检索结果-内蒙古大学图书馆

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yang, Zeyuan Liu, Jiageng Chen, Peihao Cherian, Anoop Marks, Tim K. Le Roux, Jonathan Gan, Chuang Tsinghua Univ Beijing Peoples R China Zhejiang Univ Hangzhou Peoples R China South China Univ Technol Guangzhou Peoples R China Mitsubishi Elect Res Labs MERL Cambridge MA USA UMass Amherst Amherst MA USA MIT IBM AI Lab Cambridge MA USA

ISBN: (纸本)9798350353006

We leverage Large Language Models (LLM) for zero-shot Semantic Audio visual Navigation (SAVN). Existing methods utilize extensive training demonstrations for reinforcement learning, yet achieve relatively low success rates and lack generalizability. The intermittent nature of auditory signals further poses additional obstacles to inferring the goal information. To address this challenge, we present the Reflective and Imaginative Language Agent (RILA). By employing multi-modal models to process sensory data, we instruct an LLM-based planner to actively explore the environment. During the exploration, our agent adaptively evaluates and dismisses inaccurate perceptual descriptions. Additionally, we introduce an auxiliary LLM-based assistant to enhance global environmental comprehension by mapping room layouts and providing strategic insights. Through comprehensive experiments and analysis, we show that our method outperforms relevant baselines without training demonstrations from the environment and complementary semantic information.

关键词： large language models layout comprehension semantic audio-visual navigation sound source localization zero-shot navigation

来源：评论

学校读者我要写书评

暂无评论

Multimodal Machine Translation with Fusion of Generated visual Information 1

引用

13th International conference on Computer Engineering and Networks (CENet)

作者： Yuan, Jiaqi Shi, Xiayang Niu, Yue Niu, Yufeng Wang, Xuhui Zhengzhou Univ Light Ind Coll Math & Informat Sci Zhengzhou Peoples R China Zhengzhou Univ Light Ind Coll Software Engn Zhengzhou Peoples R China Australian Natl Univ Canberra ACT 2601 Australia Inst Stand Measurement ShanXi Prov Inspect & Testing Ctr ShanXi Prov Xian Shaanxi Peoples R China

ISBN: (数字)9789819992430

ISBN: (纸本)9789819992454;9789819992430;9789819992423

Multi-modal machine translation requires a large amount of training data to improve performance. However, collecting and annotating labeled data typically requires a lot of time and human resources. For tasks such as natural language processing and computer vision, obtaining large-scale annotated data is a challenging problem that needs to be addressed. To address the issue of high cost in obtaining annotated data, this article proposes an effective method of integrating a pre-trained generative visual model for text-to-image generation into pure-text machine translation. To improve the modeling quality of semantic translation from text to image, we will perform conditional augmentation on the text used for image generation. The gate fusion mechanism is used to combine the generated image information with the conditionally augmented text information to assist in improving translation performance. To test the feasibility of the method, we conducted experiments on multiple different datasets. When generating text-to-image correspondence on the Multi30k English-to-German dataset, the Bleu score get a significant improvement in compared to pure-text translation. Experiments and visualization analysis show that the proposed method can effectively improve the quality of pure-text machine translation.

关键词： Neural machine translation visual representation Generated visual information

来源：评论

学校读者我要写书评

暂无评论

Exploratory data analysis of Population Level Smartphone-Sensed data 16th

Exploratory Data Analysis of Population Level Smartphone-Sen...

引用

16th International Joint conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) / 16th International conference on Computer Vision Theory and Applications (VISAPP)

作者： Mansoor, Hamid Gerych, Walter Alajaji, Abdulaziz Buquicchio, Luke Chandrasekaran, Kavin Agu, Emmanuel Rundensteiner, Elke Worcester Polytech Inst Worcester MA 01609 USA

ISBN: (纸本)9783031254765;9783031254772

Mobile health involves gathering smartphone-sensor data passively from user's phones, as they live their lives 'In-the-wild", periodically annotating data with health labels. Such data is used by machine learning models to predict health. Purely Computational approaches generally do not support interpretability of the results produced from such models. In addition, the interpretability of such results may become difficult with larger study cohorts which make population-level insights desirable. We propose Population Level exploration and analysis of smartphone DEtected Symptoms (PLEADES), an interactive visual analytics framework to present smartphone-sensed data. Our approach uses clustering and dimension reduction to discover similar days based on objective smartphone sensor data, across participants for population level analyses. PLEADES enables analysts to apply various clustering and projection algorithms to several smartphonesensed datasets. PLEADES overlays human-labelled symptom and contextual information from in-the-wild collected smartphone-sensed data, to empower the analyst to interpret findings. Such views enable the contextualization of the symptoms that can manifest in smartphone sensor data. We used PLEADES to visualize two real world in-the-wild collected datasets with objective sensor data and human-provided health labels. We validate our approach through evaluations with data visualization and human context recognition experts.

关键词： Interactive visual analytics In-the-wild smartphone-sensed data Exploratory data analysis

来源：评论

学校读者我要写书评

暂无评论

AirLens: Multi-Level visual exploration of Air Quality Evolution in Urban Agglomerations

引用

COMPUTER GRAPHICS FORUM 2022年第3期41卷 223-234页

作者： Qu, Dezhan Lv, Cheng Lin, Yiming Zhang, Huijie Wang, Rong Northeast Normal Univ Sch Informat Sci & Technol Changchun Peoples R China Jilin Univ Key Lab Intelligent Informat Proc Changchun Peoples R China

The precise prevention and control of air pollution is a great challenge faced by environmental experts in recent years. Understanding the air quality evolution in the urban agglomeration is important for coordinated control of air pollution. However, the complex pollutant interactions between different cities lead to the collaborative evolution of air quality. The existing statistical and machine learning methods cannot well support the comprehensive analysis of the dynamic air quality evolution. In this study, we propose AirLens, an interactive visual analytics system that can help domain experts explore and understand the air quality evolution in the urban agglomeration from multiple levels and multiple aspects. To facilitate the cognition of the complex multivariate spatiotemporal data, we first propose a multi-run clustering strategy with a novel glyph design for summarizing and understanding the typical pollutant patterns effectively. On this basis, the system supports the multi-level exploration of air quality evolution, namely, the overall level, stage level and detail level. Frequent pattern mining, city community extraction and useful filters are integrated into the system for discovering significant information comprehensively. The case study and positive feedback from domain experts demonstrate the effectiveness and usability of AirLens.

关键词： CCS Concepts • Human-centered computing → visual analytics Geographic visualization Information visualization

来源：评论

学校读者我要写书评

暂无评论

Space-Time Urban Explorer: A visual Tool for Exploring Spatiotemporal Crime and Patrolling data 37

Space-Time Urban Explorer: A Visual Tool for Exploring Spati...

引用

37th SIBGRAPI conference on Graphics, Patterns and Images (SIBGRAPI)

作者： Santos, Tiago Paulino Souza, Joao Matheus Siqueira Vieira, Thales Nonato, Luis Gustavo Fed Univ Alagoas UFAL Inst Comp Maceio Alagoas Brazil Univ Sao Paulo ICMC USP Inst Math & Comp Sci Sao Carlos Brazil

ISBN: (纸本)9798350376043;9798350376036

Spatiotemporal urban data gathered by public security departments holds immense potential for in-depth analysis, enhancing decision-making in areas such as crime prevention and patrolling strategies. However, extracting meaningful patterns from vast and complex spatiotemporal datasets presents a considerable challenge in the field of big data analytics. We introduce a novel visualization-assisted tool tailored for handling massive spatiotemporal urban datasets, with a specific focus on public security data. At the core of this tool are spatial graph vertex ordering algorithms that perform dimensionality reduction on the vertices' locations. To make this tool practical for handling massive spatiotemporal datasets, we present efficient preprocessing techniques. These techniques are carefully crafted to distill and represent urban spatiotemporal datasets, ensuring efficient data exploration. The effectiveness of the proposed solution is validated through case studies using real datasets from the Military Police of the State of Alagoas - Brazil. We demonstrate the effectiveness of the proposed solutions, showcasing the versatility of the visual tool in accomplishing various relevant analytical tasks.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

NFTeller: Dual Centric visual Analytics of NFT Transactions

NFTeller: Dual Centric Visual Analytics of NFT Transactions

引用

IEEE International conference on Big data and Smart Computing (BigComp)

作者： Cao, Yifan Xia, Meng Shigyol, Kento Cheng, Furui Yu, Qianhang Yang, Xingxing Liu, Hongkun Zeng, Wei Wang, Yang Qu, Huamin Hong Kong Univ Sci & Technol Hong Kong Peoples R China Carnegie Mellon Univ Pittsburgh PA 15213 USA Hong Kong Univ Sci & Technol Guangzhou Guangzhou Peoples R China ETH Zurich Switzerland

ISBN: (纸本)9781665475785

Non-fungible tokens (NFTs) can certify the authenticity and scarcity of digital assets on the blockchain. There is an urgent need to identify impact attributes from various potential factors and further evaluate NFT collectibles. Nevertheless, the task is challenging due to the massive amount of heterogeneous and multi-modal data (e.g., social media text, numerical transaction data, and images) in NFT transactions. To this end, we present an interactive visual analytics system, NFTeller, that provides a dual-centric perspective analysis of NFT transactions. The system i) summarizes the temporal evolution and correlation of transaction patterns and dynamic impact attributes of NFT collection projects;ii) presents an augmented chord diagram with a radial stacked bar chart for exploring the co-collected projects and co-occurring whale accounts. We derive in-depth insights from case studies on a real data set to evaluate the systems' effectiveness and usability.

关键词： Non-fungible tokens (NFTs) Blockchain visual analytics

来源：评论

学校读者我要写书评

暂无评论

The Concept of a New Neural Map for Clustering, data visualization and Prediction with Probability Distribution Approximation 19th

The Concept of a New Neural Map for Clustering, Data Visuali...

引用

19th European, Mediterranean, and Middle Eastern conference (EMCIS)

作者： Morajda, Janusz Krakow Univ Econ Krakow Poland

ISBN: (纸本)9783031306938;9783031306945

The paper submits a proposition of a new data analysis tool (named PDCM - Probability Distribution generating and Clustering Maps) constructed in the form of an extended neural map and dedicated to a variety of tasks, such as specific clustering, visualization, prediction (together with its possible visual analysis and justification) and generation of approximated Bayesian a posteriori probability density distribution for dependent variable. Basic theoretical aspects concerning the structure and training process of the proposed model have been presented. Also, research involving application of the PDCM method for real estate market data (Boston dataset) has been shown together with promising research results and conclusions.

关键词： neural maps neural networks SOM Self-Organizing Prediction Maps data analysis data exploration clustering prediction data visualization probability distribution management real estate

来源：评论

学校读者我要写书评

暂无评论

ICCECE 2024 - International conference on Computer, Electrical and Communication Engineering

ICCECE 2024 - International Conference on Computer, Electric...

引用

2024 International conference on Computer, Electrical and Communication Engineering, ICCECE 2024

ISBN: (纸本)9798350386479

The proceedings contain 35 papers. The topics discussed include: automated texture feature based bone tumor segmentation and image analysis using supervised machine learning;analysis of barrel electroplating line with process mining and Petri-Net model;an effective EEG-based image classification methodology under low data and resource requirements using machine learning;identification of hub genes in interstitial lung disease and their association with lung cancer: an in-silico analysis;impact of basic communication modules and techniques in humanitarian crisis-a brief survey;a comparative analysis between deep learning and machine learning algorithms based on user review sentiment analysis from various OTT applications;FPGA implementation of serial peripheral interface transceiver module;and EmoEyes: a machine learning exploration of emotional states through eye movement tracking in visual content.

关键词：

来源：评论

学校读者我要写书评

暂无评论

visual analysis of Tobacco Leaf Recognition Research Based on CiteSpace 14

Visual Analysis of Tobacco Leaf Recognition Research Based o...

引用

14th International conference on Software Technology and Engineering, ICSTE 2024

作者： Dai, Yanting Zhou, Hua Southwest Forestry University College of Big Data and Intelligent Engineering Kunming China

ISBN: (纸本)9798350378955

This study utilizes CiteSpace software to conduct a visual analysis of the literature in the field of tobacco leaf recognition technology in recent years, aiming to reveal the research hotspots, development trends, and contributions of key institutions and scholars in this domain. By analyzing the changes in the number of publications, keyword co-occurrence networks, author collaboration patterns, and keyword burst situations, this paper demonstrates the in-depth exploration and innovation in both basic research and practical applications of tobacco leaf recognition technology. Firstly, through the analysis of the annual publication volume, we found that research on tobacco leaf recognition has shown a significant growth trend over the past decade, indicating the increasing importance of this field in both academia and industrial applications. Secondly, the analysis of research institutions and authors reveals the dominant positions of institutions such as the Chinese Academy of Agricultural Sciences, the Chinese Academy of Sciences, and N anjing Agricultural University, as well as the outstanding contributions of scholars like Wang Ying, Wang Lu, and Guo Yongfeng in terms of publication volume and collaboration relationships. Furthermore, the keyword co-occurrence network and cluster analysis show that the research focus of tobacco leaf recognition technology covers multiple keyword groups, including gene expression, transcription factors, plant resistance, and biosynthesis, reflecting researchers' multifaceted efforts in theoretical exploration and practical applications. Finally, the keyword burst analysis reveals the rise and fall of keywords in different periods. For instance, the period from 2014 to 2017 was mainly concentrated on 'gene expression' and 'transgenic tobacco,' while from 2018 to 2020, emerging research hotspots such as 'functional analysis' and 'cell death' became prominent. This study provides profound insights and significant references for the

关键词： Agricultural Intelligence Deep Learning Tobacco Leaf Recognition

来源：评论

学校读者我要写书评

暂无评论

QEVIS: Multi-Grained visualization of Distributed Query Execution

引用

IEEE TRANSACTIONS ON visualIZATION AND COMPUTER GRAPHICS 2024年第1期30卷 153-163页

作者： Shen, Qiaomu You, Zhengxin Yan, Xiao Zhang, Chaozu Xu, Ke Zeng, Dan Qin, Jianbin Tang, Bo Southern Univ Sci & Technol Res Inst Trustworthy Autonomous Syst Shenzhen Peoples R China Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen Peoples R China Huawei Technol Co Ltd Shenzhen Peoples R China Shenzhen Univ Shenzhen Inst Comp Sci Shenzhen Peoples R China

Distributed query processing systems such as Apache Hive and Spark are widely-used in many organizations for large-scale data analytics. Analyzing and understanding the query execution process of these systems are daily routines for engineers and crucial for identifying performance problems, optimizing system configurations, and rectifying errors. However, existing visualization tools for distributed query execution are insufficient because (i) most of them (if not all) do not provide fine-grained visualization (i.e., the atomic task level), which can be crucial for understanding query performance and reasoning about the underlying execution anomalies, and (ii) they do not support proper linkages between system status and query execution, which makes it difficult to identify the causes of execution problems. To tackle these limitations, we propose QEVIS, which visualizes distributed query execution process with multiple views that focus on different granularities and complement each other. Specifically, we first devise a query logical plan layout algorithm to visualize the overall query execution progress compactly and clearly. We then propose two novel scoring methods to summarize the anomaly degrees of the jobs and machines during query execution, and visualize the anomaly scores intuitively, which allow users to easily identify the components that are worth paying attention to. Moreover, we devise a scatter plot-based task view to show a massive number of atomic tasks, where task distribution patterns are informative for execution problems. We also equip QEVIS with a suite of auxiliary views and interaction methods to support easy and effective cross-view exploration, which makes it convenient to track the causes of execution problems. QEVIS has been used in the production environment of our industry partner, and we present three use cases from real-world applications and user interview to demonstrate its effectiveness. QEVIS is open-source at https://***/

关键词： visual analytics system distributed query execution performance analysis

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：