共查询到20条相似文献，搜索用时 15 毫秒
1.
With the prevalence of accessible depth sensors, dynamic skeletons have attracted much attention as a robust modality for action recognition. Convolutional neural networks (CNNs) excel at modeling local relations within local receptive fields and are typically inefficient at capturing global relations. In this article, we first view the dynamic skeletons as a spatio-temporal graph (STG) and then learn the localized correlated features that generate the embedded nodes of the STG by message passing. To better extract global relational information, a novel model called spatial–temporal graph interaction networks (STG-INs) is proposed, which perform long-range temporal modeling of human body parts. In this model, human body parts are mapped to an interaction space where graph-based reasoning can be efficiently implemented via a graph convolutional network (GCN). After reasoning, global relation-aware features are distributed back to the embedded nodes of the STG. To evaluate our model, we conduct extensive experiments on three large-scale datasets. The experimental results demonstrate the effectiveness of our proposed model, which achieves the state-of-the-art performance. 相似文献
2.
Recently, Deep Convolutional Neural Network (DCNN) has been recognized as the most effective model for pattern recognition and classification tasks. With the fast growing Internet of Things (IoTs) and wearable devices, it becomes attractive to implement DCNNs in embedded and portable systems. However, novel computing paradigms are urgently required to deploy DCNNs that have huge power consumptions and complex topologies in systems with limited area and power supply. Recent works have demonstrated that Stochastic Computing (SC) can radically simplify the hardware implementation of arithmetic units and has the potential to bring the success of DCNNs to embedded systems. This paper introduces normalization and dropout, which are essential techniques for the state-of-the-art DCNNs, to the existing SC-based DCNN frameworks. In this work, the feature extraction block of DCNNs is implemented using an approximate parallel counter, a near-max pooling block and an SC-based rectified linear activation unit. A novel SC-based normalization design is proposed, which includes a square and summation unit, an activation unit and a division unit. The dropout technique is integrated into the training phase and the learned weights are adjusted during the hardware implementation. Experimental results on AlexNet with the ImageNet dataset show that the SC-based DCNN with the proposed normalization and dropout techniques achieves 3.26% top-1 accuracy improvement and 3.05% top-5 accuracy improvement compared with the SC-based DCNN without these two essential techniques, confirming the effectiveness of our normalization and dropout designs. 相似文献
3.
Detection of salient objects in image and video is of great importance in many computer vision applications. In spite of the fact that the state of the art in saliency detection for still images has been changed substantially over the last few years, there have been few improvements in video saliency detection. This paper proposes a novel non-local fully convolutional network architecture for capturing global dependencies more efficiently and investigates the use of recently introduced non-local neural networks in video salient object detection. The effect of non-local operations is studied separately on static and dynamic saliency detection in order to exploit both appearance and motion features. A novel deep non-local fully convolutional network architecture is introduced for video salient object detection and tested on two well-known datasets DAVIS and FBMS. The experimental results show that the proposed algorithm outperforms state-of-the-art video saliency detection methods. 相似文献
4.
In many real-world cases such as printer devices and in-camera interpolation, only the interpolated versions of the low-resolution images are available. In this paper, a new low-complexity high-performance image super resolution network is proposed that starting from the bicubic interpolated version of the low resolution image produces a high quality super resolved image. The main idea in the proposed scheme is the development of a feature generating block that is capable of producing features using multiple local spatial ranges and multiple resolution levels, fusing them in order to provide a rich set of feature maps, and using them in a recursive framework. The objective in designing such a recursive block is not simply to provide a light-weight network, as is traditionally done in the design of such a network, but also to provide a low count on the number of multiply-accumulate operations with high performance. The experimental results are provided to show that the proposed network outperforms other recursive super resolution networks when their super resolution capability, the number of parameters and number of multiply-accumulate operations are simultaneously taken into consideration. 相似文献
5.
随着高校信息化建设的不断深入,网络安全问题日益严峻。文中针对高校网络面临的主要安全威胁,提出了一种基于深度学习的网络信息安全管理系统。该系统采用MobileNet-SSD模型进行安全威胁检测,并使用图神经网络实现了威胁关联分析与响应。试验结果表明,该系统在准确性、实时性等方面优于传统方法,为高校网络安全提供了有力保障。 相似文献
6.
网络表示学习旨在将网络信息表示为低维稠密的实数向量,解决链接预测、异常检测、推荐系统等任务.近年来,网络表示学习研究取得重大进展,但研究多基于静态网络,而真实世界构成的网络是动态变化的,对动态网络分析的需求日益增加.本文总结了当前动态网络表示学习的方法与研究进展,首先提出网络表示学习的动机,阐述动态网络以及表示学习的发展历史与理论基础;接着,系统概述了大量动态网络嵌入方法,包括基于矩阵分解的动态图嵌入、基于随机游走的动态图嵌入、基于深度学习的动态图嵌入和基于重构概率的动态图嵌入,并分析与比较,给出动态网络表示学习的应用场景;最后,总结未来网络表示学习的研究方向.只有考虑网络的动态性,才能真实反映现实网络的演化,使网络表示学习更具价值. 相似文献
7.
基于三元卷积神经网络的行人再辨识算法多数采用欧式距离度量行人之间的相似度,并配合铰链(hinge)损失函数进行卷积神经网络的训练。然而,这种作法存在两个不足：欧式距离作为行人相似度,鉴别力不够强;铰链损失函数的间隔(Margin)参数设定依赖于人工预先设定且在训练过程中无法自适应调整。为此,针对上述两个不足进行改进,该文提出一种基于新型三元卷积神经网络的行人再辨识算法,以提高行人再辨识的准确率。首先,提出一种归一化混合度量函数取代传统的度量方法进行行人相似度计算,提高了行人相似度度量的鉴别力;其次,提出采用Log-logistic函数代替铰链函数,无需人工设定间隔参数,改进了特征与度量函数的联合优化效果。实验结果表明,所提出的算法在Auto Detected CUHK03 和VIPeR两个数据库上的准确率均获得显著的提升,验证了所提出算法的优越性。 相似文献
8.
知识图谱作为辅助信息可以有效缓解传统推荐模型的冷启动问题。但在提取结构化信息时,现有模型都忽略了图谱中实体之间的邻居关系。针对这一问题,该文提出一种基于共同邻居排序采样的知识图谱卷积网络(KGCN-PN)推荐模型,该模型首先基于共同邻居数目对知识图谱中的每个实体邻域进行排序采样;其次利用图卷积神经网络沿着图谱中的关系路径将实体自身信息与接收域信息逐层融合;最后将用户特征向量与融合得到的实体特征向量送入预测函数中预测用户与实体项目交互的概率。实验结果表明该模型在数据稀疏场景下相较其他基线模型性能均获得了相应提升。 相似文献
9.
《电子学报:英文版》2024,33(3)
Graph neural networks(GNNs)have emerged as powerful approaches to learn knowledge about graphs and vertices.The rapid employment of GNNs poses requirements for processing efficiency.Due to incompati-bility of general platforms,dedicated hardware devices and platforms are developed to efficiently accelerate training and inference of GNNs.We conduct a survey on hardware acceleration for GNNs.We first include and introduce re-cent advances of the domain,and then provide a methodology of categorization to classify existing works into three categories.Next,we discuss optimization techniques adopted at different levels.And finally we propose suggestions on future directions to facilitate further works. 相似文献
10.
针对有限的内存资源导致图神经网络(graph neural network, GNN)无法完全加载属性图的问题,文中提出了二值化身份感知图卷积神经网络(binary identify-aware graph convolutional network, BID-GCN)。该网络通过在消息传递过程中递归地考虑节点的信息,为了获得一个给定的节点的嵌入,BID-GCN将提取以该节点为中心的自我网络,并进行多轮的异构消息传递,在自我网络的中心节点上应用与其他节点不同的参数。在消息传递过程中,对网络参数和输入节点特征进行二值化,并将原始的矩阵乘法修改为二值化以加速运算。通过理论分析和实验评估,BID-GCN可以减少网络参数和输入数据的平均约36倍的内存消耗,并加快引文网络上平均约49倍的推理速度,可以提供与全精度基线相当的性能,较好地解决内存资源有限的问题。 相似文献
11.
《电子学报:英文版》2024,33(3)
The robustness of graph neural networks(GNNs)is a critical research topic in deep learning.Many researchers have designed regularization methods to enhance the robustness of neural networks,but there is a lack of theoretical analysis on the principle of robustness.In order to tackle the weakness of current robustness designing methods,this paper gives new insights into how to guarantee the robustness of GNNs.A novel regularization strategy named Lya-Reg is designed to guarantee the robustness of GNNs by Lyapunov theory.Our results give new insights into how regularization can mitigate the various adversarial effects on different graph signals.Extensive experiments on various public datasets demonstrate that the proposed regularization method is more robust than the state-of-the-art methods such as L1-norm,L2-norm,L21-norm,Pro-GNN,PA-GNN and GARNET against various types of graph adversarial attacks. 相似文献
12.
The involvement of external vendors in semiconductor industries increases the chance of hardware Trojan (HT) insertion in different phases of the integrated circuit (IC) design. Recently, several partial reverse engineering (RE) based HT detection techniques are reported, which attempt to reduce the time and complexity involved in the full RE process by applying machine learning or image processing techniques in IC images. However, these techniques fail to extract the relevant image features, not robust to image variations, complicated, less generalizable, and possess a low detection rate. Therefore, to overcome the above limitations, this paper proposes a new partial RE based HT detection technique that detects Trojans from IC layout images using Deep Convolutional Neural Network (DCNN). The proposed DCNN model consists of stacking several convolutional and pooling layers. It layer-wise extracts and selects the most relevant and robust features automatically from the IC images and eliminates the need to apply the feature extraction algorithm separately. To prevent the over-training of the DCNN model, a new stopping condition method and two new metrics, namely Accuracy difference measure (ADM) and Loss difference measure (LDM), are proposed that halts the training only when the performance of our model genuinely drops. Further, to combat the issue of process variations and fabrication noise generated during the RE process, we include noisy images with varying parameters in the training process of the model. We also apply the data augmentation and regularization techniques in the model to address the issues of underfitting and overfitting. Experimental evaluation shows that the proposed technique provides 99% and 97.4% accuracy on Trust-Hub and synthetic ISCAS dataset, respectively, which is on-an-average 15.83% and 21.69% higher than the existing partial RE based techniques. 相似文献
13.
Aiming at the problem that the remote sensing image quality evaluation models with manually extracted features lack robustness and generality, this paper proposes a 3D CNN-based architecture and nuclear power plant for accurate remote sensing image quality assessment. The model incorporates two sub-networks. The DSVL-based sub-network is employed to extract multi-scale, multi-direction and high-level features by layer-wise training. Afterwards, the extracted feature maps are fused as flowed as input data of the second sub-network, which is designed with 3D CNN architecture and nuclear power plant for remote sensing image quality assessment. Experimental results on remote sensing image quality database from the GeoEye-1 and WorldView-2 satellites show that the proposed model can optimally discover the essential features of the image and effectively extract the high-frequency information of each level of image, and has better overall quality assessment performance than the other state-of-the-art methods. 相似文献
14.
针对基于图卷积的点云分类模型在提取点云不同语义区域的特征信息以及高效利用聚合的高维特征方面存在的问题,本文提出了一种新的点云分类模型,该模型采用了动态自适应图卷积和多层池化相结合的方法。具体而言,本文采用了残差结构来构建更深层的卷积,以学习不同语义区域点对特征中不同层次的特征信息,从而生成动态自适应调整卷积核,针对不同的点对动态更新边的特征关系,从而提取更为精确的局部特征。同时,本文将聚合的高维特征输入到多层最大池化模块中,回收利用第一次最大池化后丢弃的特征信息进行多层最大池化,从而获取更为丰富的高维特征,提高分类模型的精度。实验结果表明,在ModelNet40数据集上,本文提出的分类模型的总体精度达到93.3%,平均精度为90.7%,明显优于目前主流的点云分类模型,并具有较强的鲁棒性。 相似文献
15.
Quality of experience (QoE) assessment for adaptive video streaming plays a significant role in advanced network management systems. It is especially challenging in case of dynamic adaptive streaming schemes over HTTP (DASH) which has increasingly complex characteristics including additional playback issues. In this paper, we provide a brief overview of adaptive video streaming quality assessment. Upon our review of related works, we analyze and compare different variations of objective QoE assessment models with or without using machine learning techniques for adaptive video streaming. Through the performance analysis, we observe that hybrid models perform better than both quality-of-service (QoS) driven QoE approaches and signal fidelity measurement. Moreover, the machine learning-based model slightly outperforms the model without using machine learning for the same setting. In addition, we find that existing video streaming QoE assessment models still have limited performance, which makes it difficult to be applied in practical communication systems. Therefore, based on the success of deep learned feature representations for traditional video quality prediction, we also apply the off-the-shelf deep convolutional neural network (DCNN) to evaluate the perceptual quality of streaming videos, where the spatio-temporal properties of streaming videos are taken into consideration. Experiments demonstrate its superiority, which sheds light on the future development of specifically designed deep learning frameworks for adaptive video streaming quality assessment. We believe this survey can serve as a guideline for QoE assessment of adaptive video streaming. 相似文献
16.
In this paper, we propose a spatio-temporal contextual network, STC-Flow, for optical flow estimation. Unlike previous optical flow estimation approaches with local pyramid feature extraction and multi-level correlation, we propose a contextual relation exploration architecture by capturing rich long-range dependencies in spatial and temporal dimensions. Specifically, STC-Flow contains three key context modules, i.e., pyramidal spatial context module, temporal context correlation module and recurrent residual contextual upsampling module for the effect of feature extraction, correlation, and flow reconstruction, respectively. Experimental results demonstrate that the proposed scheme achieves the state-of-the-art performance of two-frame based methods on Sintel and KITTI datasets. 相似文献
17.
自动调制分类在无线频谱异常检测和无线电环境感知中将发挥重要作用.随着深度学习算法的突破,调制分类任务可利用神经网络达到前所未有的高分类精确度.文中提出了一种新颖的神经网络,称为长短期卷积深度神经网络(LCDNN).该网络创造性地结合了长短期记忆网络(LSTM)、卷积神经网络(CNN)和深度网络体系结构的优点.该模型无需... 相似文献
18.
Automatic License Plate Recognition (ALPR) is an important task with many applications in Intelligent Transportation and Surveillance systems. This work presents an end-to-end ALPR method based on a hierarchical Convolutional Neural Network (CNN). The core idea of the proposed method is to identify the vehicle and the license plate region using two passes on the same CNN, and then to recognize the characters using a second CNN. The recognition CNN massively explores the use of synthetic and augmented data to cope with limited training datasets, and our results show that the augmentation process significantly increases the recognition rate. In addition, we present a novel temporal coherence technique to better stabilize the OCR output in videos. Our method was tested with publicly available datasets containing Brazilian and European license plates, achieving accuracy rates better than competitive academic methods and a commercial system. 相似文献
19.
With the development of deep learning, fatigue detection technology for drivers has achieved remarkable achievements. Although the image-based approach achieves good accuracy, it inevitably leads to greater model complexity, which is unsuitable for mobile terminal devices. Luckily, human skeletal data significantly reduces the impact of noise and input data volume while retaining valid information, and it can better deal with real-world driving scenarios with the benefit of robustness in complex driving situations. This paper proposes a lightweight multi-scale spatio-temporal attention graph convolutional network (MS-STAGCN) to efficiently utilize skeleton data to identify driver states by aggregating locally and globally valid face information, which achieves good performance even for lightweight design. The experimental results show that the method achieves 92.4% accuracy on the NTHU-DDD dataset, which can be applied to fatigue detection tasks of the driver in real-world driving scenarios in the future. 相似文献
20.
In the field of security, faces are usually blurry, occluded, diverse pose and small in the image captured by an outdoor surveillance camera, which is affected by the external environment such as the camera pose and range, weather conditions, etc. It can be described as a problem of hard face detection in natural images. To solve this problem, we propose a deep convolutional neural network named feature hierarchy encoder–decoder network (FHEDN). It is motivated by two observations from contextual semantic information and the mechanism of multi-scale face detection. The proposed network is a scale-variant style architecture and single stage, which are composed of encoder and decoder subnetworks. Based on the assumption that contextual semantic information around face being auxiliary to detect faces, we introduce a residual mechanism to fuse context prior-based information into face feature and formulate the learning chain to train each encoder–decoder pair. In addition, we discuss some important factors in implement details such as the distribution of training dataset, the scale of feature hierarchy, and anchor box size, etc. They have some impact on the detection performance of the final network. Compared with some state-of-the-art algorithms, our method achieves promising performance on the popular benchmarks including AFW, PASCAL FACE, FDDB, and WIDER FACE. Consequently, the proposed approach can be efficiently implemented and routinely applied to detect faces with severe occlusion and arbitrary pose variations in unconstrained scenes. Our code and results are available on https://github.com/zzxcoder/EvaluationFHEDN. 相似文献