检索结果-内蒙古大学图书馆

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jinhuan Wang Yuzhen Zhao Xujie Song Wenzhou Chen Qi Xuan Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology HangZhou China Department of Computer Science and Technology Hangzhou Dianzi University HangZhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

3D human pose estimation (HPE) is crucial due to its extensive applications. While current 3D HPE methods focus on human skeleton topology for accuracy, they often overlook joint angle information, which is vital in 2D-to-3D pose lifting. This paper introduces the Joint Angle Network (JANE) model to leverage joint angle features from 2D poses. We propose an angle graph convolution module to extract joint angle features and a multi-stage parallel fusion module to integrate these features with input image data. Experiments on Human3.6M show that our method improves accuracy by 8.7% and 2.6% over non-spatiotemporal baselines using 2D ground truth and 2D pose detectors, respectively.

关键词： Visualization Solid modeling Three-dimensional displays Accuracy Convolution Pose estimation Feature extraction Transformers Topology Speech processing

来源：评论

学校读者我要写书评

暂无评论

IMPROVING ULTRASOUND TONGUE CONTOUR EXTRACTION USING U-NET AND SHAPE CONSISTENCY-BASED REGULARIZER

IMPROVING ULTRASOUND TONGUE CONTOUR EXTRACTION USING U-NET A...

引用

IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Feng, Ming Wang, Yin Xu, Kele Wang, Huaimin Ding, Bo Tongji Univ Shanghai Peoples R China Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China Natl Univ Def Technol Coll Comp Changsha Peoples R China

ISBN: (纸本)9781728176055

B-mode ultrasound tongue imaging is widely used to visualize the tongue motion, due to its appearing properties. Extracting the tongue surface contour in the B-mode ultrasound image is still a challenge, while it is a prerequisite for further quantitative analysis. Recently, deep learning-based approach has been adopted in this task. However, the standard deep models fail to address faint contour when the ultrasound wave goes parallel to the tongue surface. To address the faint or missing contours in the sequence, we explore the shape consistency-based regularizer, which can take sequential information into account. By incorporating the regularizer, the deep model not only can extract frame-specific contours, but also can enforce the similarity between the contours extracted from adjacent frames. Extensive experiments are conducted both on the synthetic and real ultrasound tongue imaging dataset and the results demonstrate the effectiveness of proposed method. To better promote the research in this field, we have released our code at(1).

关键词： ultrasound tongue imaging speech production contour extraction shape consistency loss

来源：评论

学校读者我要写书评

暂无评论

SPEAR: Dynamic Spatio-Temporal Query processing over High Velocity Data Streams 37

SPEAR: Dynamic Spatio-Temporal Query Processing over High Ve...

引用

37th IEEE International conference on Data Engineering (IEEE ICDE)

作者： Baig, Furqan Teng, Dejun Kong, Jun Wang, Fusheng SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA SUNY Stony Brook Dept Biomed Informat Stony Brook NY 11794 USA Georgia State Univ Dept Comp Sci Dept Math & Stat Atlanta GA 30303 USA

ISBN: (纸本)9781728191843

With the advent of IoT and emerging 5G technology, real-time streaming data are being generated at unprecedented speed and volume having both temporal and spatial dimensions. Effective analysis at such scale and speed require support for dynamically adjusting querying capabilities in real-time. In the spatio-temporal domain, this warrants data as well as query optimization strategies especially for objects with changing motion states. Contemporary spatio-temporal data stream management systems in the distributed domain are mostly dominated by specify-once-apply-continuously query model. Any modification in query state requires query restart limiting system responsiveness and producing outdated or in worst case erroneous results. In this paper, we propose adaptations of principles from streaming databases, spatial data management, and distributed computing to support dynamic spatio-temporal query processing over high-velocity big data streams. We first formulate a set of spatio-temporal data types and functions to seamlessly handle changes in distributed query states. We develop a comprehensive set of streaming spatio-temporal querying methods and propose geohash based dynamic spatial partitioning for effective parallel processing. We implement a prototype on top of Apache Flink, where the in-memory stream processing fits nicely with our spatio-temporal models. Comparative evaluation of our prototype demonstrates the effectiveness of our strategy by maintaining high consistent processing rates for both stationary as well as moving queries over high velocity spatio-temporal big data streams.

关键词： spatio-temporal stream-processing spatiotemporal-stream real-time-spatio-temporal spatial-stream distributed-stream

来源：评论

学校读者我要写书评

暂无评论

Detecting and analysing geomorphological structures in images of comet 67P/Churyumov-Gerasimenko using Fourier transform

引用

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 2021年第3期503卷 3449-3459页

作者： Ruzicka, Birko-Katarina Schroeter, Matthias Pack, Andreas Boehnhardt, Hermann Max Planck Inst Sonnensyst Forsch Justus von Liebig Weg 3 D-37077 Gottingen Germany Georg August Univ Gottingen Geowissensch Zentrum Abt Isotopengeol Goldschmidtstr 1 D-37073 Gottingen Germany Max Planck Inst Dynam & Self Org D-37077 Gottingen Germany

We present a method for automatized detection and analysis of quasi-periodic lineament structures from images at pixel precision. The method exploits properties of the images' frequency domain found by using the Fourier transform. We developed this method with the goal of detecting lineament structures in an image of the Hathor cliff of comet 67P/Churyumov-Gerasimenko, which are caused by layerings and furrows in the nucleus material. Using our method, we determined the orientation and wavelength range of these structures. The detected layering edges have similar orientations and spatial separations of 9-20 m, and are ubiquitous throughout the image. We suggest that the layerings are a global feature of the comet nucleus that provide information about formation and evolution of comet 67P. The furrows are non-uniformly distributed throughout the image. Their orientation is broadly parallel to the direction of the local gravity vector at the Hathor cliff, with spacings similar to those of the layering structures. The furrows are interpreted as signatures of local down-slope movement of cliff material. We demonstrate that the developed method is broadly applicable to the detection and analysis of various kinds of quasi-periodic structures like geological layering, folding and faulting, and texture analysis in general. In order to facilitate the application of our method, this paper is accompanied by a demo program written in MATLAB.

关键词： methods: data analysis techniques: image processing comets: general comets: individual: 67P/Churyumov Gerasimenko

来源：评论

学校读者我要写书评

暂无评论

A Counterfactual Ultrasound Anti-Interference Self-Supervised Network for B-mode Ultrasound Tongue Extraction

A Counterfactual Ultrasound Anti-Interference Self-Supervise...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yan Jia Yuqing Cheng Kele Xu Yong Dou Peng Qiao Zhouyu He National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue’s surface contour remains a significant challenge due to the low signal-to-noise ratio (SNR) and prevalent speckle noise in ultrasound images. Traditional supervised learning models often require large labeled datasets, which are labor-intensive to produce and susceptible to noise interference. To address these limitations, we present a novel Counterfactual Ultrasound Anti-Interference Self-Supervised Network (CUAI-SSN), which integrates self-supervised learning (SSL) with counterfactual data augmentation, progressively disentangles confounding factors, ensuring that the model generalizes well across varied ultrasound conditions. Our approach leverages causal reasoning to decouple noise from relevant features, enabling the model to learn robust representations that focus on essential tongue structures. By generating counterfactual image-label pairs, our method introduces alternative, noise-independent scenarios that enhance model training. Furthermore, we introduce attention mechanisms to enhance the network’s ability to capture fine-grained details even in noisy conditions. Extensive experiments on real ultrasound tongue images demonstrate that CUAI-SSN outperforms existing methods, setting a new benchmark for automated contour extraction in ultrasound tongue imaging. Our code is publicly available at https://***/inexhaustible419/CounterfactualultrasoundAI.

关键词： Training Ultrasonic imaging Tongue Self-supervised learning Data augmentation Data models Cognition Data mining Noise measurement Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

distributed Machine Learning based Mitigating Straggler in Big Data Environment

Distributed Machine Learning based Mitigating Straggler in B...

引用

IEEE International conference on Communications (ICC)

作者： Lu, Haodong Wang, Kun Nanjing Univ Posts & Telecommun Coll Internet Things Nanjing Peoples R China Univ Calif Los Angeles Dept Elect & Comp Engn Los Angeles CA USA

ISBN: (纸本)9781728171227

In big data era, utilizing the parameter server paradigm has been regarded as an efficient and practical way to improve performance in processing deep learning (DL) applications. One of the main problems is that straggler greatly hinders DL training progress, but the previous methods cannot fully consider the resource utilization of the cluster when dealing with straggler. To mitigate straggler problem in parameter server, we propose a Deep Reinforcement Learning (DRL)-based framework called distributed Actor-critic Reinforcement Learning (DARL) that can automatically adapt each worker's training load to the dynamic cluster without parameter settings. DARL employs state-of-the-art techniques to stabilize training and improve convergence, including distributed framework, multiple actors and prioritized experience replay. Meanwhile, we also apply our customized experience sampling method to fully exploit potentially good samples. Experiments using real DL workloads show that DARL outperforms the representative Bulk Synchronous parallel (BSP) scheme by 57.8% and Stale Synchronous parallel (SSP) by 503% in terms of per-iteration time in heterogeneous environment.

关键词： Parameter Server Straggler Deep Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

parallel Solution Method for Hamiltonian Equations Based on FPGA and Matlab Programming Verification

Parallel Solution Method for Hamiltonian Equations Based on ...

引用

Computers, Information processing and Advanced Education (CIPAE), 2020 International conference on

作者： Songcheng Zhou Zijian Zhou School of Information Science and Engineering Hohai University Changzhou China Liaoning University Shenyang China

Differential equations play an important role in the fields of artificial intelligence, image processing, and aerospace, and the solution of differential equations is the mathematical basis for research in each field. Traditional numerical methods can approximate the solution of complex differential equations, but there is a problem of accuracy loss in solving systems that do not have asymptotic stability. As a numerical algorithm that preserves the structural properties of Sin, the Sin algorithm has shown advantages in tracking Hamiltonian systems over long periods. However, few studies on the acceleration of the Sim algorithm for Hamiltonian systems do not possess asymptotic stability. To this end, an improved refined Sim algorithm is proposed in this paper and its effectiveness is verified by MATLAB. In addition, an improved fine Sim algorithm IP based on FPGA devices is constructed and its accuracy and parallel acceleration are verified on a hardware platform. This study provides ideas for the research of accelerated computation of the Xin algorithm for Hamiltonian systems without asymptotic stability, which is important for improving the efficiency of numerical solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LIGHTNE: A Lightweight Graph processing System for Network Embedding 21

LIGHTNE: A Lightweight Graph Processing System for Network E...

引用

ACM SIGMOD International conference on Management of Data (SIGMOD)

作者： Qiu, Jiezhong Dhulipala, Laxman Tang, Jie Peng, Richard Wang, Chi Tsinghua Univ Beijing Peoples R China MIT CSAIL Cambridge MA 02139 USA Georgia Tech Atlanta GA USA Microsoft Res Redmond WA 98052 USA

ISBN: (纸本)9781450383431

We propose LIGHTNE,(1) a cost-effective, scalable, and high quality network embedding system that scales to graphs with hundreds of billions of edges on a single machine. In contrast to the mainstream belief that distributed architecture and GPUs are needed for large-scale network embedding with good quality, we prove that we can achieve higher quality, better scalability, lower cost and faster runtime with shared-memory, CPU-only architecture. LIGHTNE combines two theoretically grounded embedding methods NetSMF and ProNE. We introduce the following techniques to network embedding for the first time: (1) a newly proposed downsampling method to reduce the sample complexity of NetSMF while preserving its theoretical advantages;(2) a high-performance parallel graph processing stack GBBS to achieve high memory efficiency and scalability;(3) sparse parallel hash table to aggregate and maintain the matrix sparsifier in memory;and (4) Intel MKL for efficient randomized SVD and spectral propagation.

关键词： representation learning graph spectral graph processing system network embedding

来源：评论

学校读者我要写书评

暂无评论

parallel approach to high-precision smoke simulation based on a multi-GPU framework 6

Parallel approach to high-precision smoke simulation based o...

引用

6th International conference on image, Vision and Computing, ICIVC 2021

作者： Du, Jinlian Jiang, Bo Jin, Xueyun Faculty of Information Techonology Beijing University of Technology Beijing China

ISBN: (纸本)9781665443685

In this paper, a distributed parallel algorithm for smoke flow field simulation based on a multi-graphical processing unit (GPU) framework is designed, aiming at the requirements of large-scale, high-precision and real-time performance. This algorithm is based on a smoke Navier–Stokes equation with more comprehensive external force interference term to be fully described under the action of various forces. The algorithm solves the problems of data partitioning for the whole flow field, flow field grid-state synchronization between multiple GPUs and global calculation synchronization of the whole framework by designing a variable-transfer and interrupt mechanisms. A general computing framework for GPU-based smoke flow field simulation is also proposed to adaptively partition and assign tasks for the smoke flow field simulation to provide a real-time, accurate solution for simulating smoke flow fields with large-scale data. Simulation experiments show that the algorithm can ensure the correctness of the calculation and offers good efficiency in simulating the large-scale smoke flow field. © 2021 IEEE.

关键词： Navier Stokes equations

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Semi-Autonomous Robotic System for Systematic Solar Panel Cleaning

Design and Implementation of a Semi-Autonomous Robotic Syste...

引用

IEEE International conference on Control and Robotics Engineering (ICCRE)

作者： Isuru Munasinghe Vishva Vijenayake Sahan Viduranga Yomali Lokugama Peshala Jayasekara Department of Electronic and Telecommunication Engineering University of Moratuwa Sri Lanka

ISBN: (数字)9798350372694

ISBN: (纸本)9798350372700

Solar photovoltaic (PV) systems have become a trend as a sustainable energy source on a global scale. However, the dirt accumulated on solar panels often reduces their efficiency, considerably. Existing cleaning methods have limitations such as requiring manual labour, low efficiency, limited to single cleaning method or single operational mode. As a solution, this research study describes the design and implementation of a semi-autonomous solar panel cleaning robot for both dry and wet cleaning. The robot can autonomously navigate on solar panels safely, or user can manually control it using a mobile app. The robot is capable of functioning for around 75 minutes on a single charge on solar panels tilted up to 20°, facilitated by image processing algorithms achieving an accuracy surpassing 96%. The orientation estimation is accomplished through the implementation of three parallel Kalman filters running on an embedded system. Experiments and simulations conducted using the implemented mobile robot show the effectiveness of the proposed robot design.

关键词： Accuracy Systematics Navigation image processing Robot vision systems Estimation Cleaning

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：