检索结果-内蒙古大学图书馆

Hierarchical semantic compactness and proxy sparsity learning with event inversion for event person re-identification

引用

Journal of Electronic Imaging 2025年第2期34卷

作者： Chen, Wanzhang Kong, Jun Jiang, Min Tao, Xuefeng Jiangnan University Ministry of Education Key Laboratory of Advanced Process Control for Light Industry Wuxi China Jiangnan University Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi China

Event-based person re-identification (Event ReId) is an emerging research field that aims to distinguish individuals in non-overlapping event camera domains. Existing works achieve considerable performance by perceiving single-level semantic similarities. However, these methods often overlook multilevel semantic similarities and differences, leading to semantic non-compactness and proxy non-sparsity within the embedding space. Moreover, the implicit fine-grained information hidden in event representations is not effectively explored. To address these issues, we propose hierarchical semantic compactness and proxy sparsity learning with event inversion for event-based person re-identification. First, the hierarchical semantic compactness learning module is proposed to perceive semantic similarities at multi-level. Specifically, this module explores the semantic relationships between instances and global proxies through the application of proxy-level semantic awareness and instance-level semantic awareness losses. Second, the local proxy sparsity learning module is proposed to ensure the sparsity of local proxies, thereby exploring the semantic differences among local proxies. Third, we incorporate an event inversion model to further exploit fine-grained texture information from events. Finally, the excellent experiment result, with an improvement of 16.8% in mAP and 11.3% in Rank 1 accuracy on the Event-ReId dataset, highlighting the superiority of our model. © 2025 SPIE and IS&T.

关键词： event inverse model event-based person re-identification proxy sparsity semantic compactness

来源：评论

学校读者我要写书评

暂无评论

Dual-Path Interactive U-Net for Unsupervised Hyperspectral Image Super-Resolution

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11751-11766页

作者： Deng, Wenchen Liu, Jianjun Yang, Jinlong Wu, Zebin Xiao, Liang Jiangnan University Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Wuxi214122 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

Combining low-spatial-resolution hyperspectral image (LrHSI) with high-spatial-resolution multispectral image (HrMSI) serves as an effective strategy for enhancing the spatial fidelity of LrHSI. Nevertheless, most existing methods still face challenges in effectively leveraging the complementary information between the two distinct modalities and maintaining internal consistency, leading to suboptimal fusion results. Previous studies have demonstrated that U-shaped networks can capture spatial structural features within images. Inspired by this, we propose a dual-path interactive U-Net architecture to preserve spatial and spectral integrity. Specifically, we use a standard U-Net and a reversed U-Net as the backbone to extract image information and generate abundance maps of the input images. By enabling interaction between the encoders and decoders of both U-Nets, our architecture integrates information across different scales and modes, leading to enhanced fusion results. To further improve the feature extraction capability, we construct a multimode decomposition and reconstruction module, which adaptively fuses the features of LrHSI and HrMSI. This module extracts and combines correlations between the images through canonical polyadic decomposition and attention mechanism, capturing global features across different modes. In addition, we design a weight-sharing U-Net that leverages the similarities and differences between two abundance maps, ensuring internal consistency while reducing computational cost. Thorough evaluations conducted using four publicly available datasets, along with one real-world dataset, and under various noise conditions confirm the validity of our proposed model. © 2008-2012 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

sigRGCN: A Robust Residual Graph Convolutional Network for scRNA-Seq Data Clustering

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第1期22卷 271-284页

作者： Zhenqiu Shu Min Xia Kaiwen Tan Zhengtao Yu Xiao-Jun Wu Faculty of Information Engineering and Automation Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China

Clustering is a crucial step in single-cell RNA sequencing (scRNA-seq) data analysis, facilitating the discovery of new cell types and the grouping of similar cells. Recently, graph convolutional networks (GCNs) have gained prominence in scRNA-seq data clustering because they effectively learn cell representations by capturing the relationship between cells. However, GCNs are sensitive to noise in scRNA-seq data and are prone to over-smoothing, resulting in the loss of cell-specific information. To overcome these challenges, we propose sigRGCN, a robust residual graph convolutional network for scRNA-seq data clustering. Specifically, we first construct a disturbed cell graph by injecting noise into a cell graph constructed from scRNA-seq data. Then, we design a graph structure optimization graph convolutional network to eliminate the impact of noise in the disturbed cell graph. It significantly improves the robustness of the proposed model in real scRNA-seq data clustering tasks. After that, we utilize a $L$ -layers residual graph convolutional network to alleviate the over-smoothing problem. It allows our model to effectively capture higher-order relationships between cells, leading to better cell representations. Finally, we employ a self-supervised manner to optimize our model. The experimental results on nine real scRNA-seq datasets show that our proposed model demonstrates competitive performance in real clustering tasks.

关键词： Noise Data models Convolution Optimization Correlation Autoencoders RNA Graph convolutional networks Sequential analysis Noise reduction

来源：评论

学校读者我要写书评

暂无评论

EACNet:Ensemble adversarial co-training neural network for handling missing modalities in MRI images for brain tumor segmentation

引用

Journal of Measurement Science and Instrumentation 2025年第1期16卷 11-25页

作者： RAMADHAN Amran Juma CHEN Jing PENG Junlan School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computing Intelligence Jiangnan UniversityWuxi 214122China

Brain tumor segmentation is critical in clinical diagnosis and treatment *** methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical *** methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality ***,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training *** work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing *** proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”***-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing *** model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation *** was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance ***,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing *** analysis suggests that the ensemble appr

关键词： deep learning magnetic resonance imaging(MRI) medical image analysis semantic segmentation segmentation accuracy image synthesis

来源：评论

学校读者我要写书评

暂无评论

Structural Topology Refinement Network for Skeleton-Based Action recognition

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Wang, Rui Jin, Jiayao Chen, Ziheng Wu, Cong Wu, Xiao-Jun Sebe, Nicu Jiangnan University School of Artificial Intelligence and Computer Science Wuxi214122 China University of Trento Department of Information Engineering and Computer Science Trento38123 Italy Jiangnan University Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence China

The effectiveness of Graph Convolutional Networks (GCNs) has been widely demonstrated in skeleton-based action recognition. However, most existing GCN-based methods use a dense adjacency matrix to describe the structural information of the entire skeleton, i.e., a holistic representation, which neglects the discriminability of local patterns. To address this challenge, we propose a novel region descriptor by dividing the skeleton into different local sections (i.e., left arm, right arm, left leg, right leg, torso, and head). The generated representations contain rich semantic information, enabling the model to better understand the action correlation between different body parts. Inspired by the success of manifold learning in nonlinear data characterization, the Symmetric Positive Definite (SPD) matrix and Riemannian neural network are further introduced to capture the long-range statistical relationships among different topographies. These components form our Structural Topology Refinement Network (STRN). Extensive experiments on three benchmark datasets, namely NTU-60, NTU-120, and NW-UCLA, show the superiority of our proposed method over the state-of-the-art. © 1963-2012 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Multisource and Hidden Source-Based Knowledge Transfer for Solving Dynamic Multiobjective Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Song, Wei Liu, Zhi Yu, Jian Sun, Xiaoyan Jin, Yaochu Lai, Khin Wee Jiangnan University School of Artificial Intelligence and Computer Science Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi214122 China Westlake University Trustworth and General Artificial Intelligence Laboratory School of Engineering Hangzhou331712 China Universiti Malaya Department of Biomedical Engineering Kuala Lumpur50603 Malaysia

Recently, transfer learning-based dynamic multiobjective optimization algorithms (TL-DMOAs) have been shown to be very promising in solving dynamic multiobjective optimization problems (DMOPs). However, it is difficult for them to model knowledge capable of delineating the Pareto optimal solutions (POSs) found in each historical environment, because the POSs’ distribution cannot be adequately reflected. Besides, existing TL-DMOAs normally focus on acquiring knowledge from historical environments, but neglect correlations behind them for excavating potential knowledge, restricting the performance in generating high-quality initial populations (HIPs). To address these issues, herein a DMOA with multisource and hidden source-based knowledge transfer (DMOA-MHKT) is proposed. First, we design a knowledge extraction strategy by introducing mean shift, a nonparametric clustering method, to cluster the historical POSs. As clusters’ representatives, the cluster centers are considered to represent environmental knowledge, because they can adequately reflect the POSs’ distribution. Second, the most similar historical environment through environmental match and the last one are selected as two explicit sources. In the former source the POSs’ cluster centers are treated as its knowledge. By contrast, based on the POSs’ cluster centers and knee points in the latter source, a scoring method is designed to generate environmental knowledge by depicting the dynamics between two continuous environments. Third, after aligning knowledge of the explicit sources, a hidden source is learned by excavating correlations and potential knowledge behind them, facilitating the generalization enhancement in generating HIPs. The experimental results especially performance comparisons with seven state-of-the-art DMOAs demonstrate that DMOA-MHKT brings significant improvements in solving DMOPs. © 2025 IEEE. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Palmprint recognition-A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Gao, Chengrui Yang, Ziyuan Jia, Wei Leng, Lu Zhang, Bob Teoh, Andrew Beng Jin College of Computer Science Sichuan University Chengdu610065 China Singapore School of Computer and Information Hefei University of Technology Hefei China Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science University of Macau Taipa China School of Electrical and Electronic Engineering College of Engineering Yonsei University Seoul Korea Republic of

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers' prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition-often grounded in traditional methodologies-there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This paper bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. The paper systematically examines progress across key tasks, including region-of-interest segmentation, feature extraction, and security/privacy-oriented challenges. Beyond highlighting these advancements, the paper identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition. Copyright © 2025, The Authors. All rights reserved.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Self-Distillation-Based Multimodal Feature Alignment Network for Hyperspectral Image and LiDAR Classification

引用

IEEE Geoscience and Remote Sensing Letters 2025年 22卷

作者： Tianhua Mao Jianjun Liu Jinlong Yang Zebin Wu Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China School of Computer Science Nanjing University of Science and Technology Nanjing China

The joint classification of hyperspectral image (HSI) and light detection and ranging (LiDAR) data seeks to provide a more comprehensive characterization of target objects. Multimodal data possess distinct semantic structures in both spectral and spatial dimensions, making efficient feature complementarity and redundancy elimination crucial. To this end, we propose a self-distillation-based multimodal feature alignment network (DFANet), which employs two branches to capture spectral and spatial similarities, respectively, and integrates structural discriminative information from LiDAR at two stages for more effective multimodal data integration. The network comprises three main components: a feature alignment fusion module (FAFM), an offset attention module (OAM), and a self-distillation mechanism. Specifically, the FAFM guides feature alignment through channel-assimilative mapping of multimodal data. The OAM addresses boundary patch classification challenges by learning offset weights of reference points. The self-distillation mechanism filters out irrelevant information during feature alignment by enhancing the coordination between high-level and low-level features. Adequate experiments indicate that our method achieves better results compared to the most recent hyperspectral classification methods on three public datasets.

关键词： Laser radar Feature extraction Hyperspectral imaging Distance measurement Transforms Transformers Training Redundancy Knowledge transfer Geoscience and remote sensing

来源：评论

学校读者我要写书评

暂无评论

Estimating Difficulty Score of Visual Search in Images for Semi-supervised Object Detection 1

引用

16th Pacific Rim Knowledge Acquisition Workshop, PKAW 2019 held in conjunction with the 16th Pacific Rim International Conference on Artificial intelligence, PRICAI 2019

作者： Ma, Dongliang Zhang, Haipeng Wu, Hao Zhang, Tao Sun, Jun JiangSu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence JiangNan University Wuxi China

ISBN: (数字)9783030306397

ISBN: (纸本)9783030306380

Humans can intuitively understand the content of images, and often reach a consensus that some images are more difficult to visual search tasks than others. However, this is quite challenging for computers as it is a subjective task which may be influenced by human emotional factors. Instead of focusing on how the models make reactions on datasets, our method has a capability of assigning scores to samples respectively within a dataset that estimating the difficulty of visual search tasks. Our model shows better performance for predicting visual search difficulty scores of samples produced by human annotators in PASCAL VOC2012. Eventually, we demostrate with experiments that our method has an ability of selecting suitable samples to improve the performance of detectors in a semi-supervised task. © 2019, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A fast GA for automatically evolving CNN architectures 20

A fast GA for automatically evolving CNN architectures

引用

2020 Genetic and Evolutionary Computation Conference, GECCO 2020

作者： Hong, Zhou Fang, Wei Sun, Jun Wu, Xiaojun Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China

ISBN: (纸本)9781450371278

Convolutional neural networks (CNNs) have been proved to be effective models to solve a series of challenging computer vision tasks. However, designing CNN architectures with good performance is still a challenging task. Automatic CNN architecture search algorithms have been proposed in recent years which can find competitive CNN architectures without manual intervention. But automatic search algorithms usually consume considerable computational time and resources. In addition, they only use deep blocks and ignore wide blocks of CNNs, which limits the performance of evolved CNNs. In order to address the above issues, a fast approach for automatically evolving CNN architectures based on deep and wide blocks (FAE-CNN) is proposed through genetic algorithms in this paper. In FAE-CNN, a refined fitness evaluation method based on divided datasets is designed with the purpose to speed up the running time. By introducing the Inception Block, FAE-CNN can evolve optimal CNN architectures from both deep and wide directions. Experimental results on CIFAR10 and CIFAR100 show that FAE-CNN can automatically design CNNs with flexible architectures and better performance in a very short running time. © 2020 Owner/Author.

关键词： Genetic algorithms

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

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

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：