检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Cao, Congqi Lu, Yue Zhang, Yifan Jiang, Dongmei Zhang, Yanning Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Lab on Speech and Image Information Processing School of Computer Science Northwestern Poly-technical University Xi'an710129 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing100190 China

Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between any two points brings huge cost in computation and memory, especially for action recognition, where there is an additional temporal dimension. Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition. The global context is factorized into sparse relation maps. We model the relationship between points in the same line along the direction of horizon, vertical and depth at each time, which forms a 3D criss-cross structure, and duplicate the same operation with recurrent mechanism to transmit the relation between points in a line to a plane finally to the whole spatiotemporal space. Compared with the non-local method, the proposed RCCA-3D module reduces the number of parameters and FLOPs by 25% and 30% for video context modeling. We evaluate the performance of RCCA-3D with two latest action recognition networks on three datasets and make a thorough analysis of the architecture, obtaining the optimal way to factorize and fuse the relation maps. Comparisons with other state-of-the-art methods demonstrate the effectiveness and efficiency of our model. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results

arXiv

引用

arXiv 2022年

作者： Zhu, Yurui Wang, Xi Fu, Xueyang Hu, Xiaowei Hu, Jinfan Liu, Xina Chen, Xiangyu Dong, Chao Zhang, Dafeng Huang, Feiyu Liu, Shizhuo Wang, Xiaobing Jin, Zhezhu Jiang, Xuhao Shao, Guangqi Wang, Xiaotao Lei, Lei Zhang, Zhao Zhao, Suiyi Zheng, Huan Gao, Yangcheng Wei, Yanyan Ren, Jiahuan Huang, Tao Fang, Zhenxuan Huang, Mengluan Xu, Junwei Zhang, Yong Yang, Yuechi Shu, Qidi Yang, Zhiwen Li, Shaocong Yao, Mingde Xu, Ruikang Guan, Yuanshen Huang, Jie Xiong, Zhiwei Zhu, Hangyan Liu, Ming Liu, Shaohui Zuo, Wangmeng Jia, Zhuang Song, Binbin Song, Ziqi Mao, Guiting Hou, Ben Liu, Zhimou Ke, Yi Ouyang, Dengpei Han, Dekui Zhang, Jinghao Zhu, Qi Zheng, Naishan Zhao, Feng Jin, Wu Conde, Marcos Nathan, Sabari Timofte, Radu Xu, Tianyi Xu, Jun Hrishikesh, P.S. Puthussery, Densen Jiji, C.V. Biao, Jiang Yuhan, Ding Zhang, Li Wan Xiaoyue, Feng Sijing, Chen Tianheng, Zhong Lu, Jiyang Chen, Hongming Fan, Zhentao Chen, Xiang University of Science and Technology of China China Shanghai Ai Laboratory China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Macau China Samsung Research China Beijing China Xiaomi Beijing China Hefei University of Technology China School of Artificial Intelligence Xidian University China School of Remote Sensing and Information Engineering Wuhan University China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University China Harbin Institute of Technology China Changsha Research Institute of Mining and Metallurgy China Tianjin University China University of Wurzburg Computer Vision Lab Germany Couger Inc. Japan School of Statistics and Data Science Nankai University China Founding Minds Software India Department of Electronics and Communication Srm University Fudan University China Shenyang Aerospace University China Nanjing University of Science and Technology China

Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). To bridge the gap, we introduce the first MIPI challenge including five tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Under-Display Camera (UDC) Image Restoration track on MIPI 2022. In total, 167 participants were successfully registered, and 19 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Under-Display Camera Image Restoration. A detailed description of all models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://***/mipi-challenge/MIPI2022. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards efficient content discovery in NDN with enhanced component-based bloom filters 21

Towards efficient content discovery in NDN with enhanced com...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Zhang, Cuiping Wang, Yunmin School of Electronic and Computer Engineering Peking University China Shenzhen Key Lab of Information Theory and Future Network Architecture Future Network PKU Lab of National Major Research Infrastructure PKU Institute of Big Data Technology Shenzhen Engineering Lab of Converged Networking Technology Huawei and PKU Jointly Engineering Lab of Future Network Based on SDN Shenzhen Graduate School Peking University China

ISBN: (纸本)9781728120584

Variable-length hierarchical names of Named data networking (NDN) content bring about intuitive issues for both content routing and large-scale forwarding. Bloom filters can accelerate hash-based NDN content discovery with a false positive probability. In this paper, we propose ECBF, a component-based bloom filter scheme to enhance the reliability of bloom filters. We exploit the hierarchical characteristics of NDN content names and store them into different bloom filters in a component-based way, and then we present a correlation validation policy to check whether the names exist. Finally, we introduce an ECBF-based content discovery scheme BCD. ECBF and the correlation validation value are stored in a fast on-chip memory, and cryptographic check values of content names and related information are respectively stored in an off-chip memory of intermediate routers. This design not only improves the effectiveness of content discovery, but also reduces the additional memory throughput. We experimentally demonstrate that BCD can provide a more than twice reduction of false probability compared with the primary bloom filter methods. Besides, BCD can economize about 40% memory consumption. © 2019 IEEE.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Attention Autoencoder (STAAE) for ADHD Classification 23rd

Spatiotemporal Attention Autoencoder (STAAE) for ADHD Classi...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Dong, Qinglin Qiang, Ning Lv, Jinglei Li, Xiang Liu, Tianming Li, Quanzheng Center for Advanced Medical Computing and Analysis Department of Radiology Massachusetts General Hospital and Harvard Medical School BostonMA United States School of Physics and Information Technology Shaanxi Normal University Xian China School of Biomedical Engineering and Sydney Imaging Brain and Mind Centre The University of Sydney Camperdown Australia Cortical Architecture Imaging and Discovery Lab Department of Computer Science and Bioimaging Research Center The University of Georgia AthensGA United States MGH & BWH Center for Clinical Data Science BostonMA United States

ISBN: (纸本)9783030597276

It has been of great interest in the neuroimaging community to model spatiotemporal brain function and disorders based on resting state functional magnetic resonance imaging (rfMRI). A variety of spatiotemporal methods have been proposed for rfMRI so far, including deep learning models such as convolution networks (CNN) and recurrent networks (RNN). However, the dominant models fail to capture the long-distance dependency (LDD) due to their sequential nature, which becomes critical at longer sequence lengths due to memory limit. Inspired by human brains extraordinary ability of long-term memory and attention, the attention mechanism is designed for machine translation to draw global dependencies and achieved state-of-the-art. In this paper, we propose a spatiotemporal attention autoencoder (STAAE) to discover global features that address LDDs in rfMRI. STAAE encodes the information throughout the rfMRI sequence and reveals resting state networks (RSNs) that characterize spatial and temporal properties of the data. Considering that the rfMRI is measured without external tasks, an unsupervised classification framework is developed based on the connectome generated with STAAE. This framework has been evaluated on 281 children with ADHD and 266 normal control children from 4 sites of ADHD200 datasets. The proposed STAAE reveals the global functional interaction in the brain and achieves a state-of-the-art classification accuracy from 59.5% to 77.2% on multiple sites. It is evident that the proposed attention-based model provides a novel approach towards better understanding of human brain. © 2020, Springer Nature Switzerland AG.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Discovering Functional Brain Networks with 3D Residual Autoencoder (ResAE) 23rd

Discovering Functional Brain Networks with 3D Residual Autoe...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

ISBN: (纸本)9783030597276

Functional MRI has attracted increasing attention in cognitive neuroscience and clinical mental health research. Towards understanding how brain give rises to mental phenomena, deep learning has been applied to functional MRI (fMRI) dataset to discover the physiological basis of cognitive process. Considering the unsupervised nature of fMRI due to the complex intrinsic brain activities, an encoder-decoder structure is promising to model hidden structure of latent signal sources. Inspired by the success of deep residual learning, we propose a 68-layer 3D residual autoencoder (3D ResAE) to model deep representations of fMRI in this paper. The proposed model is evaluated on the fMRI data under 3 cognitive tasks in Human Connectome Project (HCP). The experimental results have shown that the temporal representations learned by the encoder matches the task design and the spatial representations can be interpreted to be meaningful functional brain networks (FBNs), which not only include tasks based FBNs, but also intrinsic FBNs. The proposed model also outperforms a 3-layer autoencoder, showing the key factor for the performance improvement is depth. Our work demonstrates the feasibility and success of adopting 2D advanced deep residual networks in computer vision into 3D fMRI volume modeling. © 2020, Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Towards Energy Positive Sensing using Kinetic Energy Harvesters

Towards Energy Positive Sensing using Kinetic Energy Harvest...

引用

IEEE International Conference on Pervasive Computing and Communications (PerCom)

作者： Muhammad Moid Sandhu Kai Geissdoerfer Sara Khalifa Raja Jurdak Marius Portmann Brano Kusy School of Information Technology and Electrical Engineering The University of Queensland Brisbane Australia Networked Embedded Systems Lab TU Dresden Germany Data61 Commonwealth Scientific and Industrial Research Organization (CSIRO) Australia School of Electrical Engineering and Computer Science Queensland University of Technology Brisbane Australia

ISBN: (数字)9781728146577

ISBN: (纸本)9781728146584

Conventional systems for motion context detection rely on batteries to provide the energy required for sampling a motion sensor. Batteries, however, have limited capacity and, once depleted, have to be replaced or recharged. Kinetic Energy Harvesting (KEH) allows to convert ambient motion and vibration into usable electricity and can enable batteryless, maintenance free operation of motion sensors. The signal from a KEH transducer correlates with the underlying motion and may thus directly be used for context detection, saving space, cost and energy by omitting the accelerometer. Previous work uses the open circuit or the capacitor voltage for sensing without using the harvested energy to power a load. In this paper, we propose to use other sensing points in the KEH circuit that offer information-rich sensing signals while the energy from the harvester is used to power a load. We systematically analyze multiple sensing signals available in different KEH architectures and compare their performance in a transport mode detection case study. To this end, we develop four hardware prototypes, conduct an extensive measurement campaign and use the data to train and evaluate different classifiers. We show that sensing the harvesting current signal from a transducer can be energy positive, delivering up to ten times as much power as it consumes for signal acquisition, while offering comparable detection accuracy to the accelerometer signal for most of the considered transport modes.

关键词： Kinetic Energy Harvester Wearables IoT Context Detection Energy Positive Sensing Sensing Points Signals signals Energy sources Wearable Kinetics motion sensor capacitor voltage harvesters Batteries LOAD kinetic energy Transducers current signal signal acquisition

来源：评论

学校读者我要写书评

暂无评论

Auto-Generating Neural Networks with Reinforcement Learning for Multi-Purpose Image Forensics

Auto-Generating Neural Networks with Reinforcement Learning ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yujun Wei Yifang Chen Xiangui Kang Z. Jane Wang Liang Xiao Guangdong Key Lab of Information Security School of Data and Computer Science Sun Yat-Sen University Guangzhou China Department of ECE University of British Colombia Vancouver Canada Department of Communication Engineering Xiamen University Xiamen China

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

Designing a forensic convolutional neural network (CNN) is usually based on some ad-hoc intuition and domain knowledge. Many methods to automate neural network design have been proposed for computer vision tasks, but they may not be directly applied to image forensic problems, which tend to detect weak traces signals left by image operations rather than strong image content signals. In this paper, we propose an approach to learn an optimal forensic CNN structure with reinforcement learning for detecting multiple image tampering operations. A learning agent is introduced to select CNN layers sequentially in a limited state-action space using Q-learning with an $\epsilon$-greedy strategy and experience replay. The experiments demonstrate that the auto-generated network performs better than other classic image forensic methods and shows more robustness against JPEG compression. To our knowledge, this is the first attempt to design forensic deep neural networks automatically with reinforcement learning.

关键词： Image forensics Learning (artificial intelligence) Task analysis Neural networks Feature extraction Transform coding

来源：评论

学校读者我要写书评

暂无评论

Interactive deep refinement network for medical image segmentation

arXiv

引用

arXiv 2020年

作者： Kitrungrotsakul, Titinunt Yutaro, Iwamoto Lin, Lanfen Tong, Ruofeng Li, Jingsong Chen, Yen-Wei Healthcare Data Science Zhejiang Lab Hangzhou China Graduate School of Information Science and Engineering Ritsumeikan University Shiga Japan College of Computer Science and Technology Zhejiang University Hangzhou China College of Biomedical Engineering & Instrument Science Zhejiang University Hangzhou China

Deep learning techniques have successfully been employed in numerous computer vision tasks including image segmentation. The techniques have also been applied to medical image segmentation, one of the most critical tasks in computer-aided diagnosis. Compared with natural images, the medical image is a gray-scale image with low-contrast (even with some invisible parts). Because some organs have similar intensity and texture with neighboring organs, there is usually a need to refine automatic segmentation results. In this paper, we propose an interactive deep refinement framework to improve the traditional semantic segmentation networks such as U-Net and fully convolutional network. In the proposed framework, we added a refinement network to traditional segmentation network to refine the segmentation *** results with public dataset revealed that the proposed method could achieve higher accuracy than other state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

GraphNorm: A principled approach to accelerating graph neural network training

arXiv

引用

arXiv 2020年

作者： Cai, Tianle Luo, Shengjie Xu, Keyulu He, Di Liu, Tie-Yan Wang, Liwei Department of Electrical and Computer Engineering Princeton University Zhongguancun Haihua Institute for Frontier Information Technology Key Laboratory of Machine Perception MOE School of EECS Peking University Center for Data Science Peking University Pazhou Lab Microsoft Research

Normalization is known to help the optimization of deep neural networks. Curiously, different architectures require specialized normalization methods. In this paper, we study what normalization is effective for Graph Neural Networks (GNNs). First, we adapt and evaluate the existing methods from other domains to GNNs. Faster convergence is achieved with InstanceNorm compared to BatchNorm and LayerNorm. We provide an explanation by showing that InstanceNorm serves as a preconditioner for GNNs, but such preconditioning effect is weaker with BatchNorm due to the heavy batch noise in graph datasets. Second, we show that the shift operation in InstanceNorm results in an expressiveness degradation of GNNs for highly regular graphs. We address this issue by proposing GraphNorm with a learnable shift. Empirically, GNNs with GraphNorm converge faster compared to GNNs using other normalization. GraphNorm also improves the generalization of GNNs, achieving better performance on graph classification benchmarks. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review

arXiv

引用

arXiv 2023年

作者： Cheng, Sibo Quilodrán-Casas, César Ouala, Said Farchi, Alban Liu, Che Tandeo, Pierre Fablet, Ronan Lucor, Didier Iooss, Bertrand Brajard, Julien Xiao, Dunhui Janjic, Tijana Ding, Weiping Guo, Yike Carrassi, Alberto Bocquet, Marc Arcucci, Rossella Data Science Institute Department of Computing Imperial College London LondonSW7 2AZ United Kingdom Department of Earth Science and Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Computer Science and Engineering Hong Kong University of Science and Technology 999077 Hong Kong IMT Atlantique Lab-STICC UMR CNRS 6285 France and Odyssey Inria/IMT France RIKEN Center for Computational Science Kobe Japan CEREA École des Ponts and EDF R&D île-de-France France The Laboratoire Interdisciplinaire des Sciences du Numérique CNRS Paris-Saclay University OrsayF-91403 France 78401 Chatou France Institut de Mathématiques de Toulouse Toulouse31062 France SINCLAIR AI Lab Saclay France Bergen Norway School of Mathematical Sciences Tongji University Shanghai200092 China Mathematical Institute for Machine Learning and Data Science KU Eichstätt-Ingolstadt Bavaria Germany School of Information Science and Technology Nantong University Nantong226019 China Department of Physics and Astronomy Augusto Righi University of Bologna Bologna40124 Italy

data Assimilation (DA) and Uncertainty quantification (UQ) are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics. Typical applications span from computational fluid dynamics (CFD) to geoscience and climate systems. Recently, much effort has been given in combining DA, UQ and machine learning (ML) techniques. These research efforts seek to address some critical challenges in high-dimensional dynamical systems, including but not limited to dynamical system identification, reduced order surrogate modelling, error covariance specification and model error correction. A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains, resulting in the necessity for a comprehensive guide. This paper provides the first overview of the state-of-the-art researches in this interdisciplinary field, covering a wide range of applications. This review aims at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models, but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems. Therefore, this article has a special focus on how ML methods can overcome the existing limits of DA and UQ, and vice versa. Some exciting perspectives of this rapidly developing research field are also discussed. © 2023, CC BY-NC-SA.

关键词： Dynamical systems

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：