检索结果-内蒙古大学图书馆

Maximal η-clique maintenance over uncertain graph streams

Information Sciences 2025年 717卷

作者： Ma, Ziyi Wang, Liqing Yang, Jianye Zhou, Xu Li, Kenli Gao, Cuiyun School of Artificial Intelligence Hebei University of Technology Tianjin 300401 China Chinacoal Beijing Coal Mining Machinery Co. Ltd. Beijing 102400 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou 543002 China Department of New Networks PengCheng Laboratory Shenzhen 518055 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou 510006 China College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) Shenzhen 518055 China

Maximal clique enumeration is a critical task for analyzing graph data and has a wide range of applications, such as community detection, protein complex identification, and group recommendation. Although many efficient algorithms have been proposed, most of them are designed for static or deterministic graphs. However, in many real-life applications, graphs are often highly dynamic and nondeterministic. In this paper, we study the problem of maximal η-clique maintenance (shorted as MCM) over uncertain graph streams. Given an uncertain graph G and a probability threshold η, MCM reports all incremental η-cliques in G for each update edge of G. To the best of our knowledge, we are the first to systematically study this problem. We first develop a local pivot-based enumeration technique that utilizes the pivot priority of candidates to achieve effective pruning during the maximal η-clique enumeration procedure. Based on the technique, we propose a competitive baseline approach LPMCM, which finds newly generated maximal η-cliques and internal maximal η-cliques. Although LPMCM avoids repeated enumeration of the same maximal η-cliques, it still requires expensive costs in terms of η-clique maximality determination. To further enhance maintenance efficiency, we introduce an approach HLPMCM using the hash-based maximality determination technique and an improved internal maximal η-clique enumeration technique. Extensive experiments show that HLPMCM can achieve 1.1x-19.0x speedup over the competitors and consumes slightly more memory. © 2025 Elsevier Inc.

关键词： Incremental maintenance Maximal clique Pivot enumeration Uncertain graph streams

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study of keypoint Descriptor Fusion

An Experimental Study of Keypoint Descriptor Fusion

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Pan, Yaling He, Li Guan, Yisheng Zhang, Hong Guangzhou China Southern University of Science and Technology Shenzhen Key Laboratory of Robotics and Computer Vision Shenzhen China

ISBN: (纸本)9781665481090

Local feature descriptors play a crucial role in computer vision problems, especially robot motion. Existing descriptors are highly accurate, but their performance de-pends on the influence of distracting factors, such as illumi-nation and viewpoint. There is room for further improvement of these descriptors. In this paper, we provide an in-depth analysis of several exciting features of the descriptor fusion model (DFM) we have proposed in our recent work, which uses an autoencoder to combine descriptors and exploit their respective advantages. With this DFM framework, we fur-ther validate that fused descriptors can retain advantageous properties and that our DFM is a generally applicable method with respect to various component descriptors. Specifically, we evaluate multiple combinations of hand-crafted and CNN descriptors concerning their performance on a benchmark dataset with illumination and viewpoint changes to obtain comprehensive experimental results. The results show that the fused descriptors have better matching accuracy than their component descriptors. © 2022 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning of non-additive joint steganographic embedding costs with attention mechanism

引用

Science China(Information Sciences) 2023年第3期66卷 273-286页

作者： Weixuan TANG Bin LI Weixiang LI Yuangen WANG Jiwu HUANG Institute of Artificial Intelligence and Blockchain Guangzhou University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science and Cyber Engineering Guangzhou University

Image steganography is the art and science of secure communication by concealing information within digital images. In recent years, the techniques of steganographic cost learning have developed rapidly. Although the existing methods can learn satisfactory additive costs, the interplay of different pixels' embedding impacts has not been considered, so the potential of learning may not be fully exploited. To overcome this limitation, in this paper, a reinforcement learning paradigm called Jo Po L(joint policy learning) is proposed to extend the idea of additive cost learning to a non-additive situation. Jo Po L aims to capture the interactions within pixel blocks by defining embedding policies and evaluating contributions of embedding impacts on a block level rather than a pixel level. Then, a policy network is utilized to learn optimal joint embedding policies for pixel blocks through interactions with the environment. Afterwards,these policies can be converted into joint embedding costs for practical message embedding. The structure of the policy network is designed with an effective attention mechanism and incorporated with the domain knowledge derived from traditional non-additive steganographic methods. The environment is responsible for assigning rewards according to the impacts of the sampled joint embedding actions, which are evaluated by the gradient information of a neural network-based steganalyzer. Experimental results show that the proposed non-additive method Jo Po L significantly outperforms the existing additive methods against both feature-based and CNN-based steganalzyers over different payloads.

关键词： information hiding non-additive steganography steganalysis cost learning image processing

来源：评论

学校读者我要写书评

暂无评论

On‐device audio‐visual multi‐person wake word spotting

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1578-1589页

作者： Yidi Li Guoquan Wang Zhan Chen Hao Tang Hong Liu Key Laboratory of Machine Perception Peking UniversityShenzhen Graduate SchoolShenzhenChina College of Computer and Information Hefei University of TechnologyHefeiChina Computer Vision Lab ETH ZurichZurichSwitzerland

Audio‐visual wake word spotting is a challenging multi‐modal task that exploits visual information of lip motion patterns to supplement acoustic speech to improve overall detection ***,most audio‐visual wake word spotting models are only suitable for simple single‐speaker scenarios and require high computational *** development is hindered by complex multi‐person scenarios and computational limitations in mobile *** this paper,a novel audio‐visual model is proposed for on‐device multi‐person wake word ***,an attention‐based audio‐visual voice activity detection module is presented,which generates an attention score matrix of audio and visual representations to derive active speaker ***,the knowledge distillation method is introduced to transfer knowledge from the large model to the on‐device model to control the size of our ***,a new audio‐visual dataset,PKU‐KWS,is collected for sentence‐level multi‐person wake word *** results on the PKU‐KWS dataset show that this approach outperforms the previous state‐of‐the‐art methods.

关键词： audio‐visual fusion human‐computer interfacing speech processing

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Receiving Filters and Complementary set of Sequences for ISAC With Sidelobe Level Suppression

IEEE Journal of Selected Areas in Sensors

引用

IEEE Journal of Selected Areas in Sensors 2024年 1卷 211-223页

作者： Zhang, Kecheng Wu, Jun Dong, Fuwang Lu, Shihang Li, Xiang Yuan, Weijie Southern University of Science and Technology Shenzhen518055 China School of Interdisciplinary Studies Lingnan University Tuen Mun Hong Kong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China

The integrated sensing and communication (ISAC) waveform with a low sidelobe level on all delay indices is important for probing targets in the ISAC scenario. In this article, we consider the problem of jointly designing receiving filters and unimodular complementary sets of sequences (CSS) by minimizing the weighted sum of complementary integrated sidelobe level (CISL) and ISAC interference term at the communication receiver. We propose an optimization algorithm based on the majorization minimization scheme to solve the formulated nonconvex problem with a promised convergence. Fast Fourier transform (FFT) operations are performed in each iteration to improve the computation efficiency. Simulation results demonstrate that the crosscorrelation between the optimized receiving filters and CSS can achieve very low autocorrelation sidelobe levels on all time delay indices. The proposed algorithm has better convergence performance and the same computation complexity compared to the gradient descent algorithm. © 2023 IEEE.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Augmented Feature Representation with Parallel Convolution for Cross-domain Facial Expression Recognition 16th

Augmented Feature Representation with Parallel Convolution ...

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Yang, Fan Xie, Weicheng Zhong, Tao Hu, Jingyu Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (纸本)9783031202322

Facial expression recognition (FER) has made significant progress in the past decade, but the inconsistency of distribution between different datasets greatly limits the generalization performance of a learned model on unseen datasets. Recent works resort to aligning feature distributions between domains to improve the cross-domain recognition performance. However, current algorithms use one output each layer for the feature representation, which can not well represent the complex correlation among multi-scale features. To this end, this work proposes a parallel convolution to augment the representation ability of each layer, and introduces an orthogonal regularization to make each convolution represent independent semantic. With the assistance of a self-attention mechanism, the proposed algorithm can generate multiple combinations of multi-scale features to allow the network to better capture the correlation among the outputs of different layers. The proposed algorithm achieves state-of-the-art (SOTA) performances in terms of the average generalization performance on the task of cross-database (CD)-FER. Meanwhile, when AFED or RAF-DB is used for the training, and other four databases, i.e. JAFFE, SFEW, FER2013 and EXPW are used for testing, the proposed algorithm outperforms the baselines by the margins of 5.93% and 2.24% in terms of the average accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

GOAL: Generalized Jointly Sparse Linear Discriminant Regression for Feature Extraction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 4959-4971页

作者： Lu, Haoquan Lai, Zhihui Zhang, Junhong Yu, Zhuozhen Wen, Jiajun Shenzhen University Computer Vision Institute College of Computer Science and Software Engineering Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China Peking University Shenzhen Graduate School School of Electronic and Computer Engineering Shenzhen518055 China

Ridge regression (RR)-based methods aim to obtain a low-dimensional subspace for feature extraction. However, the subspace's dimensionality does not exceed the number of data categories, hence compromising its capability of feature representation. Moreover, these methods with L2-norm metric and regularization cannot extract highly robust features from data with corruption. To address these problems, in this article, we propose generalized jointly sparse linear discriminant regression (GOAL), a novel regression method based on joint L2,1-norm and capped-L2-norm, which can integrate sparsity, locality, and discriminability into one model to learn a full-rank robust feature extractor. The sparsely selected discriminative features are robust enough to characterize the decision boundary between classes. Locality is related to manifold structure and Laplacian smoothing, which can enhance the robustness of the model. By using the multinorm metric and regularization regression framework, the proposed method obtains the projection with joint sparsity and guarantees that the rank of the projection matrix will not be limited by the number of classes. An iterative algorithm is proposed to compute the optimal solution. Complexity analysis and proofs of convergence are also given in the article. Experiments on well-known datasets demonstrate our model's superiority and generalization ability. © 2020 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Activation Template Matching Loss for Explainable Face Recognition 17

Activation Template Matching Loss for Explainable Face Recog...

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Lin, Huawei Liu, Haozhe Li, Qiufu Shen, Linlin Computer Vision Institute School of Computer Science and Softwre Enginnering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (纸本)9798350345445

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic Explainable Channel Loss (ECLoss) to construct an explainable face recognition network. The explainable network trained with ECLoss can easily learn the facial part-based representation on the target convolutional layer, where an individual channel can detect a certain face part. Our experiments on dozens of datasets show that ECLoss achieves superior explainability metrics, and at the same time improves the performance of face verification without face alignment. In addition, our visualization results also illustrate the effectiveness of the proposed ECLoss. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Tile selection method based on error minimization for photomosaic image creation

引用

Frontiers of computer Science 2021年第3期15卷 165-172页

作者： Hongbo ZHANG Xin GAO Jixiang DU Qing LEI Lijie YANG Department of Computer Science and Technology Huaqiao UniversityXiamen 361021China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao UniversityXiamen 361021China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao UniversityXiamen 361021China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen 518055China

Photomosaic images are composite images composed of many small images called *** its overall visual effect,a photomosaic image is similar to the target image,and photomosaics are also called“montage art”.Noisy blocks and the loss of local information are the major obstacles in most methods or programs that create photomosaic *** solve these problems and generate a photomosaic image in this study,we propose a tile selection method based on error minimization.A photomosaic image can be generated by partitioning the target image in a rectangular pattern,selecting appropriate tile images,and then adding them with a weight *** on the principles of montage art,the quality of the generated photomosaic image can be evaluated by both global and local *** the proposed framework,via an error function analysis,the results show that selecting a tile image using a global minimum distance minimizes both the global error and the local error ***,the weight coefficient of the image superposition can be used to adjust the ratio of the global and local ***,to verify the proposed method,we built a new photomosaic creation dataset during this *** experimental results show that the proposed method achieves a low mean absolute error and that the generated photomosaic images have a more artistic effect than do the existing approaches.

关键词： photomosaic image tile image target image error minimization mean absolute error

来源：评论

学校读者我要写书评

暂无评论

Shearlet-Based Structure-Aware Filtering for Hyperspectral and LiDAR Data Classification

引用

Journal of Remote Sensing 2021年第1期2021卷 237-261页

作者： Sen Jia Zhangwei Zhan Meng Xu College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the Ministry of Natural Resources Shenzhen UniversityShenzhenChina SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for SocietyShenzhenChina

The joint interpretation of hyperspectral images(HSIs)and light detection and ranging(LiDAR)data has developed rapidly in recent years due to continuously evolving image processing ***,most feature extraction methods are carried out by convolving the raw data with fixed-size filters,whereas the structural and texture information of objects in multiple scales cannot be sufficiently *** this article,a shearlet-based structure-aware filtering approach,abbreviated as ShearSAF,is proposed for HSI and LiDAR feature extraction and ***,superpixel-guided kernel principal component analysis(KPCA)is firstly adopted on raw HSIs to reduce the ***,the KPCA-reduced HSI and LiDAR data are converted to the shearlet domain for texture and area feature *** contrast,superpixel segmentation algorithm utilizes the raw HSI data to obtain the initial oversegmentation ***,by utilizing a well-designed minimum merging cost that fully considers spectral(HSI and LiDAR data),texture,and area features,a region merging procedure is gradually conducted to produce a final merging ***,a scale map that locally indicates the filter size is achieved by calculating the edge ***,the KPCA-reduced HSI and LiDAR data are convolved with the locally adaptive filters for feature extraction,and a random forest(RF)classifier is thus adopted for *** effectiveness of our ShearSAF approach is verified on three real-world datasets,and the results show that the performance of ShearSAF can achieve an accuracy higher than that of comparison methods when exploiting small-size training sample *** codes of this work will be available at http://***/papers/for the sake of reproducibility.

关键词： LiDAR Shear utilize

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：