检索结果-内蒙古大学图书馆

ieee symposium on large data analysis and visualization (LDAV)

作者： Johanna Beyer Steffen Frey Guido Reina Silvio Rizzi Gunther H. Weber Soumya Dutta Nicole Marsaglia Peer-Timo Bremer Kenneth Moreland Kristi Potter Julien Tierny Chaoli Wang Hongfeng Yu Harvard University University of Groningen University of Stuttgart Argonne National Laboratory Lawrence Berkeley National Laboratory Indian Institute of Technology Kanpur (IITK) Lawrence Livermore National Laboratory Oak Ridge National Laboratory National Renewable Energy Laboratory CNRS - Sorbonne Université University of Notre Dame University of Nebraska-Lincoln

Join us for the 14th ieee symposium on large data analysis and visualization (ieee LDAV) on Sunday, October 13th 2024 collocated with ieee VIS 2024 in St. Pete Beach, Florida, USA.

ISBN: (数字)9798331516925

ISBN: (纸本)9798331516932

Join us for the 14th ieee symposium on large data analysis and visualization (ieee LDAV) on Sunday, October 13th 2024 collocated with ieee VIS 2024 in St. Pete Beach, Florida, USA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

JIST: Joint Image and Sequence Training for Sequential Visual Place Recognition

引用

ieee ROBOTICS AND AUTOMATION LETTERS 2024年第2期9卷 1310-1317页

作者： Berton, Gabriele Trivigno, Gabriele Caputo, Barbara Masone, Carlo Politecn Torino Dept Control & Comp Engn Visual & Multimodal Appl Learning Lab I-10138 Turin Italy

Visual Place Recognition aims at recognizing previously visited places by relying on visual clues, and it is used in robotics applications for SLAM and localization. Since typically a mobile robot has access to a continuous stream of frames, this task is naturally cast as a sequence-to-sequence localization problem. Nevertheless, obtaining sequences of labelled data is much more expensive than collecting isolated images, which can be done in an automated way with little supervision. As a mitigation to this problem, we propose a novel Joint Image and Sequence Training (JIST) protocol that leverages large uncurated sets of images through a multi-task learning framework. With JIST we also introduce SeqGeM, an aggregation layer that revisits the popular GeM pooling to produce a single robust and compact embedding from a sequence of single-frame embeddings. We show that our model is able to outperform previous state of the art while being faster, using eight times smaller descriptors, having a lighter architecture and allowing to process sequences of various lengths.

关键词： Training Task analysis visualization databases Multitasking Streaming media Location awareness Representation learning simultaneous localization and mapping visual information retrieval

来源：评论

学校读者我要写书评

暂无评论

Reliability analysis of Phase Change Memory-Based Neuromorphic Circuits

Reliability Analysis of Phase Change Memory-Based Neuromorph...

引用

ieee-Computer-Society Annual symposium on VLSI (ISVLSI)

作者： Titirsha, Twisha Shuvo, Md Maruf Hossain Islam, Syed Kamrul Univ Missouri Dept Elect Engn & Comp Sci Columbia MO 65211 USA Univ Texas El Paso Dept Elect & Comp Engn El Paso TX 79968 USA

ISBN: (纸本)9798350354119

This paper presents an in-depth reliability analysis of neuromorphic circuits utilizing phase change memory (PCM). In-memory computing with PCM cells to store synaptic weights is exploited to address the performance gap between processing needs and memory constraints in machine learning computation. The integration of PCM for hardware realization of spiking neural networks (SNNs) enhances data processing and transmission capabilities. However, challenges remain in memristor-based crossbar architectures, including the effects of voltage drops and current fluctuations on the reliability of PCM. Hence, a reliability model accounting for process variations and temperature influences is proposed. The model effectively predicts the reliability of PCM in neuromorphic circuits, paving the way for more robust cognitive computing applications.

关键词： crossbar architecture memristor neuromorphic circuit phase change memory reliability

来源：评论

学校读者我要写书评

暂无评论

Open Long-Tailed Recognition in a Dynamic World

引用

ieee TRANSACTIONS ON PATTERN analysis AND MACHINE INTELLIGENCE 2024年第3期46卷 1836-1851页

作者： Liu, Ziwei Miao, Zhongqi Zhan, Xiaohang Wang, Jiayun Gong, Boqing Yu, Stella X. Nanyang Technol Univ Singapore 639798 Singapore Univ Calif Berkeley Int Comp Sci Inst Berkeley CA 94720 USA Chinese Univ Hong Kong Hong Kong Peoples R China Google Inc Mountain View CA 94043 USA

Real world data often exhibits a long-tailed and open-ended (i.e., with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes). We define Open Long-Tailed Recognition++ (OLTR++) as learning from such naturally distributed data and optimizing for the classification accuracy over a balanced test set which includes both known and open classes. OLTR++ handles imbalanced classification, few-shot learning, open-set recognition, and active learning in one integrated algorithm, whereas existing classification approaches often focus only on one or two aspects and deliver poorly over the entire spectrum. The key challenges are: 1) how to share visual knowledge between head and tail classes, 2) how to reduce confusion between tail and open classes, and 3) how to actively explore open classes with learned knowledge. Our algorithm, OLTR++, maps images to a feature space such that visual concepts can relate to each other through a memory association mechanism and a learned metric (dynamic meta-embedding) that both respects the closed world classification of seen classes and acknowledges the novelty of open classes. Additionally, we propose an active learning scheme based on visual memory, which learns to recognize open classes in a data-efficient manner for future expansions. On three large-scale open long-tailed datasets we curated from ImageNet (object-centric), Places (scene-centric), and MS1M (face-centric) data, as well as three standard benchmarks (CIFAR-10-LT, CIFAR-100-LT, and iNaturalist-18), our approach, as a unified framework, consistently demonstrates competitive performance. Notably, our approach also shows strong potential for the active exploration of open classes and the fairness analysis of minority groups.

关键词： Tail visualization Head Training Task analysis Measurement Magnetic heads Long-tailed recognition few-shot learning active learning

来源：评论

学校读者我要写书评

暂无评论

SRRNet: A Transformer Structure With Adaptive 2-D Spatial Attention Mechanism for Cell Phone-Captured Shopping Receipt Recognition

引用

ieee TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 3289-3298页

作者： Zhou, Haibin Shao, Lujiao Zhang, Haijun Harbin Inst Technol Shenzhen Dept Comp Sci Shenzhen 518055 Peoples R China

Shopping receipts, which are regarded as a kind of consumption proof provided to consumers, contain important information for trade. The digitalization of shopping receipts by extracting text information from images can provide smart retail with precise data analysis for commodity management and supply chain optimization. Despite the fact that traditional optical character recognition (OCR) systems have performed well on document template-based recognition, accurate recognition of receipts taken by cell-phones remains difficult due to the uncertainty of the shooting environment. To address irregular text recognition for receipts, in this research we propose a transformer-based text recognition network model by developing an adaptive 2D spatial attention module to extract the 2D correlation information of image features. We examined the performance of our proposed model on both public benchmarks and a large-scale real-world shopping receipt text recognition dataset. Results demonstrate the efficacy of the proposed method in comparison to extant approaches.

关键词： Text recognition Transformers Decoding Feature extraction Optical character recognition visualization Adaptation models Shopping receipt optical character recognition text recognition spatial attention transformer

来源：评论

学校读者我要写书评

暂无评论

Embedding Environmental Intelligence in Low-cost Drones

Embedding Environmental Intelligence in Low-cost Drones

引用

ieee-Computer-Society Annual symposium on VLSI (ISVLSI)

作者： Gonzalez, Roberto Gomez Gonzalez, Miguel Gomez Trevino, Luis Sundaravadivel, Prabha Univ Texas Tyler Dept Elect & Comp Engn Tyler TX 75701 USA

ISBN: (纸本)9798350354119

Effective environmental monitoring is key in our rapidly changing world, where environmental metrics such as temperature, humidity, and air quality can unexpectedly fluctuate and cause health risks and ecological imbalances and alter informed policymaking. Traditional monitoring paradigms, often associated with latency and high costs, are becoming progressively inadequate for real-time data analysis and decision-making demands. Addressing this critical gap, this paper unveils a cost-effective option for leveraging Aerial Vehicles. The Tello EDU drone, integrated with highly accurate sensors and interfaced with a Raspberry Pi 4B for advanced data processing, brings to life a potential replacement for current environmental monitoring systems. The paper delineates a comprehensive system architecture that synergizes airborne sensing with ground-level data synthesis, enabling instantaneous environmental analytics. Our approach focuses on a new era of community-centric and governance-responsive environmental surveillance. Preliminary results are promising, showcasing the proposed system's capability to transcend the limitations of existing methodologies by delivering a more efficient and scalable solution for environmental oversight.

关键词： Environmental Monitoring Unmanned Aerial Vehicles (UAVs) Internet of Things (IoT) Real-time data Processing Air Quality Sensors Raspberry Pi Influx DB

来源：评论

学校读者我要写书评

暂无评论

Towards an Integrated Performance Framework for Fire Science and Management Workflows 24

Towards an Integrated Performance Framework for Fire Science...

引用

24th ieee/ACM International symposium on Cluster, Cloud, and Internet Computing (CCGrid)

作者： Ahmed, Hena Shende, Ravi Perez, Ismael Crawl, Daniel Purawat, Shweta Altintas, Ilkay Univ Calif San Diego Halicioglu Data Sci Inst La Jolla CA 92093 USA Univ Calif San Diego San Diego Supetromputer Ctr La Jolla CA 92093 USA

ISBN: (纸本)9798350377521;9798350377514

Reliable performance metrics are necessary prerequisites to building large-scale end-to-end integrated workflows for collaborative scientific research, particularly within context of use-inspired decision making platforms with many concurrent users and when computing real-time and urgent results using large data. This work is a building block for the National data Platform, which leverages multiple use-cases including the WIFIRE data and Model Commons for wildfire behavior modeling and the EarthScope Consortium for collaborative geophysical research. This paper presents an artificial intelligence and machine learning (AI/ML) approach to performance assessment and optimization of scientific workflows. An associated early AI/ML framework spanning performance data collection, prediction and optimization is applied to wildfire science applications within the WIFIRE BurnPro3D (BP3D) platform for proactive fire management and mitigation.

关键词： Cyberinfrastructure Workflows Performance analysis Artificial Intelligence Machine Learning

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Framework for Depression Detection During COVID-19 via Harvesting Social Media

引用

ieee TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第2期11卷 2872-2888页

作者： Anshul, Ashutosh Pranav, Gumpili Sai Rehman, Mohammad Zia Ur Kumar, Nagendra Indian Inst Technol Indore Indore 453552 India

The recent coronavirus disease (COVID-19) has become a pandemic and has affected the entire globe. During the pandemic, we have observed a spike in cases related to mental health, such as anxiety, stress, and depression. Depression significantly influences most diseases worldwide, making it difficult to detect mental health conditions in people due to unawareness and unwillingness to consult a doctor. However, nowadays, people extensively use online social media platforms to express their emotions and thoughts. Hence, social media platforms are now becoming a large data source that can be utilized for detecting depression and mental illness. However, the existing approaches often overlook data sparsity in tweets and the multimodal aspects of social media. In this article, we propose a novel multimodal framework that combines textual, user-specific, and image analysis to detect depression among social media users. To provide enough context about the user's emotional state, we propose the following: 1) an extrinsic feature by harnessing the URLs present in tweets and 2) extracting textual content present in images posted in tweets. We also extract five sets of features belonging to different modalities to describe a user. In addition, we introduce a deep learning model, the visual neural network (VNN), to generate embeddings of user-posted images, which are used to create the visual feature vector for prediction. We contribute a curated COVID-19 dataset of depressed and nondepressed users for research purposes and demonstrate the effectiveness of our model in detecting depression during the COVID-19 outbreak. Our model outperforms the existing state-of-the-art methods over a benchmark dataset by 2%-8% and produces promising results on the COVID-19 dataset. Our analysis highlights the impact of each modality and provides valuable insights into users' mental and emotional states.

关键词： Depression Feature extraction Social networking (online) COVID-19 Blogs visualization Surveys Coronavirus disease (COVID-19) deep learning depression machine learning multimodal analysis social media

来源：评论

学校读者我要写书评

暂无评论

引用

ieee TRANSACTIONS ON AFFECTIVE COMPUTING 2024年第4期15卷 2070-2082页

作者： Liu, Wuchao Li, Wengen Ruan, Yu-Ping Shu, Yulou Chen, Juntao Li, Yina Yu, Caili Zhang, Yichao Guan, Jihong Zhou, Shuigeng Tongji Univ Dept Comp Sci & Technol Shanghai 200070 Peoples R China Zhejiang Lab Hangzhou 311121 Peoples R China Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China

Existing multimodal sentiment analysis models focus more on fusing highly correlated image-text pairs, and thus achieves unsatisfactory performance on multimodal social media data which usually manifests weak correlations between different modalities. To address this issue, we first build a large multimodal social media sentiment analysis dataset RU-Senti which contains more than 100,000 image-text pairs with sentiment labels. Then, we proposed a topic-oriented model (TOM) which assumes that text is usually related to a certain portion of the image contents and significant variances exist in sentiment distribution across diverse topics. TOM learns the topic information from textual content and designs a topic-oriented feature alignment module to extract textual semantics correlated information from images, thus achieving the alignment between two modalities. Then, TOM utilizes a transformer encoder initialized with the parameters from a pre-trained vision-language model to fuse the multimodal features for sentiment prediction. According to the experiments over the public MVSA-Multiple dataset and our RU-Senti dataset, RU-Senti is of high suitability for studying weakly correlated multimodal sentiment analysis, and the proposed TOM model also largely outperforms the SOTA mulitimodal sentiment analysis methods and pre-trained vision-language models.

关键词： Sentiment analysis Social networking (online) Reviews Analytical models Correlation visualization Blogs Image-text alignment multimodal sentiment analysis topic-oriented analysis weak correlation

来源：评论

学校读者我要写书评

暂无评论

Efficient representation and analysis for a large tetrahedral mesh using Apache Spark

Efficient representation and analysis for a large tetrahedra...

引用

2024 ieee Topological data analysis and visualization, TopoInVis 2024

作者： Qian, Yuehui Liu, Guoxi Iuricich, Federico Floriani, Leila De University of Maryland College Park United States Clemson University United States

ISBN: (纸本)9798331528447

Tetrahedral meshes are widely used due to their flexibility and adaptability in representing changes of complex geometries and topology. However, most existing data structures struggle to efficiently encode the irregular connectivity of tetrahedral meshes with billions of vertices. We address this problem by proposing a novel framework for efficient and scalable analysis of large tetrahedral meshes using Apache Spark. The proposed framework, called Tetra-Spark, features optimized approaches to locally compute many connectivity relations by first retrieving the Vertex-Tetrahedron (VT) relation. This strategy significantly improves Tetra-Spark's efficiency in performing morphology computations on large tetrahedral meshes. To prove the effectiveness and scalability of such a framework, we conduct a comprehensive comparison against a vanilla Spark implementation for the analysis of tetrahedral meshes. Our experimental evaluation shows that Tetra-Spark achieves up to a 78 × speedup and reduces memory usage by up to 80% when retrieving connectivity relations with the VT relation available. This optimized design further accelerates subsequent morphology computations, resulting in up to a 47.7 × speedup. © 2024 ieee.

关键词： Mesh generation

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：