: hierarchical contrastive graph convolutional network for unsupervised domain adaptation on person re-identification

引用

MULTIMEDIA SYSTEMS 2023年第5期29卷 2779-2790页

作者： Chen, Si Xu, Bolun Zhang, Miaohui Yan, Yan Du, Xia Zhuang, Weiwei Wu, Yun Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understand Xiamen 361024 Peoples R China Jiangxi Acad Sci Inst Energy Res Nanchang 330096 Peoples R China Xiamen Univ Sch Informat Fujian Key Lab Sensing & Comp Smart City Xiamen 361005 Peoples R China

The unsupervised domain adaptation (UDA) task on person re-identification (ReID) aims at spotting a person of interest under cross-camera by transferring the person knowledge learned from a labeled source domain to an unlabeled target domain. Recently, the contrastive loss provides an effective approach for UDA person ReID by comparing global features of the pedestrians. Generally, the fine-grained local features are favorable to distinguish the pedestrian appearance changes. However, the traditional contrastive loss-based UDA methods ignore the importance of local details and the relationship between the different granularities of features. To overcome this problem, we propose a hierarchical contrastive graph convolutional network, termed HC-GCN, for UDA person ReID. We first build an effective hierarchical graph model to learn the relationship between the global and local pedestrian features, where the local features are obtained by rough split and affine transformation. Moreover, we introduce the contrastive loss to suppress the pedestrian-irrelevant features, where the global and local contrastive losses are used. Experiments demonstrate that our method can achieve superior performance on the challenging Market-1501 and MSMT17 datasets.

关键词： Person re-identification Unsupervised domain adaptation Graph convolutional network Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

MCKIE: Multi-class key Information Extraction from Complex Documents Based on Graph Convolutional Network 6th

MCKIE: Multi-class Key Information Extraction from Complex D...

引用

6th Chinese Conference on pattern recognition and Computer Vision (PRCV)

作者： Huang, Zhicai Xiao, Shunxin Wang, Da-Han Zhu, Shunzhi Xiamen Huaxia Univ Coll Informat & Smart Elect Engn Xiamen 361024 Peoples R China Xiamen Univ Technol Sch Comp & Informat Engn Xiamen 361024 Peoples R China Fujian Key Lab Pattern Recognit & Image Understan Xiamen 361024 Peoples R China

ISBN: (纸本)9789819985395;9789819985401

The majority of key information extraction in document analysis work relies on simple layout scenes with few classes, such as the date and amount on invoices or receipts. However, many document applications entail sophisticated layouts with various types of elements. The mortgage contract agreement, for example, often has over ninety entities, and it is expensive to design template for each document. To this end, we propose an efficient multi-class key information extraction (MCKIE) method based on graph convolutional network. In detail, we design a graph construction strategy to generate a text box graph. Then, MCKIE utilizes the message-passing mechanism to learn node representation by aggregating information from neighborhoods. Besides, we compare the performance of various graph construction methods and verify the effectiveness of MCKIE on the realistic contract document dataset. Extensive experimental results show that the proposed model significantly outperforms other baseline models.

关键词： key Information Extraction Complex Document image Graph Convolutional Network

来源：评论

学校读者我要写书评

暂无评论

HD-Net: A hybrid dynamic spatio-temporal network for traffic flow prediction

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2024年第4期18卷 672-690页

作者： Liu, Lijuan Wang, Fengzhi Liu, Hang Zhu, Shunzhi Wang, Yan Xiamen Univ Technol Coll Comp & Informat Engn Xiamen Peoples R China Fujian Key Lab Pattern Recognit & Image Understand Xiamen Peoples R China Xiamen Univ Technol Coll Comp & Informat Engn Xiamen 361024 Peoples R China

Accurately predicting traffic flow is crucial for intelligent transportation systems (ITS). In recent years, many deep learning-based prediction models have been widely applied in traffic flow prediction, and various spatio-temporal networks have been proposed. However, most of the existing models follow a general technical route to extract the spatio-temporal features, which lack the capacity of extracting the important historical information with the high spatial and temporal correlations dynamically and deeply. How to develop a well-performance traffic flow prediction model for a complex transportation network is still facing some challenges. In this paper, a hybrid dynamic spatio-temporal network (HD-Net) for traffic flow prediction is proposed. In HD-Net, the authors first extract the dynamic spatio-temporal features using dynamic graph convolution and bidirectional gate recurrent uni (BiGRU). Subsequently, the authors extract the important features with high spatial and temporal correlations from the obtained dynamic spatio-temporal features using an auto-correlation mechanism from a local perspective, and self-attention mechanism from a global perspective, respectively. Extensive experiments have been conducted on two real-world traffic datasets. The experimental results demonstrate that the proposed HD-Net outperforms the baselines in the field of capturing the dynamic and important spatio-temporal features with high correlations. In HD-Net, the authors first extract the dynamic spatio-temporal features using dynamic graph convolution and bidirectional gate recurrent unit (BiGRU). Then, the authors further extract the important features with high spatial and temporal correlation from the obtained dynamic spatio-temporal features using the auto-correlation mechanism from a local perspective, and self-attention mechanism from a global ***

关键词： management and control traffic modelling transport modelling and microsimulation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised remote sensing image thin cloud removal method based on contrastive learning

引用

IET image PROCESSING 2024年第7期18卷 1844-1861页

作者： Tan, Zhan Cong Du, Xiao Feng Man, Wang Xie, Xiao Zhu Wang, Gui Song Nie, Qin Xiamen Univ Technol Sch Comp & Informat Engn Xiamen 361024 Peoples R China Xiamen Univ Technol Inst Spatial Informat Technol Xiamen Peoples R China Fujian Key Lab Pattern Recognit & Image Understand Xiamen Peoples R China

Cloud removal algorithm is a crucial step of remote sensing image preprocessing. The current mainstream remote sensing image cloud removal algorithms are implemented based on deep learning, and most of them are supervised. A large number of data pairs are required for training to achieve cloud removal. However, real with/without cloud image pairs datasets are difficult to obtain in the real world, and the models obtained by training on synthetic datasets often need to generalize better to natural scenes. And the existing unsupervised thin cloud removal methods based on Cycle-GAN framework with considerable model complexity and unstable training are not an excellent solution to the problem of lack of paired datasets. Based on this, in this paper, the authors propose an unsupervised remote sensing image thin cloud removal method based on contrastive learning-GAN-UD. It is a network consisting of a frequency-spatial attention generator and a discriminator. In addition, the authors introduce local contrastive loss and global content loss to constrain the content of the generated images to ensure that the generated cloud-free images are consistent with the input cloud images in terms of image content. Experimental results show that the proposed method in this paper can still effectively remove thin clouds from remote sensing images without paired training datasets, outperforms current unsupervised cloud removal methods, and achieves comparable performance to supervised methods. The authors propose an unsupervised remote sensing image thin cloud removal method based on contrastive learning-Generative Adversarial Network of Unpair Data. It is a network consisting of a frequency-spatial attention generator and a discriminator. In addition, the authors introduce local contrastive loss and global content loss to constrain the content of the generated images to ensure that the generated cloud-free images are consistent with the input cloud images in terms of image content. ima

关键词： image reconstruction remote sensing unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Misclassification Information for Fine-Grained image Classification

引用

SENSORS 2021年第12期21卷 4176-4176页

作者： Wang, Da-Han Zhou, Wei Li, Jianmin Wu, Yun Zhu, Shunzhi Fujian Key Lab Pattern Recognit & Image Understan Xiamen 361024 Peoples R China Xiamen Univ Technol Sch Comp & Informat Engn Xiamen 361024 Peoples R China

Fine-grained image classification is a hot topic that has been widely studied recently. Many fine-grained image classification methods ignore misclassification information, which is important to improve classification accuracy. To make use of misclassification information, in this paper, we propose a novel fine-grained image classification method by exploring the misclassification information (FGMI) of prelearned models. For each class, we harvest the confusion information from several prelearned fine-grained image classification models. For one particular class, we select a number of classes which are likely to be misclassified with this class. The images of selected classes are then used to train classifiers. In this way, we can reduce the influence of irrelevant images to some extent. We use the misclassification information for all the classes by training a number of confusion classifiers. The outputs of these trained classifiers are combined to represent images and produce classifications. To evaluate the effectiveness of the proposed FGMI method, we conduct fine-grained classification experiments on several public image datasets. Experimental results prove the usefulness of the proposed method.

关键词： fine-grained image classification misclassification information confusion information object categorization

来源：评论

学校读者我要写书评

暂无评论

HASI: Hierarchical Attention-Aware Spatio-Temporal Interaction for Video-Based Person Re-Identification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第6期34卷 4973-4988页

作者： Chen, Si Da, Hui Wang, Da-Han Zhang, Xu-Yao Yan, Yan Zhu, Shunzhi Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understan Xiamen 361024 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Xiamen Univ Sch Informat Xiamen 361005 Peoples R China

Video-based person re-identification (re-ID) aims to match the same pedestrian of video sequences across non-overlapping cameras. Video re-ID methods generally adopt frame-level feature extraction for different video frames, but they still lack effective spatio-temporal interaction, easily leading to the multi-frame misalignment problem. In this paper, we propose a Hierarchical Attention-aware Spatio-temporal Interaction (HASI) network, including an Attention-aware Temporal Interaction (ATI) module and a Hierarchical Local-spatial Enhancement (HLE) module for video-based person re-ID. In order to avoid the spatial misalignment between video frames, the ATI module employs multiple Frame-to-Frame Temporal Interaction (2FTI) blocks with the Multi-head Inter-frame Alignment Attention (MIAA) to make the current frame iteratively interact with each rest frame of a video in a positive single-cycle manner, rather than only interacting with the adjacent frame or directly building the relationship of all frames at once. This module can not only obtain the long-range non-adjacent temporal information, but also learn the pairwise frame-to-frame relationships. Moreover, the HLE module is designed to enhance the local fine-grained features from multiple Transformer layers, whilst delivering low-level information to further enrich middle-level and high-level semantic knowledge. Thus, our method can learn multi-perspective pedestrian information, including inter-frame long-range interaction information and intra-frame multi-layer global and local information. Extensive experiments demonstrate the superiority of the proposed HASI method compared with the state-of-the-art methods on the three challenging video-based re-ID datasets, i.e., MARS, iLIDS-VID, and PRID-2011.

关键词： Video-based person re-identification vision transformer spatio-temporal interaction deep feature fusion

来源：评论

学校读者我要写书评

暂无评论

2D License Plate recognition based on Automatic Perspective Rectification 25

2D License Plate Recognition based on Automatic Perspective ...

引用

25th International Conference on pattern recognition (ICPR)

作者： Xu, Hui Guo, Zhao-Hong Wang, Da-Han Zhou, Xiang-Dong Shi, Yu Chinese Acad Sci Chongqing Inst Green & Intelligent Technol Beijing Peoples R China Univ Chinese Acad Sci Chongqing Sch Beijing Peoples R China Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understan Xiamen Peoples R China

ISBN: (纸本)9781728188089

License plate recognition (LPR) remains a challenging task in face of some difficulties such as image deformation and multi-line character distribution. Text rectification that is crucial to eliminate the effects of image deformation has attracted increasing attentions in scene text recognition. However, current text rectification methods are not designed specifically for LPR, which did not take the features of plate deformation into account. Considering the fact that a license plate (LP) can only generate perspective distortion in the image due to its rigid feature, in this paper we propose a novel perspective rectification network (PRN) to automatically estimate the perspective transformation and rectify the distorted LP accordingly. For recognition, we propose a location-aware 2D attention based recognition network that is capable of recognizing both single-line and double-line plates with perspective deformation. The rectification network and recognition network are connected for end-to-end training. Experiments on common datasets show that the proposed method achieves the state-of-the-art performance, demonstrating the effectiveness of the proposed approach.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Manifold Learning With Applications to Supervised Classification for High-Resolution Remotely Sensed images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2014年第3期52卷 1677-1692页

作者： Huang, Hong-Bing Huo, Hong Fang, Tao Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Dept Automat Shanghai 200240 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China Fujian Agr & Forestry Univ Fuzhou 350002 Peoples R China

Manifold learning is one of the representative nonlinear dimensionality reduction techniques and has had many successful applications in the fields of information processing, especially pattern classification, and computer vision. However, when it is used for supervised classification, in particular for hierarchical classification, the result is still unsatisfactory. To address this issue, a novel supervised approach, namely hierarchical manifold learning (HML) is proposed. HML takes into account both the between-class label information and the within-class local structural information of the training sets simultaneously to guide the dimension reduction process for classification purpose. In this process, we extract sharing features to represent the parent manifold's information, and better solve the out-of-sample problem of manifold learning by using the generalized regression neural network at considerably lower computational cost, thereby making the proposed HML more suitable for supervised classification. Experimental results demonstrate the feasibility and effectiveness of our proposed algorithm.

关键词： Dimensionality reduction generalized regression neural network hierarchical manifold learning (HML) imagery classification sharing features submanifold

来源：评论

学校读者我要写书评

暂无评论

MSCNet: A Multilevel Stacked Context Network for Oriented Object Detection in Optical Remote Sensing images

引用

REMOTE SENSING 2022年第20期14卷 5066-5066页

作者： Zhang, Rui Zhang, Xinxin Zheng, Yuchao Wang, Dahan Hua, Lizhong Xiamen Univ Technol Coll Comp & Informat Engn Xiamen 361024 Peoples R China Xiamen Univ Technol Fujian Key Lab Pattern Recognit & Image Understan Xiamen 361024 Peoples R China

Oriented object detection has recently become a hot research topic in remote sensing because it provides a better spatial expression of oriented target objects. Although research has made considerable progress in this field, the feature of multiscale and arbitrary directions still poses great challenges for oriented object detection tasks. In this paper, a multilevel stacked context network (MSCNet) is proposed to enhance target detection accuracy by aggregating the semantic relationships between different objects and contexts in remote sensing images. Additionally, to alleviate the impact of the defects of the traditional oriented bounding box representation, the feasibility of using a Gaussian distribution instead of the traditional representation is discussed in this paper. Finally, we verified the performance of our work on two common remote sensing datasets, and the results show that our proposed network improved on the baseline.

关键词： oriented object detection multilevel stacked context remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial networks with decoder-encoder output noises

引用

NEURAL NETWORKS 2020年 127卷 19-28页

作者： Zhong, Guoqiang Gao, Wei Liu, Yongbin Yang, Youzhao Wang, Han Huang, Kaizhu Ocean Univ China Dept Comp Sci & Technol Qingdao 266100 Peoples R China Fudan Univ Dept Comp Sci & Technol Shanghai 200433 Peoples R China Xiamen Univ Technol Fujian Key Lab Pattern Recognit & Image Understan Xiamen 361024 Peoples R China Xian Jiaotong Liverpool Univ Dept Elect & Elect Engn Suzhou 215123 Peoples R China Alibaba Zhejiang Univ Joint Inst Frontier Technol Hangzhou Peoples R China

In recent years, research on image generation has been developing very fast. The generative adversarial network (GAN) emerges as a promising framework, which uses adversarial training to improve the generative ability of its generator. However, since GAN and most of its variants use randomly sampled noises as the input of their generators, they have to learn a mapping function from a whole random distribution to the image manifold. As the structures of the random distribution and the image manifold are generally different, this results in GAN and its variants difficult to train and converge. In this paper, we propose a novel deep model called generative adversarial networks with decoder-encoder output noises (DE-GANs), which take advantage of both the adversarial training and the variational Bayesian inference to improve GAN and its variants on image generation performances. DE-GANs use a pre-trained decoder-encoder architecture to map the random noise vectors to informative ones and feed them to the generator of the adversarial networks. Since the decoder-encoder architecture is trained with the same data set as the generator, its output vectors, as the inputs of the generator, could carry the intrinsic distribution information of the training images, which greatly improves the learnability of the generator and the quality of the generated images. Extensive experiments demonstrate the effectiveness of the proposed model, DE-GANs. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： image generation Generative models Generative adversarial networks Variational autoencoders Noise

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：