检索结果-内蒙古大学图书馆

Footwear segmentation and recommendation supported by deep learning: an exploratory proposal

Procedia computer Science 2023年 219卷 724-735页

作者： João Oliveira Rui Gomes Dibet Gonzalez Nuno Sousa Somayeh Shahrabadi Miguel Guevara Maria José Ferreira Pedro Alves Emanuel Peres Luís Magalhães Telmo Adão CCG: Centre for Computer Graphics Campus de Azurém Edifício 14 4800-058 Guimarães Portugal Martins Sarmento High School Alameda Prof. Abel Salazar 4810-247 Guimarães Portugal Technology College Polytechnic Institute of Setúbal Campos do IPS Estefanilha 2914-761 Setúbal Portugal. Portuguese Footwear Technological Centre (CTCP) Rua de Fundões - Devesa Velha 3700-121 S. João da Madeira Portugal. Kyaia - Soluções Informáticas Lda Rua Abílio Lopes Das Neves 593 4805-214 - Guimarães. Portugal CITAB University of Trás-os-Montes e Alto Douro 5000-801 Vila Real Portugal Algoritmi Centre University of Minho Campus de Azurém Av. da Universidade 4800-058 Guimarães Portugal.

The management of an online footwear retail store - also known as marketplace - usually involves activities that directly or indirectly end up to interface with customers, wherein communication efficiency and effectiveness is crucially relevant. Critical factors concerning entities developing remote business in these areas or similar include: (i) production of appealing catalogues and (ii) digital tools to shorten the distance between customers and marketplaces. The former requires using specific third parties - often technically complex - to arrange and prepare photographic entries acquired in studio-like environments. This can delay the diffusion of products supply that may result in financial losses. The latter prevents the retailer of reaching critical mass at a higher potential. Considering such issues, this paper proposes a couple of modules for footwear marketplaces, powered by deep learning: one to segment shoes as a fully automatic background removal tool for easing and quickening catalogue creation activities in a back-office perspective; and another to provide visual search services that allow a customer to submit photographs of footwear of interest to obtain recommendations of similar products directly retrieved from online retail databases, establishing another digital bridge with potential buyers. Preliminary implementation and pilot tests point out Mask-RCNN as a promising approach for shoes segmentation. The same applies to ResNet101 and Xception, but for shoes recommendation, based on multi-label classification.

关键词： ootwear Marketplace Digital Transformation Deep Learning Convolutional Neural Network Segmentation Multilabel Classification

来源：评论

学校读者我要写书评

暂无评论

Elastic flattening of painted pottery surfaces

Elastic flattening of painted pottery surfaces

引用

2018 Eurographics Workshop on graphics and Cultural Heritage, GCH 2018

作者： Preiner, Reinhold Karl, Stephan Baye, Paul Schreck, Tobias Graz University of Technology Institute of Computer Graphics and Knowledge Visualization Austria University of Graz Department of Archaeology Austria

ISBN: (纸本)9783038680574

Generating flat images from paintings on curved surfaces is an important task in Archaeological analysis of ancient pottery. It allows comparing styles and painting techniques, e.g, for style and workshop attribution, and serves as basis for domain publications which typically use 2d images. To obtain such flat images from scanned textured 3d models of the pottery objects, current practice is to perform so-called rollouts using approximating shape primitives like cones or spheres, onto which the mesh surfaces are projected. While this process provides in intuitive deformation metaphor for the users, it naturally introduces unwanted distortions in the mapping of the surface, especially for vessels with high-curvature profiles. In this work, we perform an elastic flattening of these projected meshes, where stretch energy is minimized by simulating a physical relaxation process on a damped elastic spring model. We propose an intuitive contraction-directed physical setup which allows for an efficient relaxation while ensuring a controlled convergence. Our work has shown to produce images of significantly improved suitability for domain experts' tasks like interpretation, documentation and attribution of ancient pottery. © 2018 GCH 2018 - Eurographics Workshop on graphics and Cultural Heritage. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

GP2C: Geometric projection parameter consensus for joint 3D pose and focal length estimation in the wild

arXiv

引用

arXiv 2019年

作者： Grabner, Alexander Roth, Peter M. Lepetit, Vincent Institute of Computer Graphics and Vision Graz University of Technology Austria Laboratoire Bordelais de Recherche en Informatique University of Bordeaux France

We present a joint 3D pose and focal length estimation approach for object categories in the wild. In contrast to previous methods that predict 3D poses independently of the focal length or assume a constant focal length, we explicitly estimate and integrate the focal length into the 3D pose estimation. For this purpose, we combine deep learning techniques and geometric algorithms in a two-stage approach: First, we estimate an initial focal length and establish 2D- 3D correspondences from a single RGB image using a deep network. Second, we recover 3D poses and refine the focal length by minimizing the reprojection error of the predicted correspondences. In this way, we exploit the geometric prior given by the focal length for 3D pose estimation. This results in two advantages: First, we achieve significantly improved 3D translation and 3D pose accuracy compared to existing methods. Second, our approach finds a geometric consensus between the individual projection parameters, which is required for precise 2D-3D alignment. We evaluate our proposed approach on three challenging real-world datasets (Pix3D, Comp, and Stanford) with different object categories and significantly outperform the state-of-the-art by up to 20% absolute in multiple different metrics. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Performing arithmetic using a neural network trained on digit permutation pairs

arXiv

引用

arXiv 2019年

作者： Bloice, Marcus D. Roth, Peter M. Holzinger, Andreas Institute for Medical Informatics Statistics Documentation Medical University Graz Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

In this paper a neural network is trained to perform simple arithmetic using images of concatenated handwritten digit pairs. A convolutional neural network was trained with images consisting of two side-by-side handwritten digits, where the image’s label is the summation of the two digits contained in the combined image. Crucially, the network was tested on permutation pairs that were not present during training in an effort to see if the network could learn the task of addition, as opposed to simply mapping images to labels. A dataset was generated for all possible permutation pairs of length 2 for the digits 0–9 using MNIST as a basis for the images, with one thousand samples generated for each permutation pair. For testing the network, samples generated from previously unseen permutation pairs were fed into the trained network, and its predictions measured. Results were encouraging, with the network achieving an accuracy of over 90% on some permutation train/test splits. This suggests that the network learned at first digit recognition, and subsequently the further task of addition based on the two recognised digits. As far as the authors are aware, no previous work has concentrated on learning a mathematical operation in this way. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization

arXiv

引用

arXiv 2019年

作者： Payer, Christian Štern, Darko Bischof, Horst Urschler, Martin Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Ludwig Boltzmann Institute for Clinical Forensic Imaging Graz Austria

In many medical image analysis applications, often only a limited amount of training data is available, which makes training of convolutional neural networks (CNNs) challenging. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the spatial configuration of landmarks. In our experimental evaluation, we show that the proposed SCN outperforms related methods in terms of landmark localization error on size-limited datasets. Keywords: anatomical landmarks, localization, heatmap regression, spatial configuration Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Smart hypothesis generation for efficient and robust room layout estimation

arXiv

引用

arXiv 2019年

作者： Hirzer, Martin Roth, Peter M. Lepetit, Vincent Institute of Computer Graphics and Vision Graz University of Technology Austria Laboratoire Bordelais de Recherche en Informatique University of Bordeaux France

We propose a novel method to efficiently estimate the spatial layout of a room from a single monocular RGB image. As existing approaches based on low-level feature extraction, followed by a vanishing point estimation are very slow and often unreliable in realistic scenarios, we build on semantic segmentation of the input image. To obtain better segmentations, we introduce a robust, accurate and very efficient hypothesize-and-test scheme. The key idea is to use three segmentation hypotheses, each based on a different number of visible walls. For each hypothesis, we predict the image locations of the room corners and select the hypothesis for which the layout estimated from the room corners is consistent with the segmentation. We demonstrate the efficiency and robustness of our method on three challenging benchmark datasets, where we significantly outperform the state-of-the-art. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Location field descriptors: Single image 3D model retrieval in the wild

arXiv

引用

arXiv 2019年

We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images to an embedding space, we establish a common low-level representation in the form of location fields from which we compute pose invariant 3D shape descriptors. Location fields encode correspondences between 2D pixels and 3D surface coordinates and, thus, explicitly capture 3D shape and 3D pose information without appearance variations which are irrelevant for the task. This early fusion of 3D models and RGB images results in three main advantages: First, the bottleneck location field prediction acts as a regularizer during training. Second, major parts of the system benefit from training on a virtually infinite amount of synthetic data. Finally, the predicted location fields are visually interpretable and unblackbox the system. We evaluate our proposed approach on three challenging real-world datasets (Pix3D, Comp, and Stanford) with different object categories and significantly outperform the state-of-the-art by up to 20% absolute in multiple 3D retrieval metrics. Copyright © 2019, The Authors. All rights reserved.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Improved Upper Bounds on the Growth Constants of Polyominoes and Polycubes

arXiv

引用

arXiv 2019年

作者： Barequet, Gill Shalah, Mira Center for Graphics Geometric Computing Computer Science Department Technion—Israel Institute of Technology Haifa3200003 Israel Computer Science Department Stanford University CA United States

A d-dimensional polycube is a facet-connected set of cells (cubes) on the d-dimensional cubical lattice Zd. Let Ad(n) denote the number of d-dimensional polycubes (distinct up to translations) with n cubes, and λd denote the limit of the ratio Ad(n+1)/Ad(n) as n → ∞. The exact value of λd is still unknown rigorously for any dimension d ≥ 2;the asymptotics of λd, as d → ∞, also remained elusive as of today. In this paper, we revisit and extend the approach presented by Klarner and Rivest in 1973 to bound A2(n) from above. Our contributions are: • Using available computing power, we prove that λ2 ≤ 4.5252. This is the first improvement of the upper bound on λ2 in almost half a century;• We prove that λd ≤ (2d−2)e+o(1) for any value of d ≥ 2, using a novel construction of a rational generating function which dominates that of the sequence (Ad(n));• For d = 3, this provides a subtantial improvement of the upper bound on λ3 from 12.2071 to 9.8073;• However, we implement an iterative process in three dimensions, which improves further the upper bound on λ3 to 9.3835;Copyright © 2019, The Authors. All rights reserved.

关键词： Rational functions

来源：评论

学校读者我要写书评

暂无评论

Casting geometric constraints in semantic segmentation as semi-supervised learning

arXiv

引用

arXiv 2019年

作者： Stekovic, Sinisa Fraundorfer, Friedrich Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Université Paris-Est École des Ponts ParisTech Paris France

We propose a simple yet effective method to learn to segment new indoor scenes from video frames: State-ofthe- art methods trained on one dataset, even as large as the SUNRGB-D dataset, can perform poorly when applied to images that are not part of the dataset, because of the dataset bias, a common phenomenon in computer vision. To make semantic segmentation more useful in practice, one can exploit geometric constraints. Our main contribution is to show that these constraints can be cast conveniently as semi-supervised terms, which enforce the fact that the same class should be predicted for the projections of the same 3D location in different images. This is interesting as we can exploit general existing techniques developed for semi-supervised learning to efficiently incorporate the constraints. We show that this approach can efficiently and accurately learn to segment target sequences of ScanNet and our own target sequences using only annotations from SUNRGB-D, and geometric relations between the video frames of target sequences. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

AI-based Aortic Vessel Tree Segmentation for Cardiovascular Diseases Treatment: Status Quo

arXiv

引用

arXiv 2021年

作者： Jin, Yuan Pepe, Antonio Li, Jianning Gsaxner, Christina Zhao, Fen-Hua Pomykala, Kelsey L. Kleesiek, Jens Frangi, Alejandro F. Egger, Jan Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16 Graz8010 Austria Computer Algorithms for Medicine Laboratory Graz Austria Research Center for Connected Healthcare Big Data ZhejiangLab Zhejiang Hangzhou311121 China Girardetstraße 2 Essen45131 Germany Department of Radiology Affiliated Dongyang Hospital of Wenzhou Medical University Zhejiang Dongyang322100 China Hufelandstraße 55 Essen45147 Germany Partner Site Essen Hufelandstraße 55 Essen45147 Germany School of Computing University of Leeds Leeds United Kingdom School of Medicine University of Leeds Leeds United Kingdom

The aortic vessel tree is composed of the aorta and its branching arteries, and plays a key role in supplying the whole body with blood. Aortic diseases, like aneurysms or dissections, can lead to an aortic rupture, whose treatment with open surgery is highly risky. Therefore, patients commonly undergo drug treatment under constant monitoring, which requires regular inspections of the vessels through imaging. The standard imaging modality for diagnosis and monitoring is computed tomography (CT), which can provide a detailed picture of the aorta and its branching vessels if completed with a contrast agent, called CT angiography (CTA). Optimally, the whole aortic vessel tree geometry from consecutive CTAs is overlaid and compared. This allows not only detection of changes in the aorta, but also of its branches, caused by the primary pathology or newly developed. When performed manually, this reconstruction requires slice by slice contouring, which could easily take a whole day for a single aortic vessel tree, and is therefore not feasible in clinical practice. Automatic or semi-automatic vessel tree segmentation algorithms, however, can complete this task in a fraction of the manual execution time and run in parallel to the clinical routine of the clinicians. In this paper, we systematically review computing techniques for the automatic and semi-automatic segmentation of the aortic vessel tree. The review concludes with an in-depth discussion on how close these state-of-the-art approaches are to an application in clinical practice and how active this research field is, taking into account the number of publications, datasets and challenges. Copyright © 2021, The Authors. All rights reserved.

关键词： Diseases

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：