检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Cong, Runmin Lin, Qinwei Zhang, Chen Li, Chongyi Cao, Xiaochun Huang, Qingming Zhao, Yao Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China School of Computer Science and Engineering Nanyang Technological University Singapore School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University 518107 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China

Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement. For the cross-modality interaction, 1) a progressive attention guided integration unit is proposed to sufficiently integrate RGB-D feature representations in the encoder stage, and 2) a convergence aggregation structure is proposed, which flows the RGB and depth decoding features into the corresponding RGB-D decoding streams via an importance gated fusion unit in the decoder stage. For the cross-modality refinement, we insert a refinement middleware structure between the encoder and the decoder, in which the RGB, depth, and RGB-D encoder features are further refined by successively using a self-modality attention refinement unit and a cross-modality weighting refinement unit. At last, with the gradually refined features, we predict the saliency map in the decoder stage. Extensive experiments on six popular RGB-D SOD benchmarks demonstrate that our network outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively. The code and results can be found from the link of https://***. io/proj_***. © 2022, CC BY-NC-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervision

arXiv

引用

arXiv 2023年

作者： Jiang, Jianping Li, Jiahe Zhang, Baowen Deng, Xiaoming Shi, Boxin National Key Laboratory for Multimedia Information Processing National Engineering Research Center of Visual Technology AI Innovation Center School of Computer Science Peking University Beijing100871 China Beijing Key Laboratory of Human Computer Interactions Institute of Software Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing China

Event camera shows great potential in 3D hand pose estimation, especially addressing the challenges of fast motion and high dynamic range in a low-power way. However, due to the asynchronous differential imaging mechanism, it is challenging to design event representation to encode hand motion information especially when the hands are not moving (causing motion ambiguity), and it is infeasible to fully annotate the temporally dense event stream. In this paper, we propose EvHandPose with novel hand flow representations in Event-to-Pose module for accurate hand pose estimation and alleviating the motion ambiguity issue. To solve the problem under sparse annotation, we design contrast maximization and hand-edge constraints in Pose-to-IWE (Image with Warped Events) module and formulate EvHandPose in a weakly-supervision framework. We further build EvRealHands, the first large-scale real-world event-based hand pose dataset on several challenging scenes to bridge the real-synthetic domain gap. Experiments on EvRealHands demonstrate that EvHandPose outperforms previous event-based methods under all evaluation scenes, achieves accurate and stable hand pose estimation with high temporal resolution in fast motion and strong light scenes compared with RGB-based methods, generalizes well to outdoor scenes and another type of event camera, and shows the potential for the hand gesture recognition task. Copyright © 2023, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Graph Pattern Matching through Model Checking

Graph Pattern Matching through Model Checking

引用

International Conference on Database Theory and Application (DTA)

作者： Rui Qiao Xiaolei Zhong Ling Zhang Heng He College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China School of Software Huazhong University of Science Wuhan China College of Management Wuhan University of Science and Technology Wuhan China

Graph pattern matching is a hot spot in the big data era, which is to find answer graphs matching a given query graph in a data graph of graph databases. “Matching” means two graphs satisfy some relation, such as isomorphism, simulation, bisimulation, etc. Since there are seldom algorithms for the subgraph bisimulation, our work commits to solve the graph pattern matching problem involving bisimulation relations through the model checking technology. We characterize query graphs by modal formulas. By model checking the formulas in the data graphs, the answer graphs bisimilar to the query graphs can be discovered. We add * to basic modal logic language resulting in ML + * language, and add r* to form ML + * formulas. Then a theorem which states that ML + * formulas characterize finite directed graphs modulo bisimulation is put forward. Furthermore, we list steps to find answer graphs bisimilar to a query graph.

关键词： Model checking Pattern matching Databases Big data Topology Arrays computer science

来源：评论

学校读者我要写书评

暂无评论

Research of simulation of creative stage scene based on the 3DGans technology

引用

Journal of information Hiding and Multimedia Signal processing 2018年第6期9卷 1430-1443页

作者： Zhang, Fuquan Ding, Gangyi Lin, Qing Xu, Lin Li, Zuoyong Li, Lijie Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University School of Computer Science & Technology Beijing Institute of Technology Room A9-301 Juyuan Jinshan JiyuanFuzhou350008 China School of Computer Science & Technology Beijing Institute of Technology Room 611 Software Building 5 South Zhongguancun Street Haidian Beijing100081 China College of Foreign Languages Minjiang University Room 303 Building A13 No. 15 Binzhou road Cangshan district JiyuanFuzhou350008 China Innovative Information Industry Research Institute Fujian Normal University Fuqing Brunch of Fujian Normal University Campus County No.1 Longjiang Road FuqingFuzhou350300 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University 200 Xi-yuan-gong Road Room B201 Administrative Building Minhou350121 China School of Computer Science & Technology Beijing Institute of Technology Room 613 Software Building 5 South Zhongguancun Street Haidian Beijing100081 China

Aiming to the feature of the modern stage scenery, combined with 3DGANs technology, we make research into the creation of creative stage scenes to rapidly display problem scene design, reduce the cost of stage design and the data error of virtual and actual simulated effect of the stage. We improve the data of the creative stage scene at the beginning of the design to increase efficiency of the rehearsal stage to enable the simulation scene more intuitive to the displaying of the stage scene and provide the basis for dynamic management of the stage. In this paper, simulation of virtual reality stage scene will be realized through 3DGANs technology. Firstly, the stage data will be extracted and the data of the creative stage scene will be modified. Secondly, the data of the registration of 3D surface image data on the creative scene in the data will be modified by using genetic algorithm. Finally, the simulation experiments will be conducted by using 3DGANs technology to generate creative stage scenes. The results indicated that simulation of the creative stage scene generated by 3DGANs technology would synchronize with the real-time stage effect in which multi-thread processing can improve processor utilization, shorten the reading time of the video image data, effectively reduce the switching time between different tasks, improve the amount of the amount of throughput and concurrency system and to offer a key support for virtual simulation and dynamic management of stage creative scene based on the 3DGANs technology. © 2018, Ubiquitous International. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System for Image Classification

arXiv

引用

arXiv 2023年

作者： Lei, Chunyu Chen, C.L. Philip Guo, Jifeng Zhang, Tong The Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Brain and Affective Cognitive Research Center Pazhou Lab Guangzhou510335 China

Deep learning generally suffers from enormous computational resources and time-consuming training processes. Broad Learning System (BLS) and its convolutional variants have been proposed to mitigate these issues and have achieved superb performance in image classification. However, the existing convolutional-based broad learning system (C-BLS) either lacks an efficient training method and incremental learning capability or suffers from poor performance. To this end, we propose a convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multi-scale (TSMS) feature fusion, which consists of the convolutional feature (CF) layer, convolutional enhancement (CE) layer, TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CF layers. Compared with random filters, the SKM algorithm makes the CF layer learn more comprehensive spatial features. Second, similar to the vanilla BLS, CE layers are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multi-scale features through the integration of CF layers and CE layers. Thanks to the above design and the pseudo-inverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Prediction of hot spots in protein-protein interaction by Nine-Pipeline & Ensemble Learning strategy

Prediction of hot spots in protein-protein interaction by Ni...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jing Hu Zonghao Li Xiaolong Zhang Nansheng Chen School of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Molecular Biology and Biochemistry Simon Fraser University BC Canada

ISBN: (纸本)9781665429825

This paper proposes a NPEL (Nine-Pipeline & Ensemble Learning) strategy based on machine Learning algorithm to predict protein-protein interaction hotspots by training amino acid composition, surface area, amino acid chains and other complex/interface-related structural information. We applied Random Forest, Linear Svm, KNN, Gaussian Naive Bayes, Multi-layer Perceptron Neural Network, Adaboost, XGBoost etc. nine machine learning algorithms combination into an independent pipeline to predict protein hot spots, and the final results are optimized through voting and stacking scheme. In the stacking result of XGBoost and Logistic Regression, the highest accuracy is 0.8462 and improve the indicators of the pipeline results greatly.

关键词： Proteins Drugs Training Protein engineering Machine learning algorithms Three-dimensional displays Pipelines

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral classification based on lightweight 3-D-CNN with transfer learning

arXiv

引用

arXiv 2020年

作者： Zhang, Haokui Li, Ying Jiang, Yenan Wang, Peng Shen, Qiang Shen, Chunhua Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Computer Science University of Adelaide AdelaideSA5005 Australia Faculty of Business and Physical Sciences Aberystwyth University AberystwythSY23 3DB United Kingdom

Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limited available training samples and massive model parameters, DL methods may suffer from overfitting. In this paper, we propose an end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as 3-D-LWNet) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy, in which we pretrain a 3-D model in the source HSI data sets containing a greater number of labeled samples and then transfer it to the target HSI data sets and 2) cross-modal strategy, in which we pretrain a 3-D model in the 2-D RGB image data sets containing a large number of samples and then transfer it to the target HSI data sets. In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets. Experiments on three public HSI data sets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods. © 2020, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Correntropy-Induced Tensor Learning for Multi-view Subspace Clustering

Correntropy-Induced Tensor Learning for Multi-view Subspace ...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yongyong Chen Shuqin Wang Jingyong Su Junxin Chen School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) Shenzhen China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen China Institute of Information Science Beijing Jiaotong University Beijing China School of Software Dalian University of Technology Dalian China

Using some specific optimization problems with specific regularizers, multi-view subspace clustering has achieved better performance over single-view subspace clustering. However, they simply assume the noise obeys the Gaussian distribution only, and thus the dataset with non-Gaussian noise or outliers may not be accurately clustered. To address this issue, this paper proposes a novel correntropy-induced tensor learning method for multi-view subspace clustering (CTMSC). Specifically, CTMSC adopts the correntropy-induced metric to substitute the traditional mean square error (MSE) to handle non-Gaussian noise or outliers. Furthermore, the proposed objective function is optimized using an alternating direction method of multipliers with the aid of half-quadratic technology in the form of multiplication. Extensive experimental results on various real-world datasets demonstrate the effectiveness of the proposed method by comparing several state-of-the-art multi-view subspace clustering methods.

关键词： Measurement Learning systems Tensors Clustering methods Mean square error methods Gaussian distribution Linear programming

来源：评论

学校读者我要写书评

暂无评论

Meta auxiliary learning for facial action unit detection

arXiv

引用

arXiv 2021年

作者： Li, Yong Shan, Shiguang Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Cas Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Cas Center for Excellence in Brain Science and Intelligence Technology

Despite the success of deep neural networks on facial action unit (AU) detection, better performance depends on a large number of training images with accurate AU annotations. However, labeling AU is time-consuming, expensive, and error-prone. Considering AU detection and facial expression recognition (FER) are two highly correlated tasks, and facial expression (FE) is relatively easy to annotate, we consider learning AU detection and FER in a multi-task manner. However, the performance of the AU detection task cannot be always enhanced due to the negative transfer in the multi-task scenario. To alleviate this issue, we propose a Meta Auxiliary Learning method (MAL) that automatically selects highly related FE samples by learning adaptative weights for the training FE samples in a meta learning manner. The learned sample weights alleviate the negative transfer from two aspects: 1) balance the loss of each task automatically, and 2) suppress the weights of FE samples that have large uncertainties. Experimental results on several popular AU datasets demonstrate MAL consistently improves the AU detection performance compared with the state-of-the-art multi-task and auxiliary learning methods. MAL automatically estimates adaptive weights for the auxiliary FE samples according to their semantic relevance with the primary AU detection task. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

High Spectral-Efficiency, Ultra-low MIMO SDM Transmission over a Field-Deployed Multi-Core OAM Fiber

arXiv

引用

arXiv 2024年

作者： Liu, Junyi Xu, Zengquan Mo, Shuqi Huang, Yuming Huang, Yining Li, Zhenhua Guo, Yuying Shen, Lei Xu, Shuo Gao, Ran Du, Cheng Feng, Qian Luo, Jie Liu, Jie Yu, Siyuan State Key Laboratory of Optoelectronic Materials and Technologies School of Electronics and Information Technology Sun Yat-Sen University Guangzhou510006 China Yangtze Optical Fibre and Cable Joint Stock Limited Company State Key Laboratory of Optical Fibre and Cable Manufacture Technology No.9 Guanggu Avenue Hubei Wuhan China School of Information and Electronics Beijing Institute of Technology Beijing100081 China Fiberhome Telecommunication Technologies Co. Ltd Wuhan430074 China School of Electronics and Information Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Sun Yat-sen University Guangzhou510006 China

Few-mode multi-core fiber (FM-MCF) based Space-Division Multiplexing (SDM) systems possess the potential to maximize the number of multiplexed spatial channels per fiber by harnessing both the space (fiber cores) and mode (optical mode per core) dimensions. However, to date, no SDM transmissions over field-deployed FM-MCFs in realistic outdoor settings have been reported, which contrasts with SDM schemes demonstrated using single-mode multi-core fibers (SM-MCFs) installed in practical fiber cable ducts. In this paper, we present the successful demonstration of bidirectional SDM transmission over a 5-km field-deployed seven ring-core fiber (7-RCF) with a cladding diameter of 178 μm, achieving a Spectral Efficiency (SE) of 2×201.6 bit/s/Hz. This work establishes a new record for the highest SE attained in SDM demonstrations utilizing field-deployed fiber cables, achieving an approximate 10x increase compared to the SE of reported field-deployed optical fiber cable transmission systems. Notably, these results are realized through the utilization of small-scale modular 4×4 multiple-input multiple-output (MIMO) processing with a time-domain equalization (TDE) tap number not exceeding 15, maintaining a complexity per unit capacity comparable to that of MIMO equalization in SDM demonstrations employing weakly coupled SM-MCF cables. These results underscore the significant potential for achieving heightened SE and expanding capacity per individual fiber using SDM techniques in practical applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Equalizers

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：