检索结果-内蒙古大学图书馆

13th IEEE conference on visual Analytics Science and Technology (VAST)

作者： Pham, Vung V. Dang, Tommy Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA

ISBN: (纸本)9781538668610

This work proposes a visual analytic solution which is well-designed to provide investigative functions with fluent interactions to analyze multi-dimensional temporal data. The solution allows users to view different dimensions of the data at different levels of details with a well-designed mixture of different visualizations and smooth interactions. At the general/overview level, various aggregation strategies are used to reduce data to be visualized, and different sorting procedures are used to cluster correlated data together to help discover patterns. Detail views are provided to explore and confirm/reject the identified patterns. Interaction and smooth transition between views are implemented to enable natural actions while performing analysis tasks. This work also presents the result of applying the solution to the VAST 2018 - Mini-Challenge (MC) 2 dataset, which led to the Strong Support for Exploratory analysis award for the challenge.

关键词： Multi-dimensional, temporal data analysis-Heat-map-Line-graph-Interaction Design VAST Challenge 2018-Mini-Challenge 2-Award: Strong Support for Exploratory analysis

来源：评论

学校读者我要写书评

暂无评论

On Expert-Defined Versus Learned Hierarchies for Image Classification 8th

On Expert-Defined Versus Learned Hierarchies for Image Class...

引用

8th International conference on analysis of Images, Social Networks, and Texts (AIST)

作者： Panchenko, Ivan Khan, Adil Innopolis Univ Inst Artificial Intelligence & Data Sci 1 Univ Skaya Str Innopolis Russia

ISBN: (纸本)9783030373344;9783030373337

For classification task involving a large number of classes, a decrease in recognition accuracy is observed for visually similar classes. We believe that forcing the model to learn appropriate features separately for each set of similar classes could improve classification performance. To justify our idea, we tried to improve classification performance by employing class hierarchy, which reflects visual similarities in data. More specifically, we used and compared two kinds of hierarchies to enhance classification performance of the model: (i) a hierarchy defined by experts (H-E), and (ii) a hierarchy created from performance results of a flat classifier and using DBScan clustering method (H-C). Moreover, we created a classification model that efficiently utilizes these hierarchies to learn appropriate features at different levels of the hierarchy. We evaluated the performance of the model on CIFAR-100 benchmark. Our results demonstrate that the hierarchical classification under H-C outperforms both H-E and the flat classifier.

关键词： Hierarchical classification Image classification Confusion matrix Class similarity

来源：评论

学校读者我要写书评

暂无评论

DFVS: Deep Flow Guided Scene Agnostic Image Based visual Servoing

DFVS: Deep Flow Guided Scene Agnostic Image Based Visual Ser...

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Y V S Harish Harit Pandya Ayush Gaud Shreya Terupally Sai Shankar K. Madhava Krishna IIIT Hyderabad India University of Lincoln UK Mathworks India

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Existing deep learning based visual servoing approaches regress the relative camera pose between a pair of images. Therefore, they require a huge amount of training data and sometimes fine-tuning for adaptation to a novel scene. Furthermore, current approaches do not consider underlying geometry of the scene and rely on direct estimation of camera pose. Thus, inaccuracies in prediction of the camera pose, especially for distant goals, lead to a degradation in the servoing performance. In this paper, we propose a two-fold solution: (i) We consider optical flow as our visual features, which are predicted using a deep neural network. (ii) These flow features are then systematically integrated with depth estimates provided by another neural network using interaction matrix. We further present an extensive benchmark in a photo-realistic 3D simulation across diverse scenes to study the convergence and generalisation of visual servoing approaches. We show convergence for over 3m and 40 degrees while maintaining precise positioning of under 2cm and 1 degree on our challenging benchmark where the existing approaches that are unable to converge for majority of scenarios for over 1.5m and 20 degrees. Furthermore, we also evaluate our approach for a real scenario on an aerial robot. Our approach generalizes to novel scenarios producing precise and robust servoing performance for 6 degrees of freedom positioning tasks with even large camera transformations without any retraining or fine-tuning.

关键词： visual servoing Cameras Convergence visualization Adaptive optics Task analysis

来源：评论

学校读者我要写书评

暂无评论

Criteria analysis, weight and Priority for Handling Bridges in Kudus District using AHP and Promethee ii methods 2

Criteria Analysis, weight and Priority for Handling Bridges ...

引用

2nd Forum in Research, Science, and Technology (FIRST)

作者： Prasetyo, E. D. W. Handajani, Mudjiastuti Ismiyati Off Publ Works & Spatial Planning Kudus Dist 59311 Central Java Indonesia Diponegoro Univ Civil Engn Semarang 50275 Indonesia

To determine the criteria for selecting bridges, the ideal support method was required to assist the decision makers. This study was based in the Kudus district and the object of this research was 20 proposals from the Public Works Office for the 2019 bridge handling. From the visual assessment: severe bridge damage (10 bridges), minor bridge damage (3 bridges), medium bridge damage (6 bridges) and bridges in good condition (1 bridge). An imbalance exists between the bridges that need to be maintained and the capacity that can. Depend on existing data, the objective of this study is to analyze the ideal weight main criteria and priority for handling the bridge using the AHP and Promethee ii method. A total of 10 respondents were involved in assessing the criteria for The AHP method. A more consistent weighting criteria were produced with a value of 0.31, the ADT weight was 0.19, the number of public and social facilities weight was 0.12, the population weight was 0.15, the area weight was 0.05, the bridge length weight was 0.05, and the bridge width weight was 0.13. The weight of the ideal main criteria is approximately 0.40. Furthermore, the Promethee ii method makes the process of priority weighting more dynamic and easier by reducing questionnaire from the AHP method. The main priority was the 8 severely damaged. The highest weight priority was the Klaling - Tanjungrejo 05 bridge.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Lynceus: Cost-efficient Tuning and Provisioning of data Analytic Jobs

Lynceus: Cost-efficient Tuning and Provisioning of Data Anal...

引用

International conference on Distributed Computing Systems

作者： Maria Casimiro Diego Didona Paolo Romano Luís Rodrigues Willy Zwaenepoel David Garlan INESC-ID and Instituto Superior Técnico Universidade de Lisboa Institute for Software Research Carnegie Mellon University IBM Research Europe Zurich University of Sydney

ISBN: (数字)9781728170022

ISBN: (纸本)9781728170039

Modern data analytic and machine learning jobs find in the cloud a natural deployment platform to satisfy their notoriously large resource requirements. Yet, to achieve cost efficiency, it is crucial to identify a deployment configuration that satisfies user-defined QoS constraints (e.g., on execution time), while avoiding unnecessary *** paper introduces Lynceus, a new approach for the optimization of cloud-based data analytic jobs that improves over state-of-the-art approaches by enabling significant cost savings both in terms of the final recommended configuration and of the optimization process used to recommend *** existing solutions, Lynceus optimizes in a joint fashion both the cloud-related (i.e., which and how many machines to provision) and the application-level (e.g. the hyper-parameters of a machine learning algorithm) parameters. This allows for a reduction of the cost of recommended configurations by up to 3.7× at the 90-th percentile with respect to existing approaches, which treat the optimization of cloud-related and application- level parameters as two independent ***, Lynceus reduces the cost of the optimization process (i.e., the cloud cost incurred for testing configurations) by up to 11×. Such an improvement is achieved thanks to two mechanisms: i) a timeout approach which allows to abort the exploration of configurations that are deemed suboptimal, while still extracting useful information to guide future explorations and to improve its predictive model - differently from recent works, which either incur the full cost for testing suboptimal configurations or are unable to extract any knowledge from aborted runs; ii) a long-sighted and budget-aware technique that determines which configurations to test by predicting the long-term impact of each exploration - unlike state-of-the-art approaches for the optimization of cloud jobs, which adopt greedy optimization methods.

关键词： data analysis Quality of service Predictive models data mining Optimization Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

Integrated stratigraphic, thermal/burial and uncertainty modeling of the levant basin (East-Mediterranean region)

Integrated stratigraphic, thermal/burial and uncertainty mod...

引用

Offshore Mediterranean conference and Exhibition 2019, OMC 2019

作者： Nader, Fadi H. IFP Energies nouvelles France

An integrated workflow for modeling sedimentary basins including source to sink stratigraphic forward simulations, thermal and burial evolutions and uncertainty analyses, has been designed and applied on the frontier Levant Basin in the East-Mediterranean region (model covering around 200,000 sq. km, with horizontal cells grid resolution of 5 sq. km and less than 50m thick). The objective of this workflow is to produce reasonable multi-scenario simulations and probabilistic information that can help make sound decisions for less risky hydrocarbon exploration. Alternatively, the same approach can be applied to better understand sedimentary basins for developing hydrothermal energy resources and/or carbon and energy storage elsewhere. The keyword is "integration", and it involves a variety of numerical tools (as well as concept-thinking). Uncertainty has to be quantified ultimately, and minimized for plausible geological and physical simulations. To reach that end, a unique working environment for efficient basin analysis has to secure the following steps: i) basic characterization/integration of all available geological, geophysical and geochemical data (leading to conceptual models);ii) sedimentary facies modeling (with stratigraphic forward numerical engines);iii) structural characterization and modeling (deformation, inversion and faults);iv) burial/thermal and petroleum systems modeling;and v) uncertainty analysis and modeling (risk management). Bridging the gap between sedimentologists, structural geologists, geochemists, petroleum geologists, and geo-modelers proved to be a must for achieving integrated concepts and thereafter numerical models. © 2019 Offshore Mediterranean conference (OMC). All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Making machine intelligence less scary for criminal analysts: reflections on designing a visual comparative case analysis tool

引用

visual COMPUTER 2018年第9期34卷 1225-1241页

作者： Jentner, Wolfgang Sacha, Dominik Stoffel, Florian Ellis, Geoffrey Zhang, Leishi Keim, Daniel A. Middlesex Univ Data Intens Syst London England Univ Konstanz Univ Str 10 D-78464 Constance Germany Univ Konstanz Data Anal & Visualizat Grp Univ Str 10 D-78464 Constance Germany

A fundamental task in criminal intelligence analysis is to analyze the similarity of crime cases, called comparative case analysis (CCA), to identify common crime patterns and to reason about unsolved crimes. Typically, the data are complex and high dimensional and the use of complex analytical processes would be appropriate. State-of-the-art CCA tools lack flexibility in interactive data exploration and fall short of computational transparency in terms of revealing alternative methods and results. In this paper, we report on the design of the Concept Explorer, a flexible, transparent and interactive CCA system. During this design process, we observed that most criminal analysts are not able to understand the underlying complex technical processes, which decrease the users' trust in the results and hence a reluctance to use the tool. Our CCA solution implements a computational pipeline together with a visual platform that allows the analysts to interact with each stage of the analysis process and to validate the result. The proposed visual analytics workflow iteratively supports the interpretation of the results of clustering with the respective feature relations, the development of alternative models, as well as cluster verification. The visualizations offer an understandable and usable way for the analyst to provide feedback to the system and to observe the impact of their interactions. Expert feedback confirmed that our user-centered design decisions made this computational complexity less scary to criminal analysts.

关键词： Crime intelligence analysis visual analytics Clustering System design Human-computer interaction Sequential pattern mining Text analysis Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

analysis on the performance of VIO according to Trajectory Planning of UAV

Analysis on the performance of VIO according to Trajectory P...

引用

International conference on Control, Automation and Systems ( ICCAS)

作者： EungChang Mason Lee Hyun Myung School of Electrical Engineering KI-AI KI-R Korea Advanced Institute of Science and Technology Daejeon Korea

ISBN: (数字)9788993215205

ISBN: (纸本)9781728185620

Recently, Unmanned Aerial Vehicles (UAVs) have been widely researched to accomplish tasks such as structural inspection, drone racing, and exploration of an unknown environment. To make the most of UAV and correctly estimate its pose with inexpensive and light-weight sensors such as Inertial Measurement Unit (IMU) and cameras, visual Inertial Odometry (VIO) has been intensively researched. There were a few analyses on the performance of VIO methods where only estimated pose error and utilization of the computing resources were considered. However, the performance of them according to trajectory planning was not treated. Trajectory planning can be one of the main reasons for the drift of localization from VIO since the sensors acquire the data at their sampling rates. In this paper, we analyze the performance of VIO on various trajectories that have different orders of polynomials for the desired position over time and hence different velocity, acceleration, and the first, second derivative of acceleration, using simulator which reflects the real dynamics of UAV. As a result, the higher the order of polynomial for trajectory, the better performance of VIO can be observed.

关键词： Trajectory Acceleration Cameras visualization Trajectory planning State estimation Pose estimation

来源：评论

学校读者我要写书评

暂无评论

25th International conference on MultiMedia Modeling, MMM 2019

25th International Conference on MultiMedia Modeling, MMM 20...

引用

25th International conference on MultiMedia Modeling, MMM 2019

ISBN: (纸本)9783030057152

The proceedings contain 119 papers. The special focus in this conference is on MultiMedia Modeling. The topics include: From Movement to Events: Improving Soccer Match Annotations;multimodal Video Annotation for Retrieval and Discovery of Newsworthy Video in a News Verification Scenario;integration of exploration and Search: A Case Study of the M 3 Model;face Swapping for Solving Collateral Privacy Issues in Multimedia Analytics;exploring the Impact of Training data Bias on Automatic Generation of Video Captions;fashion Police: Towards Semantic Indexing of Clothing Information in Surveillance data;CNN-Based Non-contact Detection of Food Level in Bottles from RGB Images;personalized Recommendation of Photography Based on Deep Learning;two-Level Attention with Multi-task Learning for Facial Emotion Estimation;SCOD: Dynamical Spatial Constraints for Object Detection;user Interaction for visual Lifelog Retrieval in a Virtual Environment;query-by-Dancing: A Dance Music Retrieval System Based on Body-Motion Similarity;joint visual-Textual Sentiment analysis Based on Cross-Modality Attention Mechanism;deep Hashing with Triplet Labels and Unification Binary Code Selection for Fast Image Retrieval;incremental Training for Face Recognition;Character Prediction in TV Series via a Semantic Projection Network;a Test Collection for Interactive Lifelog Retrieval;SEPHLA: Challenges and Opportunities Within Environment - Personal Health Archives;Athens Urban Soundscape (ATHUS): A dataset for Urban Soundscape Quality Recognition;v3C – A Research Video Collection;STMP: Spatial Temporal Multi-level Proposal Network for Activity Detection;image Aesthetics Assessment Using Fully Convolutional Neural Networks;detecting Tampered Videos with Multimedia Forensics and Deep Learning;improving Robustness of Image Tampering Detection for Compression.

关键词：

来源：评论

学校读者我要写书评

暂无评论

25th International conference on MultiMedia Modeling, MMM 2019

25th International Conference on MultiMedia Modeling, MMM 20...

引用

25th International conference on MultiMedia Modeling, MMM 2019

ISBN: (纸本)9783030057091

关键词：

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：