检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gao, Yue Lu, Jiaxuan Li, Siqi Li, Yipeng Du, Shaoyi BNRist THUIBCS BLBCI School of Software Tsinghua University Beijing100084 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China BNRist THUIBCS BLBCI Department of Automation Tsinghua University Beijing100084 China Department of Ultrasound The Second Affiliated Hospital of Xi’an Jiaotong University China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

Action recognition from video data forms a cornerstone with wide-ranging applications. Single-view action recognition faces limitations due to its reliance on a single viewpoint. In contrast, multi-view approaches capture complementary information from various viewpoints for improved accuracy. Recently, event cameras have emerged as innovative bio-inspired sensors, leading to advancements in event-based action recognition. However, existing works predominantly focus on single-view scenarios, leaving a gap in multi-view event data exploitation, particularly in challenges like information deficit and semantic misalignment. To bridge this gap, we introduce HyperMV, a multi-view event-based action recognition framework. HyperMV converts discrete event data into frame-like representations and extracts view-related features using a shared convolutional network. By treating segments as vertices and constructing hyperedges using rule-based and KNN-based strategies, a multi-view hypergraph neural network that captures relationships across viewpoint and temporal features is established. The vertex attention hypergraph propagation is also introduced for enhanced feature fusion. To prompt research in this area, we present the largest multi-view event-based action dataset THUMV-EACT-50, comprising 50 actions from 6 viewpoints, which surpasses existing datasets by over tenfold. Experimental results show that HyperMV significantly outperforms baselines in both cross-subject and cross-view scenarios, and also exceeds the state-of-the-arts in frame-based multi-view action recognition. Copyright © 2024, 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

Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization

arXiv

引用

arXiv 2021年

作者： Lu, Jianglin Wang, Hailing Zhou, Jie Yan, Mengfan Wen, Jiajun College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China College of Computer Software Tianjin University Tianjin300350 China College of Engineering and Computer Science Australian National University CanberraACT0200 Australia

Recently, deep hashing methods have been widely used in image retrieval task. Most existing deep hashing approaches adopt one-to-one quantization to reduce information loss. However, such class-unrelated quantization cannot give discriminative feedback for network training. In addition, these methods only utilize single label to integrate supervision information of data for hashing function learning, which may result in inferior network generalization performance and relatively low-quality hash codes since the inter-class information of data is totally ignored. In this paper, we propose a dual semantic asymmetric hashing (DSAH) method, which generates discriminative hash codes under three-fold constraints. Firstly, DSAH utilizes class prior to conduct class structure quantization so as to transmit class information during the quantization process. Secondly, a simple yet effective label mechanism is designed to characterize both the intra-class compactness and inter-class separability of data, thereby achieving semantic-sensitive binary code learning. Finally, a meaningful pairwise similarity preserving loss is devised to minimize the distances between class-related network outputs based on an affinity graph. With these three main components, high-quality hash codes can be generated through network. Extensive experiments conducted on various data sets demonstrate the superiority of DSAH in comparison with state-of-the-art deep hashing methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Perceptive self-supervised learning network for noisy image watermark removal

arXiv

引用

arXiv 2024年

作者： Tian, Chunwei Zheng, Menghua Li, Bo Zhang, Yanning Zhang, Shichao Zhang, David School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China School of Electronics and Information Northwestern Polytechnical University Xi’an710129 China School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated AeroSpace-Ground-Ocean Big Data Application Technology Xi’an710129 China Guangxi Key Lab of Multisource Information Mining & Security College of Computer Science & Engineering Guangxi Normal University Guilin541004 China Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China

Popular methods usually use a degradation model in a supervised way to learn a watermark removal model. However, it is true that reference images are difficult to obtain in the real world, as well as collected images by cameras suffer from noise. To overcome these drawbacks, we propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) in this paper. PSLNet depends on a parallel network to remove noise and watermarks. The upper network uses task decomposition ideas to remove noise and watermarks in sequence. The lower network utilizes the degradation model idea to simultaneously remove noise and watermarks. Specifically, mentioned paired watermark images are obtained in a self-supervised way, and paired noisy images (i.e., noisy and reference images) are obtained in a supervised way. To enhance the clarity of obtained images, interacting two sub-networks and fusing obtained clean images are used to improve the effects of image watermark removal in terms of structural information and pixel enhancement. Taking into texture information account, a mixed loss uses obtained images and features to achieve a robust model of noisy image watermark removal. Comprehensive experiments show that our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal. Codes can be obtained at https://***/hellloxiaotian/PSLNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Human Locomotion Assistance using Two-Dimensional Features Based Adaptive Oscillator

Human Locomotion Assistance using Two-Dimensional Features B...

引用

Wearable-robotics-Association Conference (WearRAcon)

作者： Chinimilli, Prudhvi Tej Subramanian, Susheelkumar C. Redkar, Sangram Sugar, Thomas School of Software Engineering Xi’an Jiaotong University Xi’an China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9781538680568

In this paper, an adaptive oscillator method Amplitude Omega Adaptive Oscillator (A omega AO), is proposed to provide bilateral hip assistance for human locomotion. A real-time human locomotion recognition algorithm is integrated with A omega AO to make it robust for various gait activities. The human locomotion recognition algorithm comprises both low-level (to detect activities) and high-level classifiers to detect transitions between activities. The Support Vector Machine (SVM) and Discrete Hidden Markov Model (DHMM) are used as low-level and high-level classifiers respectively. The human locomotion recognition algorithm is trained using two-dimensional features, Amplitude (A) and Omega (omega), obtained from thigh angle measurements, using a single Inertial Measurement Unit (IMU) on each limb. In A omega AO, a pool with four adaptive oscillators (AOs) is used to estimate the filtered thigh angle trajectory. This pool converges to the frequency and phase of the signal, adaptively. To account for amplitude convergence, the amplitude parameters of the oscillator need to be reinitialized based on the human activity, identified by the human locomotion recognition algorithm. In addition to the adaptive oscillators, a Gaussian kernel function based nonlinear filter is employed to predict the future estimates of thigh angles. These predicted estimates, along with the user thigh angles, are used to calculate hip assistive torque in real-time. To verify the efficacy of the proposed approach, experiments were performed, using Hip exoskeleton for Superior Assistance (HeSA), on three healthy subjects. The human locomotion recognition algorithm reported higher classification and prediction accuracy of 95.2% and 94.9% respectively.

关键词： Activity Classification Assistive devices Human Activity Recognition

来源：评论

学校读者我要写书评

暂无评论

Geometry Constrained Weakly Supervised Object Localization 16th

Geometry Constrained Weakly Supervised Object Localization

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Lu, Weizeng Jia, Xi Xie, Weicheng Shen, Linlin Zhou, Yicong Duan, Jinming Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Birmingham Birmingham United Kingdom Department of Computer and Information Science University of Macau Zhuhai China

ISBN: (纸本)9783030585730

We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization (WSOL). GC-Net consists of three modules: a detector, a generator and a classifier. The detector predicts the object location defined by a set of coefficients describing a geometric shape (i.e. ellipse or rectangle), which is geometrically constrained by the mask produced by the generator. The classifier takes the resulting masked images as input and performs two complementary classification tasks for the object and background. To make the mask more compact and more complete, we propose a novel multi-task loss function that takes into account area of the geometric shape, the categorical cross-entropy and the negative entropy. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing (e.g. thresholding) that may require additional tuning. Extensive experiments on the CUB-200-2011 and ILSVRC2012 datasets show that GC-Net outperforms state-of-the-art methods by a large margin. Our source code is available at https://***/lwzeng/GC-Net. © 2020, Springer Nature Switzerland AG.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

DP-Hybrid: A Two-Layer Consensus Protocol for High Scalability in Permissioned Blockchain 2nd

DP-Hybrid: A Two-Layer Consensus Protocol for High Scalabili...

引用

2nd International Conference on Blockchain and Trustworthy Systems, Blocksys 2020

作者： Wen, Fulin Yang, Lei Cai, Wei Zhou, Pan School of Software Engineering South China University of Technology Guangzhou510006 China School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811592126

The permissioned blockchain has attracted the attention of multiple industries like the supply chain due to its decentralization and data tamper resistance. In these industries applications, the permissioned blockchain maintained by multiple participants often has a large number of nodes. The PBFT consensus is commonly used in the permissioned blockchain, but it requires a large amount of message transmission to reach consensus, resulting in poor scalability. In this paper, we propose DP-Hybrid, a novel two-layer consensus protocol, to reduce the communication costs and improve scalability. Specifically, nodes use PBFT to establish K autonomous systems at the bottom layer, and then participate at the top layer with Constrained PoW consensus protocol. DP-Hybrid reduces the communication costs from PBFT’s. The experiment results show that DP-Hybrid’s throughput is always about 10 times that of PBFT when the number of nodes increases. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Spectrogram-based Aging Assessment for Insulations on Stator Coil Bar

Spectrogram-based Aging Assessment for Insulations on Stator...

引用

Chinese Automation Congress (CAC)

作者： Shuo Liu Yue Zhang Bo Hu Jian Ding Jianji Wang Institute of Artificial Intelligence and Robotics College of Artificial Intelligence Xi’an Jiaotong University Xi’an China School of Software Engineering Xi’an Jiaotong University Xi’an China DongFang Electric Machinery Co. Ltd Deyang China

ISBN: (纸本)9781665426480

Based on four kinds of spectrograms, this paper studies how to effectively predict the age of insultations on stator coil bar. The prediction of using time can guide the assessment of stator coil bar. In this work, some samples with different ages and temperatures of epoxy insulations are generated in an accelerated aging test. Then the microscopic morphology spectrograms are obtained for the samples. We use the histogram of oriented gradient (HOG) and gray-level co-occurrence matrix (GLCM) to extract the features of the spectrograms. Finally, support vector machine (SVM) is used to classify and predict the using time of samples based on HOG and GLCM features. This method with accuracy 90.3333% on the classification and prediction for the age of insulations on stator coil bar.

关键词： Insulation Microscopy Accelerated aging Morphology Support vector machine classification Stators Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SGCN:Sparse graph convolution network for pedestrian trajectory prediction

arXiv

引用

arXiv 2021年

作者： Shi, Liushuai Wang, Le Long, Chengjiang Zhou, Sanping Zhou, Mo Niu, Zhenxing Hua, Gang School of Software Engineering Xi'an Jiaotong University China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China JD Finance America Corporation Machine Intelligence Lab Alibaba Group China Wormpex AI Research

Pedestrian trajectory prediction is a key technology in autopilot, which remains to be very challenging due to complex interactions between pedestrians. However, previous works based on dense undirected interaction suffer from modeling superfluous interactions and neglect of trajectory motion tendency, and thus inevitably result in a considerable deviance from the reality. To cope with these issues, we present a Sparse Graph Convolution Network (SGCN) for pedestrian trajectory prediction. Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians. Meanwhile, we use a sparse directed temporal graph to model the motion tendency, thus to facilitate the prediction based on the observed direction. Finally, parameters of a bi-Gaussian distribution for trajectory prediction are estimated by fusing the above two sparse graphs. We evaluate our proposed method on the ETH and UCY datasets, and the experimental results show our method outperforms comparative state-of-the-art methods by 9% in Average Displacement Error (ADE) and 13% in Final Displacement Error (FDE). Notably, visualizations indicate that our method can capture adaptive interactions between pedestrians and their effective motion tendencies. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Temporal Recursive Propagation Network for Action Recognition

Temporal Recursive Propagation Network for Action Recognitio...

引用

International Conference on Computer engineering and Applications (ICCEA)

作者： Xu Li Ming Zeng Jinjun Wang School of Software Engineering Xi’an Jiaotong University Xi’an China Institute of Artificial Intelligence and Robotics XJTU Xi’an China

ISBN: (数字)9781728159041

ISBN: (纸本)9781728159058

Efficient spatio-temporal information modeling is the key to action recognition. Present state-of-the-art suffers from the trade-off of spatiotemporal information modeling capability and model complexity. In this paper, we propose a novel temporal recursive propagation network (TRP) which can efficiently encode and fusion spatiotemporal information. TRP Module can be inserted in existing 2D CNN architectures such as ResNet and MobileNet. Abundant experiments show that TRP enjoys the performance over 3D CNN at lower computational cost than 2D CNN. We evaluate the proposed TRP on the large action recognition benchmark dataset UCF-101. TRP outperforms the state-of-the-art methods on UCF-101 from scratch.

关键词： Convolution Feature extraction Videos Two dimensional displays Three-dimensional displays Network architecture Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A method to generate high precision mesh model and RGB-D dataset for 6D pose estimation task

arXiv

引用

arXiv 2020年

作者： Lu, Minglei Guo, Yu Wang, Fei Dang, Zheng Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China School of Software Engineering Xi’an Jiaotong University China

Recently, 3D version has been improved greatly due to the development of deep neural networks. A high quality dataset is important to the deep learning method. Existing datasets for 3D vision has been constructed, such as Bigbird and YCB. However, the depth sensors used to make these datasets are out of date, which made the resolution and accuracy of the datasets cannot full fill the higher standards of demand. Although the equipment and technology got better, but no one was trying to collect new and better dataset. Here we are trying to fill that gap. To this end, we propose a new method for object reconstruction, which takes into account the speed, accuracy and robustness. Our method could be used to produce large dataset with better and more accurate annotation. More importantly, our data is more close to the rendering data, which shrinking the gap between the real data and synthetic data further. © 2020, CC-BY.

关键词： Large dataset

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：