检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Brenner, Simon Sablatnig, Robert Computer Vision Lab Institute of Visual Computing and Human-Centered technology TU Wien Vienna Austria

The research field concerned with the digital restoration of degraded written heritage lacks a quantitative metric for evaluating its results, which prevents the comparison of relevant methods on large datasets. Thus, we introduce a novel dataset of Subjective Assessments of Legibility in Ancient Manuscript Images (SALAMI) to serve as a ground truth for the development of quantitative evaluation metrics in the field of digital text restoration. This dataset consists of 250 images of 50 manuscript regions with corresponding spatial maps of mean legibility and uncertainty, which are based on a study conducted with 20 experts of philology and paleography. As this study is the first of its kind, the validity and reliability of its design and the results obtained are motivated statistically: we report a high intra- and inter-rater agreement and show that the bulk of variation in the scores is introduced by the images regions observed and not by controlled or uncontrolled properties of participants and test environments, thus concluding that the legibility scores measured are valid attributes of the underlying images. Copyright © 2021, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

A study on training data selection for object detection in nighttime traffic scenes

A study on training data selection for object detection in n...

引用

2020 Autonomous Vehicles and Machines Conference, AVM 2020

作者： Unger, Astrid Gelautz, Margrit Seitner, Florian Institute of Visual Computing and Human-Centered Technology TU Wien Vienna Austria Emotion3D GmbH Vienna Austria

With the growing demand for robust object detection algorithms in self-driving systems, it is important to consider the varying lighting and weather conditions in which cars operate all year round. The goal of our work is to gain a deeper understanding of meaningful strategies for selecting and merging training data from currently available databases and self-annotated videos in the context of automotive night scenes. We retrain an existing Convolutional Neural Network (YOLOv3) to study the influence of different training dataset combinations on the final object detection results in nighttime and low-visibility traffic scenes. Our evaluation shows that a suitable selection of training data from the GTSRD, VIPER, and BDD databases in conjunction with selfrecorded night scenes can achieve an mAP of 63,5% for ten object classes, which is an improvement of 16,7% when compared to the performance of the original YOLOv3 network on the same test set. © 2020, Society for Imaging Science and technology.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT LOADING and visualIZATION of MASSIVE FEATURE-RICH POINT CLOUDS without HIERARCHICAL ACCELERATION STRUCTURES 24

EFFICIENT LOADING and VISUALIZATION of MASSIVE FEATURE-RICH ...

引用

2020 24th ISPRS Congress - Technical Commission II

作者： Otepka, J. Mandlburger, G. Schütz, M. Pfeifer, N. Wimmer, M. TU Wien Department of Geodesy and Geoinformation Vienna Austria TU Wien Institute of Visual Computing and Human-Centered Technology Vienna Austria

Nowadays, point clouds are the standard product when capturing reality independent of scale and measurement technique. Especially, Dense Image Matching (DIM) and Laser Scanning (LS) are state of the art capturing methods for a great variety of applications producing detailed point clouds up to billions of points. In-depth analysis of such huge point clouds typically requires sophisticated spatial indexing structures to support potentially long-lasting automated non-interactive processing tasks like feature extraction, semantic labelling, surface generation, and the like. Nevertheless, a visual inspection of the point data is often necessary to obtain an impression of the scene, roughly check for completeness, quality, and outlier rates of the captured data in advance. Also intermediate processing results, containing additional per-point computed attributes, may require visual analyses to draw conclusions or to parameterize further processing. Over the last decades a variety of commercial, free, and open source viewers have been developed that can visualise huge point clouds and colorize them based on available attributes. However, they have either a poor loading and navigation performance, visualize only a subset of the points, or require the creation of spatial indexing structures in advance. In this paper, we evaluate a progressive method that is capable of rendering any point cloud that fits in GPU memory in real time without the need of time consuming hierarchical acceleration structure generation. In combination with our multi-threaded LAS and LAZ loaders, we achieve load performance of up to 20 million points per second, display points already while loading, support flexible switching between different attributes, and rendering up to one billion points with visually appealing navigation behaviour. Furthermore, loading times of different data sets for different open source and commercial software packages are analysed. © 2020 International Archives of the Photo

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Understanding Comparative Genomics Data visualization for Biodiversity Domain Through Persona-Based Interviews

Understanding Comparative Genomics Data Visualization for Bi...

引用

2024 IEEE International Conference on computing, ICOCO 2024

作者： Chan, Vei Siang Mohamed, Farhan Bin Salleh, Faezah Binti Mohd Iglesias, Andres Jamaludin, Najwa Ayuni Binti Mustafa Albakri, Ikmal Faiq Albakri Media and Game Innovation Center of Excellence Institute of Human Centered Engineering Universiti Teknologi Malaysia Johor Bahru Malaysia Department of Biosciences Faculty of Science Universiti Teknologi Malaysia Johor Bahru Malaysia Department of Applied Mathematics and Computational Sciences Universidad de Cantabria Santander Spain Pervasive Computing & Educational Technology Department of Media Interactive Fakulti Teknologi Maklumat dan Komunikasi Universiti Teknikal Malaysia Melaka Melaka Malaysia

ISBN: (纸本)9798331530303

Understanding the needs of genomic data visualization techniques is important to help bioinformaticians to perform their comparative analytical tasks effectively. DNA sequencing datasets consist of a long sequential string of nucleotide base pairs combination and are often involved in multiple sequences alignment for comparative analysis. Therefore, existing challenges include designing suitable visualization layout and the need of user-centered approach to ensure optimal user experience. Existing works also featured heavily on the qualitative evaluation of comparative visualization tools, such as use cases and case studies, which are difficult to quantify and conduct follow up evaluation for tool improvement. Hence, this paper aims to understand the needs of visualization tools in comparative genomic analysis to identify visualization tasks and visual design requirements. The methodology includes the creation of semi-structured interview based on personas template as guiding questions and the synthesis of thematic analysis results. These results presented the requirements of the visualization tasks for the biodiversity domain based on comparative targets. For future work, this research will design, develop, and validate the comparative visualization tool based on the discovered requirements. ©2024 IEEE.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Porphyrin Based-Optical Fiber Sensor for Pattern Recognition of Chlorides and Nitrates

SSRN

引用

SSRN 2024年

作者： Yadav, Mukti Kundu, Kaustubh Kaler, R.S. Kundu, Tapanendu Electronics and Communication Engineering Department Thapar Institute of Engineering and Technology Punjab Patiala147004 India Department of Human Centered Computing University Monash University Wellington Rd ClaytonVIC3800 Australia Physics Department Indian Institute of Technology Bombay Maharashtra Mumbai400076 India

The paper introduces a novel approach to develop a photonic device for chemical applications using an evanescent wave absorption technique-based optical fiber probe layered with a Tetraamine porphyrin (TAPP) monolayer exploiting the optical properties of TAPP. The interactions between the TAPP and nitrate and chloride ions in the solution phase were monitored and the changes in the absorption spectra of TAPP molecules were recorded. Distinct optical patterns emerge, and ion-dependent shifts in the Soret and Q-bands are analyzed for eight samples of nitrates and chlorides. Principal Component Analysis (PCA) is employed to discern ion groups based on the spectral pattern recognition. These fiber probes exhibit sensitivity to nitrate and chloride ions, with enhanced selectivity, robustness, and a rapid response time of 2-3 seconds. The study demonstrates the emergence of porphyrin-based optical fiber sensors as a useful sensor technology in environmental monitoring. © 2024, The Authors. All rights reserved.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

visual Analytics Meets Process Mining: Challenges and Opportunities

Visual Analytics Meets Process Mining: Challenges and Opport...

引用

International Conference on Process Mining (ICPM)

作者： Silvia Miksch Institute of Visual Computing and Human-Centered Technology Vienna University of Technology (TU Wien) Favoritenstraße 9-11/193-07 Vienna Austria

visual Analytics integrates the outstanding capabilities of humans in terms of visual information exploration with the enormous processing power of computers to form a powerful knowledge discovery environment. In other words, visual Analytics is the science of analytical reasoning facilitated by interactive interfaces and captures the information discovery process keeping the human in the loop. Process Mining aims to extract information and knowledge from event logs to discover, monitor, and improve processes in a variety of application domains. Such event data or traces of activities often possess data quality issues as well as exhibit unexpected behavior and complex relations. Consequently, before and during the implementation of interactive (automated or semi-automated) analysis methods, such as Process Mining algorithms, the analyst needs to explore, investigate, and understand the data at hand in order to decide which analysis methods might be appropriate. The combination of interactive visual data analyses and exploration with Process Mining algorithms makes complex information structures more comprehensible and facilitates new insights. In this talk, I will illustrate the concepts of visual Analytics, how visual Analytics combined with Process Mining techniques supports to extract more insights from complex event data, and elaborate about the challenges and opportunities for analyzing process data with visual Analytics methods. Various examples will illustrate what has been achieved so far and show possible future directions and challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WHEN DISCOURSE STALLS: MOVING PAST FIVE SEMANTIC STOPSIGNS ABOUT GENERATIVE AI IN DESIGN RESEARCH

arXiv

引用

arXiv 2025年

作者： van der Maden, Willem van der Burg, Vera Halperin, Brett A. Jääskeläinen, Petra Lindley, Joseph Lomas, Derek Merritt, Timothy HCI & Design Section ITU Copenhagen Copenhagen Denmark Designing Intelligence Lab Technical University Delft Delft Netherlands Human Centered Design & Engineering University of Washington SeattleWA United States EECS/HCT MID KTH Royal Institute of Technology Stockholm Sweden Lancaster University Lancaster United Kingdom TU Delft Delft Netherlands Dept. of Computer Science Human Centered Computing University Aalborg Denmark

This essay examines how Generative AI (GenAI) is rapidly transforming design practices and how discourse often falls into over-simplified narratives that impede meaningful research and practical progress. We identify and deconstruct five prevalent "semantic stopsigns"—reductive framings about GenAI in design that halt deeper inquiry and limit productive engagement. Reflecting upon two expert workshops at ACM conferences and semi-structured interviews with design practitioners, we analyze how these stopsigns manifest in research and practice. Our analysis develops mid-level knowledge that bridges theoretical discourse and practical implementation, helping designers and researchers interrogate common assumptions about GenAI in their own contexts. By recasting these stopsigns into more nuanced frameworks, we provide the design research community with practical approaches for thinking about and working with these emerging technologies. © 2025, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation

Lookahead Exploration with Neural Radiance Representation fo...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zihan Wang L. Xiangyang Jiahao Yang Yeqi Liu H. Junjie Ming Jiang Shuqiang Jiang Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Computer Science University of Wisconsin Madison WI USA Department of Biostatistics and Medical Informatics University of Wisconsin Madison WI USA Department of Human-centered Computing Indiana University Indianapolis IN USA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. At each navigation step, the agent selects from possible candidate locations and then makes the move. For better navigation planning, the lookahead exploration strategy aims to effectively evaluate the agent's next action by accurately anticipating the future environment of candidate locations. To this end, some existing works predict RGB images for future environments, while this strategy suffers from image distortion and high computational cost. To address these issues, we propose the pre-trained hierarchical neural radiance representation model (HNR) to produce multi-level semantic features for future environments, which are more robust and efficient than pixel-wise RGB reconstruction. Furthermore, with the predicted future environmental representations, our lookahead VLN model is able to construct the navigable future path tree and select the optimal path via efficient parallel evaluation. Extensive experiments on the VLN-CE datasets confirm the effectiveness of our method. The code is available at https://***/MrZihan/HNR-VLN

关键词： Solid modeling Three-dimensional displays Navigation Computational modeling Semantics Predictive models Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

MCCNet: Multi-Color Cascade Network with Weight Transfer for Single Image Depth Prediction on Outdoor Relief Images 25th

MCCNet: Multi-Color Cascade Network with Weight Transfer for...

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Frisky, Aufaclav Zatu Kusuma Putranto, Andi Zambanini, Sebastian Sablatnig, Robert Computer Vision Lab Institute of Visual Computing and Human-Centered Technology Faculty of Informatics TU Wien Vienna Austria Department of Computer Science and Electronics Faculty of Mathematics and Natural Sciences Universitas Gadjah Mada Yogyakarta Indonesia Department of Archaeology Faculty of Cultural Science Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9783030687861

Single image depth prediction is considerably difficult since depth cannot be estimated from pixel correspondences. Thus, prior knowledge, such as registered pixel and depth information from the user is required. Another problem rises when targeting a specific domain requirement as the number of freely available training datasets is limited. Due to color problem in relief images, we present a new outdoor Registered Relief Depth (RRD) Prambanan dataset, consisting of outdoor images of Prambanan temple relief with registered depth information supervised by archaeologists and computer scientists. In order to solve the problem, we also propose a new depth predictor, called Multi-Color Cascade Network (MCCNet), with weight transfer. Applied on the new RRD Prambanan dataset, our method performs better in different materials than the baseline with 2.53 mm RMSE. In the NYU Depth V2 dataset, our method’s performance is better than the baselines and in line with other state-of-the-art works. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Cost Volume Refinement for Depth Prediction

Cost Volume Refinement for Depth Prediction

引用

International Conference on Pattern Recognition

作者： João L. Cardoso Nuno Gonçalves Michael Wimmer Institute of Visual Computing and Human-Centered Technology TU Wien Vienna Austria Institute of Systems and Robotics University of Coimbra Portuguese Mint and Official Printing Office Lisbon

Light-field cameras are becoming more popular in the consumer market. Their data redundancy allows, in theory, to accurately refocus images after acquisition and to predict the depth of each point visible from the camera. Combined, these two features allow for the generation of full-focus images, which is impossible in traditional cameras. Multiple methods for depth prediction from light fields (or stereo) have been proposed over the years. A large subset of these methods relies on cost-volume estimates - 3D objects where each layer represents a heuristic of whether each point in the image is at a certain distance from the camera. Generally, this volume is used to regress a depth map, which is then refined for better results. In this paper, we argue that refining the cost volumes is superior to refining the depth maps in order to further increase the accuracy of depth predictions. We propose a set of cost-volume refinement algorithms and show their effectiveness.

关键词： Three-dimensional displays Smoothing methods Volume measurement Refining Redundancy Pipelines Cameras

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：