检索结果-内蒙古大学图书馆

A Tutorial on Dataset Creation for Sensor-based Human Activity recognition

A Tutorial on Dataset Creation for Sensor-based Human Activi...

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

作者： Reining, Christopher Nair, Nilah Ravi Niemann, Friedrich Rueda, Fernando Moya Fink, Gernot A. Chair of Material Handling and Warehousing Germany Pattern Recognition in Embedded Systems Group Germany

ISBN: (纸本)9781665453813

Well-documented, large and diverse datasets are important to facilitate supervised and transferable deep learning methods for human activity recognition. The past years have seen the machine learning community strive to achieve best practices in dataset creation for various applications. This contribution is the first to provide a comprehensive tutorial on data creation for sensor-based human activity recognition with firsthand instructions. We introduce the dataset creation process consisting of three phases as a guideline for the community. Each phase explains common challenges researchers may face and suggest solutions. A case study demonstrates how the framework can be used by researchers for holistically planning and critically reflecting their approach of dataset creation. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Time-Series Person and Soft-Biometric Identification 26th

Multi-Channel Time-Series Person and Soft-Biometric Identif...

引用

26th International Conference on pattern recognition, ICPR 2022

作者： Nair, Nilah Ravi Moya Rueda, Fernando Reining, Christopher Fink, Gernot A. Chair of Material Handling and Warehousing TU Dortmund University Dortmund Germany Pattern Recognition in Embedded Systems Group TU Dortmund University Dortmund Germany

ISBN: (纸本)9783031376597

Multi-channel time-series datasets are popular in the context of human activity recognition (HAR). On-body device (OBD) recordings of human movements are often preferred for HAR applications not only for their reliability but as an approach for identity protection, e.g., in industrial settings. Contradictory, the gait activity is a biometric, as the cyclic movement is distinctive and collectable. In addition, the gait cycle has proven to contain soft-biometric information of human groups, such as age and height. Though general human movements have not been considered a biometric, they might contain identity information. This work investigates person and soft-biometrics identification from OBD recordings of humans performing different activities using deep architectures. Furthermore, we propose the use of attribute representation for soft-biometric identification. We evaluate the method on four datasets of multi-channel time-series HAR, measuring the performance of a person and soft-biometrics identification and its relation concerning performed activities. We find that person identification is not limited to gait activity. The impact of activities on the identification performance was found to be training and dataset specific. Soft-biometric based attribute representation shows promising results and emphasis the necessity of larger datasets. © 2023, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Tutorial on Dataset Creation for Sensor-based Human Activity recognition

A Tutorial on Dataset Creation for Sensor-based Human Activi...

引用

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Christopher Reining Nilah Ravi Nair Friedrich Niemann Fernando Moya Rueda Gernot A. Fink Chair of Material Handling and Warehousing Pattern Recognition in Embedded Systems Group

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Image Unfolding: Flattening Sparse Anatomical Structures using Neural Fields

arXiv

引用

arXiv 2024年

作者： Rist, Leonhard Stephan, Pluvio Maul, Noah Vorberg, Linda Ditt, Hendrik Sühling, Michael Maier, Andreas Egger, Bernhard Taubmann, Oliver Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Computed Tomography Siemens Healthineers AG Forchheim Germany Chair of Visual Computing Friedrich-Alexander-Universität Erlangen-Nürnberg Germany

Tomographic imaging reveals internal structures of 3D objects and is crucial for medical diagnoses. Visualizing the morphology and appearance of non-planar sparse anatomical structures that extend over multiple 2D slices in tomographic volumes is inherently difficult but valuable for decision-making and reporting. Hence, various organ-specific unfolding techniques exist to map their densely sampled 3D surfaces to a distortion-minimized 2D representation. However, there is no versatile framework to flatten complex sparse structures including vascular, duct or bone systems. We deploy a neural field to fit the transformation of the anatomy of interest to a 2D overview image. We further propose distortion regularization strategies and combine geometric with intensity-based loss formulations to also display non-annotated and auxiliary targets. In addition to improved versatility, our unfolding technique outperforms mesh-based baselines for sparse structures w.r.t. peak distortion and our regularization scheme yields smoother transformations compared to Jacobian formulations from neural field-based image registration. Copyright © 2024, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Dataset Bias in Human Activity recognition

arXiv

引用

arXiv 2023年

作者： Nair, Nilah Ravi Schmid, Lena Rueda, Fernando Moya Pauly, Markus Fink, Gernot A. Reining, Christopher Chair of Material Handling and Warehousing TU Dortmund University Germany Department of Statistics TU Dortmund University Germany Research Center Trustworthy Data Science and Security UA Ruhr Germany Pattern Recognition in Embedded Systems Group TU Dortmund University Germany

When creating multi-channel time-series datasets for Human Activity recognition (HAR), researchers are faced with the issue of subject selection criteria. It is unknown what physical characteristics and/or soft-biometrics, such as age, height, and weight, need to be taken into account to train a classifier to achieve robustness towards heterogeneous populations in the training and testing data. This contribution statistically curates the training data to assess to what degree the physical characteristics of humans influence HAR performance. We evaluate the performance of a state-of-the-art convolutional neural network on two HAR datasets that vary in the sensors, activities, and recording for time-series HAR. The training data is intentionally biased with respect to human characteristics to determine the features that impact motion behaviour. The evaluations brought forth the impact of the subjects’ characteristics on HAR. Thus, providing insights regarding the robustness of the classifier with respect to heterogeneous populations. The study is a step forward in the direction of fair and trustworthy artificial intelligence by attempting to quantify representation bias in multi-channel time series HAR data. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Annotation Procedures for Multi-channel Time Series HAR Dataset

Benchmarking Annotation Procedures for Multi-channel Time Se...

引用

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Hülya Avsar Erik Altermann Christopher Reining Fernando Moya Rueda Gernot A. Fink Michael ten Hompel Chair of Materials Handling and Warehousing TU Dortmund University Dortmund Pattern Recognition in Embedded Systems Group TU Dortmund University Dortmund

This contribution evaluates semi-automated annotation for generating high-quality data for multi-channel time series Human Activity recognition. For this purpose, time series data that consists of Optical Motion Capturing and inertial measurements from on-body devices for industrial deployment is created, annotated, and revised by four individuals. The semi-automated annotation consists of predictions from a temporal convolutional neural-network, and manual revisions for generating high-quality and fine-grained annotations for Human Activity recognition. This annotation approach reduces the annotation effort keeping similar quality as compared to manual annotation.

关键词： Pervasive computing Annotations Conferences Time series analysis Manuals Optical variables measurement Activity recognition

来源：评论

学校读者我要写书评

暂无评论

Task-specific View Selection for 2D X-ray Inspection of Large Objects with Robotic CT Systems

e-Journal of Nondestructive Testing

引用

e-Journal of Nondestructive Testing 2024年第3期29卷

作者： Müller, Jonas Herl, Gabriel Schromm, Thomas Jahnke, Peter Maier, Andreas FAU—Pattern Recognition Lab Martensstr. 2 Erlangen91058 Germany BMW AG—Technologie Werkstoff-und Verfahrensanalytik Hufelandstraße 5 München80937 Germany THD—Deggendorf Institute of Technology Dieter-Görlitz-Platz 1 Deggendorf94469 Germany TUM—Chair of Non-destructive Testing Franz-Langinger-Straße 10 München81245 Germany

Computed tomography (CT) is a powerful method for non-destructive testing (NDT) in various industrial testing scenarios. Conventional laboratory based CT systems require that the object that is to be inspected can be placed between the X-ray source and the detector in the inspection cabinet and that the areas to be inspected are easily accessible to the X-ray tube and detector. To surmount the constraints imposed by such setups, robotic CT systems have gained traction in the recent past. This approach facilitates the preemptive planning of robotic paths, thereby guaranteeing the determination of collision-free trajectories, the optimal alignment of imaging perspectives, and eventually enabling 2D stitching of larger samples such as automotive body parts. Addressing the intricacies of robot positioning, which involves considerations of accessibility and the scanned object absorption characteristics, we introduce a refined inspection planning workflow tailored for 2D X-ray imaging task. Utilizing available resources, such as CAD models or the object’s boundary geometry, in conjunction with task-specific relevance criteria, we ascertain the most advantageous viewpoints for 2D inspection utilizing a CT robotic system. This methodology enables proactive path planning for the robot, ensuring the establishment of collision-free routes and the precise calibration of imaging angles for optimal inspection outcomes. © 2024, NDT. net GmbH and Co. KG. All rights reserved.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

One-Shot Object Detection in Heterogeneous Artwork Datasets

One-Shot Object Detection in Heterogeneous Artwork Datasets

引用

Workshops on Image Processing Theory, Tools and Applications, IPTA

作者： Prathmesh Madhu Anna Meyer Mathias Zinnen Lara Mü hrenberg Dirk Suckow Torsten Bendschus Corinna Reinhardt Peter Bell Ute Verstegen Ronak Kosti Andreas Maier Vincent Christlein Pattern Recognition Lab Friedrich-Alexander-Universitat Erlangen-N&#x00FC rnberg Germany Chair of Christian Archaeology Friedrich-Alexander-Universitat Erlangen-N&#x00FC Institute of Art History Friedrich-Alexander-Universitat Erlangen-N&#x00FC Chair of Classical Archaeology Friedrich-Alexander-Universitat Erlangen-N&#x00FC German and Art Studies Philipps University Marburg Germany

Christian archeologists face many challenges in understanding visual narration through artwork images. This understanding is essential to access underlying semantic in-formation. Therefore, narrative elements (objects) need to be labeled, compared, and contextualized by experts, which takes an enormous amount of time and effort. Our work aims to reduce labeling costs by using one-shot object detection to generate a labeled database from unannotated images. Novel object categories can be defined broadly and annotated using visual examples of narrative elements without training exclusively for such objects. In this work, we propose two ways of using contextual information as data augmentation to improve the detection performance. Furthermore, we introduce a multi-relation detector to our framework, which extracts global, local, and patch-based relations of the image. Additionally, we evaluate the use of contrastive learning. We use data from Christian archeology (CHA) and art history - IconArt-v2 (IA). Our context encoding approach improves the typical fine-tuning approach in terms of mean average precision (mAP) by about 3.5 % (4 %) at 0.25 intersection over union (IoU) for UnSeen categories, and 6 % (1.5 %) for Seen categories in CHA (IA). To the best of our knowledge, our work is the first to explore few shot object detection on heterogeneous artistic data by investigating evaluation methods and data augmentation strategies. We will release the code and models after acceptance of the work.

关键词： Training Adaptation models Visualization Archeology Art Semantics Object detection

来源：评论

学校读者我要写书评

暂无评论

Nuremberg Letterbooks: A Multi-Transcriptional Dataset of Early 15th Century Manuscripts for Document Analysis

arXiv

引用

arXiv 2024年

作者： Mayr, Martin Krenz, Julian Neumeier, Katharina Bub, Anna Bürcky, Simon Brolich, Nina Herbers, Klaus Habermann, Mechthild Fleischmann, Peter Maier, Andreas Christlein, Vincent Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen91058 Germany Senior Fellow of Medieval History Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen91054 Germany Department of German Linguistics Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen91054 Germany Chair of Regional History of Bavaria and Franconia Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen91054 Germany

Most datasets in the field of document analysis utilize highly standardized labels, which, while simplifying specific tasks, often produce outputs that are not directly applicable to humanities research. In contrast, the Nuremberg Letterbooks dataset, which comprises historical documents from the early 15th century, addresses this gap by providing multiple types of transcriptions and accompanying metadata. This approach allows for developing methods that are more closely aligned with the needs of the humanities. The dataset includes 4 books containing 1711 labeled pages written by 10 scribes. Three types of transcriptions are provided for handwritten text recognition: Basic, diplomatic, and regularized. For the latter two, versions with and without expanded abbreviations are also available. A combination of letter ID and writer ID supports writer identification due to changing writers within pages. In the technical validation, we established baselines for various tasks, demonstrating data consistency and providing benchmarks for future research to build upon. Copyright © 2024, The Authors. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Self-attention transfer networks for speech emotion recognition

引用

Virtual Reality & Intelligent Hardware 2021年第1期3卷 43-54页

作者： Ziping ZHAO Keru Wang Zhongtian BAO Zixing ZHANG Nicholas CUMMINS Shihuang SUN Haishuai WANG Jianhua TAO Björn WSCHULLER College of Computer and Information Engineering Tianjin Normal UniversityTianjin 300387China GLAM-Group on Language Audio&MusicImperial College LondonSW72AZUK Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg86159Germany Department of Biostatistics and Health Informatics IoPPNKing's College LondonLondonSE58AFUK Department of Computer Science and Engineering Fairfield University 06824USA National Laboratory of Pattern Recognition CASIABeijing 100190China

Background A crucial element of human-machine interaction,the automatic detection of emotional states from human speech has long been regarded as a challenging task for machine learning *** vital challenge in speech emotion recognition(SER)is learning robust and discriminative representations from *** machine learning methods have been widely applied in SER research,the inadequate amount of available annotated data has become a bottleneck impeding the extended application of such techniques(e.g.,deep neural networks).To address this issue,we present a deep learning method that combines knowledge transfer and self-attention for SER ***,we apply the log-Mel spectrogram with deltas and delta-deltas as ***,given that emotions are time dependent,we apply temporal convolutional neural networks to model the variations in *** further introduce an attention transfer mechanism,which is based on a self-attention algorithm to learn long-term *** self-attention transfer network(SATN)in our proposed approach takes advantage of attention transfer to learn attention from speech recognition,followed by transferring this knowledge into *** evaluation built on Interactive Emotional Dyadic Motion Capture(IEMOCAP)dataset demonstrates the effectiveness of the proposed model.

关键词： Speech emotion recognition Attention transfer Self-attention Temporal convolutional neural networks(TCNs)

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：