检索结果-内蒙古大学图书馆

Multi-Branch Enhanced Discriminative Network for Vehicle Re-Identification

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第2期25卷 1263-1274页

作者： Lian, Jiawei Wang, Da-Han Wu, Yun Zhu, Shunzhi Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understand Xiamen 361024 Peoples R China

Vehicle re-identification (ReID) is the task of identifying the same vehicle across numerous cameras. This is a complex classification task, and the fine-grained information and strong discrimination features have proven to be effective in handling the re-identification classification task. However, most existing methods focuses on extracting local area features in combination with global features, while exploring subtle distinguishing features, which is a difficult task, remains an open problem and unsolved. In this paper, we propose a multi-branch enhanced discriminative network (MED) to better extract subtle distinguishing features that have high discriminative power to improve the ReID performance. In the proposed MED method, each feature map obtained by convolutional neural network (CNN) is divided into 4 spatial sub-maps, on each of which, the vertical and the horizontal branches are used to extract the subtle distinguishing features intrinsically contained in sub-areas. The vertical and the horizontal branches are combined with the global branch to perform the ReID task. Moreover, our proposed method is capable of extracting rich fine-grained features without the need of extra manual annotation while maintaining a simple design structure. We conducted extensive experiments on the vehicle ReID datasets (VehicleID and VeRi-776), showing that the proposed MED method outperforms most existing methods. Further, we directly apply the MED method to the pedestrian ReID problem on the Market-1501, DUKEMTMC, and MSMT17 datasets, achieving the state-of-the-art (SOTA) performance as well. This demonstrates that the proposed method has good generality and can be flexibly applied to the ReID tasks.

关键词： Feature extraction Task analysis Data mining Pedestrians Annotations Manuals Vehicle dynamics Vehicle re-identification multi-branch deep learning intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Vehicle Re-Identification by Separating Representative Spatial Features

引用

COGNITIVE COMPUTATION 2023年第5期15卷 1640-1655页

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

As a complex image classification problem, re-identification (ReID) requires the model to capture diverse representative features of vehicles through different spatial orientation cameras. However, it has been observed that the existing models tend to focus on extracting features with strong discrimination, while ignoring other valuable spatial features. In addition, the existing methods lack effective suppression of noise caused by spatial variations. Inspired by the observation from the human cognition that, the view and direction of the vehicle can be correctly recognized by human beings with only partial representative spatial features observed, in this paper, we propose a novel method to effectively separate representative spatial (SRS) information and non-spatial region discriminative information of vehicles. First, we specifically use an effective network to extract the vehicle keypoint information (e.g., roof and left wheel), and capture the representative local spatial region via the keypoint information. Then, we use the representative spatial features in the local spatial region and the distinguishing discriminative features in the non-spatial region to eliminate the interference arising from the spatial shift while enhancing the robustness of the model. Finally, the global discriminative information and representative spatial information are combined for vehicle re-identification to enhance the performance of the model. We validate the effectiveness of our proposed approach on the vehicle ReID datasets (VehicleID, VeRi-776 and VeRi-Wild). Experimental results show that our method achieves state-of-the-art performance.

关键词： Vehicle re-identification Representative spatial features Spatial significance Deep learning

来源：评论

学校读者我要写书评

暂无评论

CCNN-former: Combining convolutional neural network and Transformer for image-based traffic time series prediction

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 268卷

作者： Liu, Lijuan Wu, Mingxiao Lv, Qinzhi Liu, Hang Wang, Yan Xiamen Univ Technol Sch Comp & Informat Engn Xiamen 361024 Peoples R China Fujian Key Lab Pattern Recognit & Image Understand Xiamen 361024 Peoples R China

Traffic time series prediction is crucial to the development of urban intelligent transportation systems (ITS). Traditional prediction models are mainly designed to extract the spatio-temporal features based on historical traffic flow in the form of time series, ignoring the learning of the implicit periodic patterns hidden in the flow. In addition, most of the models solely employ the historical traffic flow with no more than 12 time steps for prediction. Such short-term input struggles to contain rich, continuous and diverse periodic patterns, limiting their performance. To this end, we propose a model of combining convolutional neural network (CNN) and Transformer (CCNN-Former) tailored for image-based traffic time series prediction. Specifically, we first propose a data conversion module that converts the long-term time series traffic flow into a new representation of image with fixed resolution, ensuring that both short- and long-term information is contained in an image. Then, CNN and Transformer are utilized to learn the image-based features from local and global perspectives, respectively. The core of CCNN-Former is to creatively propose a new long-term time series data imaging strategy and use a computer vision method to extract rich short- and long-term image-based features, achieving the goal of improving prediction performance while maintaining high efficiency. Extensive experiments are conducted on two real-world datasets to demonstrate the superiority of CCNN-Former compared with seven competitive baselines.

关键词： Traffic prediction Time series Imaging Periodic pattern Transformer

来源：评论

学校读者我要写书评

暂无评论

Multimodal urban traffic flow prediction based on multi-scale time series imaging

引用

pattern recognitION 2025年 164卷

作者： Lv, Qinzhi Liu, Lijuan Yang, Ruotong Wang, Yan Xiamen Univ Technol Sch Comp & Informat Engn Xiamen 361024 Peoples R China Fujian Key Lab Pattern Recognit & Image Understand Xiamen 361024 Peoples R China

Accurate traffic flow prediction is of great significance for administrators and travelers to make informed decisions in advance. Since the increasing correlation between predicted flow and historical flow from more recent periods, most existing traffic flow prediction models generally learn spatial-temporal patterns from historical single-scale time series data with time steps not exceeding 12. However, such short-term flow does not contain continuous and dynamic long-term spatial-temporal patterns. Thus, how to comprehensively learn the diverse patterns and achieve a satisfactory balance between effectiveness and efficiency presents a challenge. To this end, we propose a multimodal urban traffic flow prediction model based on multi-scale time series imaging (MM-TSI). Specifically, a data processing mechanism of multi-scale time series imaging is specially designed to efficiently learn both short- and long-term spatial-temporal patterns. After that, an image- based module is proposed to be parallelly integrated into a traditional time series-based module. By adaptively fusing the two-modal features extracted from image-based module and time series-based module, MM-TSI is capable of effectively learning more comprehensive and diverse spatial-temporal patterns while maintaining efficiency to a certain extent. Extensive experiments are conducted on three real-world urban traffic flow datasets. The results demonstrate that the proposed MM-TSI significantly outperforms the state-of-the-art (SOTA) models and exhibits generalization ability in both short- and long-term prediction.

关键词： Urban traffic flow prediction Multimodal learning Time series Imaging Multi-scale modeling

来源：评论

学校读者我要写书评

暂无评论

Global-local graph attention: unifying global and local attention for node classification

引用

COMPUTER JOURNAL 2024年第10期67卷 2959-2969页

作者： Lin, Keao Xie, Xiaozhu Weng, Wei Du, Xiaofeng Xiamen Univ Technol Coll Comp & Informat Engn Xiamen 361024 Peoples R China Fujian Key Lab Pattern Recognit & Image Understand Xiamen 361024 Peoples R China

Graph Neural Networks (GNNs) are deep learning models specifically designed for analyzing graph-structured data, capturing complex relationships and structures to improve analysis and prediction. A common task in GNNs is node classification, where each node in the graph is assigned a predefined category. The Graph Attention Network (GAT) is a popular variant of GNNs known for its ability to capture complex dependencies by assigning importance weights to nodes during information aggregation. However, the GAT's reliance on local attention mechanisms limits its effectiveness in capturing global information and long-range dependencies. To address this limitation, we propose a new attention mechanism called Global-Local Graph Attention (GLGA). Our mechanism enables the GAT to capture long-range dependencies and global graph structures while maintaining its ability to focus on local interactions. We evaluate our algorithm on three citation datasets (Cora, Citeseer, and Pubmed) using multiple metrics, demonstrating its superiority over other baseline models. The proposed GLGA mechanism has been proven to be an effective solution for improving node classification tasks.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Distillation-Based Utility Assessment for Compacted Underwater Information

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 481-485页

作者： Liao, Honggang Jiang, Nanfeng Chen, Weiling Wei, Hongan Zhao, Tiesong Fuzhou Univ Fujian Key Lab Intelligent Proc & Wireless Transmi Fuzhou 350108 Peoples R China Xiamen Univ Technol Fujian Key Lab Pattern Recognit & Image Understand Xiamen 361024 Peoples R China Fujian Sci & Technol Innovat Lab Optoelect Informa Fuzhou 350116 Peoples R China

The limited bandwidth of underwater acoustic channels poses a challenge to the efficiency of multimedia information transmission. To improve efficiency, the system aims to transmit less data while maintaining image utility at the receiving end. Although assessing utility within compressed information is essential, the current methods exhibit limitations in addressing utility-driven quality assessment. Therefore, this letter built a Utility-oriented compacted image Quality Dataset (UCIQD) that contains utility qualities of reference images and their corresponding compcated information at different levels. The utility score is derived from the average confidence of various object detection models. Then, based on UCIQD, we introduce a Distillation-based Compacted Information Quality assessment metric (DCIQ) for utility-oriented quality evaluation in the context of underwater machine vision. In DCIQ, utility features of compacted information are acquired through transfer learning and mapped using a Transformer. Besides, we propose a utility-oriented cross-model feature fusion mechanism to address different detection algorithm preferences. After that, a utility-oriented feature quality measure assesses compacted feature utility. Finally, we utilize distillation to compress the model by reducing its parameters by 55%. Experiment results effectively demonstrate that our proposed DCIQ can predict utility-oriented quality within compressed underwater information.

关键词： Compacted underwater information utility-oriented quality assessment distillation

来源：评论

学校读者我要写书评

暂无评论

SiamCCF: Siamese visual tracking via cross-layer calibration fusion

引用

IET COMPUTER VISION 2023年第8期17卷 869-882页

作者： Chen, Si Huang, Huang Zhu, Shunzhi Xu, Huarong He, Yifan Wang, Da-Han Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understand Xiamen Peoples R China Reconova Technol Co Ltd Xiamen Peoples R China

Siamese networks have attracted wide attention in visual tracking due to their competitive accuracy and speed. However, the existing Siamese trackers usually leverage a fixed linear aggregation of feature maps, which does not effectively fuse the different layers of features with attention. Besides, most of Siamese trackers calculate the similarity between the template and the search region through a cross-correlation operation between the features of the last blocks from the two branches, which might introduce the redundant noise information. In order to solve these problems, this study proposes a novel Siamese visual tracking method via cross-layer calibration fusion, termed SiamCCF. An attention-based feature fusion module is employed using local attention and non-local attention to fuse the features from the deep and shallow layers, so as to capture both local details and high-level semantic information. Moreover, a cross-layer calibration module can use the fused features to calibrate the features of the last network blocks and build the cross-layer long-range spatial and inter-channel dependencies around each spatial location. Extensive experiments demonstrate that the proposed method has achieved competitive tracking performance compared with state-of-the-art trackers on challenging benchmarks, including OTB100, OTB2013, UAV123, UAV20L, and LaSOT.

关键词： computer vision object tracking

来源：评论

学校读者我要写书评

暂无评论

Identity-Aware Contrastive Knowledge Distillation for Facial Attribute recognition

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第10期33卷 5692-5706页

作者： Chen, Si Zhu, Xueyan Yan, Yan Zhu, Shunzhi Li, Shao-Zi Wang, Da-Han Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understand Xiamen 361024 Peoples R China Xiamen Univ Sch Informat Xiamen 361005 Peoples R China

Facial attribute recognition (FAR) is an important and yet challenging multi-label learning task in computer vision. Existing FAR methods have achieved promising performance with the development of deep learning. However, they usually suffer from prohibitive computational and memory costs. In this paper, we propose an identity-aware contrastive knowledge distillation method, termed ICKD, to compress the FAR model. A nonlinear weight-sharing mapping (NWSM) mechanism is firstly designed to avoid the difficulty of directly matching features of the teacher and student networks due to the lower representation ability of the student network. Furthermore, an identity-aware contrastive distillation (ICD) loss is employed to guide the student network to effectively learn the mutual relations between samples with multiple attributes. In addition, an adjustable ladder distillation (ALD) loss is developed to automatically adjust the importance of different distillation points with the progress of training. Extensive experiments demonstrate that our method can significantly improve the performance of student networks and outperforms the existing FAR methods on the public challenging datasets.

关键词： Facial attribute recognition knowledge distillation contrastive learning contrastive knowledge distillation adjustable ladder distillation loss

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

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：