检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yin, He-Feng Wu, Xiao-Jun Song, Xiao-Ning Jiangnan University School of Artificial Intelligence and Computer Science No. 1800 Lihu Avenue Wuxi214122 China Jiangsu Provincial Laboratory of Pattern Recognition and Computational Intelligence No. 1800 Lihu Avenue Wuxi214122 China

Conventional subspace learning approaches based on image gradient orientations only employ the first-order gradient information. However, recent researches on human vision system (HVS) uncover that the neural image is a landscape or a surface whose geometric properties can be captured through the second order gradient information. The second order image gradient orientations (SOIGO) can mitigate the adverse effect of noises in face images. To reduce the redundancy of SOIGO, we propose compact SOIGO (CSOIGO) by applying linear complex principal component analysis (PCA) in SOIGO. Combined with collaborative representation based classification (CRC) algorithm, the classification performance of CSOIGO is further enhanced. CSOIGO is evaluated under real-world disguise, synthesized occlusion and mixed variations. Experimental results indicate that the proposed method is superior to its competing approaches with few training samples, and even outperforms some prevailing deep neural network based approaches. The source code of CSOIGO is available at https://***/yinhefeng/SOIGO. © 2022, CC BY-SA.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Defect detection in textile fabrics with optimal Gabor filter and BRDPSO algorithm 2

Defect detection in textile fabrics with optimal Gabor filte...

引用

2020 2nd International Conference on Artificial intelligence Technologies and Application, ICAITA 2020

作者： Zhang, Jiawei Li, Yueyang Luo, Haichi Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China College of Internet of Things Engineering Jiangnan University Wuxi214122 China

This paper presents an effective method that can detect fabric defects. The method utilizes the optimal Gabor filter and binary random drift particle swarm algorithm (BRDPSO) that can implement feature selection and parameter optimization synchronously. The parameters of 2D-Gabor filters are adjusted by quantum-behaved particle swarm optimization algorithm (QPSO) and the optimal Gabor filter is obtained. BRDPSO is used to select features on the original feature set and simultaneously optimize the parameters of the Isolation Forest (IF) classifier. Extensive experimental results indicate that the proposed method has effective detecting performance on the defect detection of textile fabric. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Textile industry

来源：评论

学校读者我要写书评

暂无评论

Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning

arXiv

引用

arXiv 2022年

作者： Liu, Zhe Li, Yun Yao, Lina Chang, Xiaojun Fang, Wei Wu, Xiaojun Yang, Yi Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University China The School of Computer Science and Engineering University of New South Wales Australia The Australian Artificial Intelligence Institute University of Technology Sydney Australia School of Computer Science and Technology Zhejiang University China

The task of Compositional Zero-Shot Learning (CZSL) is to recognize images of novel state-object compositions that are absent during the training stage. Previous methods of learning compositional embedding have shown effectiveness in closed-world CZSL. However, in Open-World CZSL (OW-CZSL), their performance tends to degrade significantly due to the large cardinality of possible compositions. Some recent works separately predict simple primitives (i.e., states and objects) to reduce cardinality. However, they consider simple primitives as independent probability distributions, ignoring the heavy dependence between states, objects, and compositions. In this paper, we model the dependence of compositions via feasibility and contextuality. Feasibility-dependence refers to the unequal feasibility relations between simple primitives, e.g., hairy is more feasible with cat than with building in the real world. Contextuality-dependence represents the contextual variance in images, e.g., cat shows diverse appearances under the state of dry and wet. We design Semantic Attention (SA) and generative Knowledge Disentanglement (KD) to learn the dependence of feasibility and contextuality, respectively. SA captures semantics in compositions to alleviate impossible predictions, driven by the visual similarity between simple primitives. KD disentangles images into unbiased feature representations, easing contextual bias in predictions. Moreover, we complement the current compositional probability model with feasibility and contextuality in a compatible format. Finally, we conduct comprehensive experiments to analyze and validate the superior or competitive performance of our model, Semantic Attention and knowledge Disentanglement guided Simple Primitives (SAD-SP), on three widely-used benchmark OW-CZSL datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Label distribution expression recognition algorithm based on asymptotic truth value

引用

Journal of Measurement Science and Instrumentation 2021年第3期12卷 295-303页

作者： HUANG Hao GE Hongwei School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi 214122 China

Ambiguous expression is a common phenomenon in facial expression recognition(FER).Because of the existence of ambiguous expression,the effect of FER is severely *** reason maybe that the single label of the data cannot effectively describe complex emotional intentions which are vital in *** distribution learning contains more information and is a possible way to solve this *** apply label distribution learning on FER,a label distribution expression recognition algorithm based on asymptotic truth value is *** the premise of not incorporating extraneous quantitative information,the original information of database is fully used to complete the generation and utilization of label ***,in training part,single label learning is used to collect the mean value of the overall distribution of ***,the true value of data label is approached gradually on the granularity of data ***,the whole network model is retrained using the generated label distribution *** results show that this method can improve the accuracy of the network model obviously,and has certain competitiveness compared with the advanced algorithms.

关键词： facial expression recognition(FER) label distributed learning label smoothing ambiguous expression

来源：评论

学校读者我要写书评

暂无评论

Lace Fabric Image Retrieval Using Siamese Neural Network

Lace Fabric Image Retrieval Using Siamese Neural Network

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： DongDong Xu Yueyang Li HaiChi Luo Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China College of Internet of Things Engineering Jiangnan University Wuxi China

ISBN: (纸本)9781665446006

An efficient lace fabric image retrieval method based on DCNN learning features is proposed in this paper. Fine-tuning with Siamese Neural Network is used to learn effective feature of lace fabric image. During the process of training the Siamese Neural Network, hard negative pairs are selective to achieve fast convergence and good performance. The DCNN learning features are combined with the unique shape feature to enable accurate and efficient retrieval of massive image data. Experimental results demonstrate the effectiveness of retrieval performance of the proposed algorithm and possible practical application of the retrieval system in lace fabric industry to improve management efficiency.

关键词： Training Industries Shape Image processing Conferences Neural networks Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking

arXiv

引用

arXiv 2022年

作者： Tang, Zhangyong Xu, Tianyang Li, Hui Wu, Xiao-Jun Zhu, XueFeng Kittler, Josef Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China The Center for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

We address the problem of multi-modal object tracking in video and explore various options of fusing the complementary information conveyed by the visible (RGB) and thermal infrared (TIR) modalities including pixel-level, feature-level and decision-level fusion. Specifically, different from the existing methods, paradigm of image fusion task is heeded for fusion at pixel level. Feature-level fusion is fulfilled by attention mechanism with channels excited optionally. Besides, at decision level, a novel fusion strategy is put forward since an effortless averaging configuration has shown the superiority. The effectiveness of the proposed decision-level fusion strategy owes to a number of innovative contributions, including a dynamic weighting of the RGB and TIR contributions and a linear template update operation. A variant of which produced the winning tracker at the Visual Object Tracking Challenge 2020 (VOT-RGBT2020). The concurrent exploration of innovative pixel- and feature-level fusion strategies highlights the advantages of the proposed decision-level fusion method. Extensive experimental results on three challenging datasets, i.e., GTOT, VOT-RGBT2019, and VOT-RGBT2020, demonstrate the effectiveness and robustness of the proposed method, compared to the state-of-the-art approaches. Code will be shared at https://***/Zhangyong-Tang/DFAT. © 2022, CC BY.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A multi-view K-multiple-means clustering method

引用

Journal of Measurement Science and Instrumentation 2021年第4期12卷 405-411页

作者： ZHANG Nini GE Hongwei School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi 214122 China

The K-multiple-means(KMM)retains the simple and efficient advantages of the K-means algorithm by setting multiple subclasses,and improves its effect on non-convex data *** aiming at the problem that it cannot be applied to the Internet on a multi-view data set,a multi-view K-multiple-means(MKMM)clustering method is proposed in this *** new algorithm introduces view weight parameter,reserves the design of setting multiple subclasses,makes the number of clusters as constraint and obtains clusters by solving optimization *** new algorithm is compared with some popular multi-view clustering *** effectiveness of the new algorithm is proved through the analysis of the experimental results.

关键词： K-multiple-means(KMM)clustering weight parameters multi-view K-multiple-means(MKMM)method

来源：评论

学校读者我要写书评

暂无评论

Adaptive multi-modal feature fusion for far and hard object detection

引用

Journal of Measurement Science and Instrumentation 2021年第2期12卷 232-241页

作者： LI Yang GE Hongwei Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi 214122 China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China

In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image ***,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection ***,semantema of each image feature map is enhanced by semantic information from all subsequent feature ***,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of ***,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target *** experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,*** the AP by 8.78%and 5.49%on medium and hard difficulty ***,our method achieves greater detection performance compared with many mainstream multi-modal methods,*** the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.

关键词： 3D object detection adaptive fusion multi-modal data fusion attention mechanism multi-neighborhood features

来源：评论

学校读者我要写书评

暂无评论

Model inspired autoencoder for unsupervised hyperspectral image super-resolution

arXiv

引用

arXiv 2021年

作者： Liu, Jianjun Wu, Zebin Xiao, Liang Wu, Xiao-Jun The Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China The School of Computer Science Nanjing University of Science and Technology Nanjing China

This paper focuses on hyperspectral image (HSI) super-resolution that aims to fuse a low-spatial-resolution HSI and a high-spatial-resolution multispectral image to form a high-spatial-resolution HSI (HR-HSI). Existing deep learning-based approaches are mostly supervised that rely on a large number of labeled training samples, which is unrealistic. The commonly used model-based approaches are unsupervised and flexible but rely on hand-craft priors. Inspired by the specific properties of model, we make the first attempt to design a model inspired deep network for HSI super-resolution in an unsupervised manner. This approach consists of an implicit autoencoder network built on the target HR-HSI that treats each pixel as an individual sample. The nonnegative matrix factorization (NMF) of the target HR-HSI is integrated into the autoencoder network, where the two NMF parts, spectral and spatial matrices, are treated as decoder parameters and hidden outputs respectively. In the encoding stage, we present a pixel-wise fusion model to estimate hidden outputs directly, and then reformulate and unfold the model’s algorithm to form the encoder network. With the specific architecture, the proposed network is similar to a manifold prior-based model, and can be trained patch by patch rather than the entire image. Moreover, we propose an additional unsupervised network to estimate the point spread function and spectral response function. Experimental results conducted on both synthetic and real datasets demonstrate the effectiveness of the proposed approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Spectroscopy

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

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：