检索结果-内蒙古大学图书馆

A Baseline Approach for AutoImplant: the MICCAI 2020 Cranial Implant Design Challenge?

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Jianning Pepe, Antonio Gsaxner, Christina von Campe, Gord Egger, Jan Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Graz Austria Department of Oral and Maxillofacial Surgery Medical University of Graz Graz Austria Department of Neurosurgery Medical University of Graz Graz Austria

In this study, we present a baseline approach for AutoImplant (https://***/) – the cranial implant design challenge, which, as suggested by the organizers, can be formulated as a volumetric shape learning task. In this task, the defective skull, the complete skull and the cranial implant are represented as binary voxel grids. To accomplish this task, the implant can be either reconstructed directly from the defective skull or obtained by taking the difference between a defective skull and a complete skull. In the latter case, a complete skull has to be reconstructed given a defective skull, which defines a volumetric shape completion problem. Our baseline approach for this task is based on the former formulation, i.e., a deep neural network is trained to predict the implants directly from the defective skulls. The approach generates high-quality implants in two steps: First, an encoder-decoder network learns a coarse representation of the implant from down-sampled, defective skulls;The coarse implant is only used to generate the bounding box of the defected region in the original high-resolution skull. Second, another encoder-decoder network is trained to generate a fine implant from the bounded area. On the test set, the proposed approach achieves an average dice similarity score (DSC) of 0.8555 and Hausdorff distance (HD) of 5.1825 mm. The code is publicly available at https://***/Jianningli/autoimplant. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

SHREC'19 track: Extended 2D scene image-based 3D scene retrieval 12

学校读者我要写书评

暂无评论

SHREC'19 track: Extended 2D scene image-based 3D scene retri...

12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for computer graphics, EG 2019

作者： Abdul-Rashid, Hameed Yuan, Juefei Li, Bo Lu, Yijuan Schreck, Tobias Bui, Ngoc-Minh Do, Trong-Le Holenderski, Mike Jarnikov, Dmitri Le, Khiem T. Menkovski, Vlado Nguyen, Khac-Tuan Nguyen, Thanh-An Nguyen, Vinh-Tiep Ninh, Tu V. Rey, Perez Tran, Minh-Triet Wang, Tianyang School of Computer Science and Computer Engineering University of Southern Mississippi United States Department of Computer Science Texas State University United States Institue of Computer Graphics and Knowledge Visualization Graz University of Technology Austria Faculty of Information Technology Vietnam National University Ho Chi Minh City Viet Nam Software Engineering Lab Vietnam National University Ho Chi Minh City Viet Nam Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands University of Information Technology Vietnam National University Ho Chi Minh City Viet Nam Department of Computer Science and Information Technology Austin Peay State University United States

ISBN: (纸本)9783038680772

In the months following our SHREC 2018 - 2D Scene Image-Based 3D Scene Retrieval (SceneIBR2018) track, we have extended the number of the scene categories from the initial 10 classes in the SceneIBR2018 benchmark to 30 classes, resulting in a new benchmark SceneIBR2019 which has 30,000 scene images and 3,000 3D scene models. For that reason, we seek to further evaluate the performance of existing and new 2D scene image-based 3D scene retrieval algorithms using this extended and more comprehensive new benchmark. Three groups from the Netherlands, The United States and Vietnam participated and collectively submitted eight runs. This report documents the evaluation of each method based on seven performance metrics, offers an in-depth discussion as well as analysis on the methods employed and discusses future directions that have the potential to address this task. Again, deep learning techniques have demonstrated notable performance in terms of both accuracy and scalability when applied to this exigent retrieval task. To further enrich the current state of 3D scene understanding and retrieval, our evaluation toolkit, all participating methods' results and the comprehensive 2D/3D benchmark have all been made publicly available. © 2019 The Author(s)

关键词： Three dimensional computer graphics

Image morphing in deep feature spaces: Theory and applications

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Effland, Alexander Kobler, Erich Pock, Thomas Rajković, Marko Rumpf, Martin Institute of Computer Graphics and Vision Graz University of Technology Institute for Numerical Simulation University of Bonn

This paper combines image metamorphosis with deep features. To this end, images are considered as maps into a high-dimensional feature space and a structure-sensitive, anisotropic flow regularization is incorporated in the metamorphosis model proposed by Miller, Trouvé, Younes and coworkers [MY01, TY05b]. For this model a variational time discretization of the Riemannian path energy is presented and the existence of discrete geodesic paths minimizing this energy is demonstrated. Furthermore, convergence of discrete geodesic paths to geodesic paths in the time continuous model is investigated. The spatial discretization is based on a finite difference approximation in image space and a stable spline approximation in deformation space, the fully discrete model is optimized using the iPALM algorithm. Numerical experiments indicate that the incorporation of semantic deep features is superior to intensity-based *** Codes 65D18, 37L65, 49M25, 53C22, 65L20 Copyright © 2019, The Authors. All rights reserved.

关键词： Finite difference method

Generative Adversarial Network with Policy Gradient for Text Summarization

学校读者我要写书评

暂无评论

Generative Adversarial Network with Policy Gradient for Text...

International Conference on Semantic Computing

作者： Banafsheh Rekabdar Christos Mousas Bidyut Gupta Department of Computer Science Southern Illinois University Carbondale IL Computer Graphics Technology Purdue University West Lafayette IN

Abstractive text summarization is the task of generating meaningful summary from a given document (short or long). This is a very challenging task for longer documents, since they suffer from repetitions (redundancy) when the given document is long and the generated summary should contain multi-sentences. In this paper we present an approach for applying generative adversarial networks in abstractive text summarization tasks with a novel time-decay attention mechanism. The data generator is modeled as a stochastic policy in reinforcement learning. The generator's goal is to generate summaries which are difficult to be discriminated from real summaries. The discriminator aims to estimate the probability that a summary came from the training data rather than the generator to guide the training of the generative model. This framework corresponds to a minimax two-player game. Qualitatively and quantitatively experimental results (human evaluations and ROUGE scores) show that our model can generate more relevant, less repetitive, grammatically correct, preferable by humans and is promising in solving the abstractive text summarization task.

关键词： Generators Decoding Task analysis Generative adversarial networks Reinforcement learning Training Mathematical model

Machine-learning guided differentiation between photoplethysmography waveforms of supraventricular and ventricular origin

学校读者我要写书评

暂无评论

EP Europace 2024年第SUPPLEMENT_1期26卷

作者： Manninger, M Lercher, I Hermans, A N L Isaksen, J L Prassl, A J Zirlik, A Vernooy, K Chaldoupi, S M Luermans, J Ter Bekke, R M A Kanters, J K Plank, G Scherr, D Pock, T Linz, D Medical University of Graz Department of Cardiology Graz Austria Graz University of Technology Institute of Computer Graphics and Vision Graz Austria Maastricht University Medical Centre (MUMC) Department of Cardiology Maastricht Netherlands (The) University of Copenhagen Department of Biomedical Sciences Faculty of Health and Medical Sciences Copenhagen Denmark Medical University of Graz Gottfried Schatz Research Centre Division of Biophysics Graz Austria

FakeNews: GAN-based generation of realistic 3D volumetric data A systematic review and taxonomy

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ferreira, André Li, Jianning Alves, Victor Pomykala, Kelsey L. Kleesiek, Jens Egger, Jan Center Algoritmi University of Minho Braga Portugal Computer Algorithms for Medicine Laboratory Graz Austria University Medicine Essen Girardetstraße 2 Essen45131 Germany University Medicine Essen Hufelandstraße 55 Essen45147 Germany Partner Site Essen Hufelandstraße 55 Essen45147 Germany Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16 Graz8010 Austria TU Dortmund University Department of Physics Otto-Hahn-Straße 4 Dortmund44227 Germany Department of Oral and Maxillofacial Surgery University Hospital RWTH Aachen Aachen52074 Germany Institute of Medical Informatics University Hospital RWTH Aachen Aachen52074 Germany

With the massive proliferation of data-driven algorithms, such as deep learning-based approaches, the availability of high-quality data is of great interest. Volumetric data is very important in medicine, as it ranges from disease diagnoses to therapy monitoring. When the dataset is sufficient, models can be trained to help doctors with these tasks. Unfortunately, there are scenarios where large amounts of data is unavailable. For example, rare diseases and privacy issues can lead to restricted data availability. In non-medical fields, the high cost of obtaining enough high-quality data can also be a concern. A solution to these problems can be the generation of realistic synthetic data using Generative Adversarial Networks (GANs). The existence of these mechanisms is a good asset, especially in healthcare, as the data must be of good quality, realistic, and without privacy issues. Therefore, most of the publications on volumetric GANs are within the medical domain. In this review, we provide a summary of works that generate realistic volumetric synthetic data using GANs. We therefore outline GAN-based methods in these areas with common architectures, loss functions and evaluation metrics, including their advantages and disadvantages. We present a novel taxonomy, evaluations, challenges, and research opportunities to provide a holistic overview of the current state of volumetric GANs. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

On the estimation of the Wasserstein distance in generative models

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Pinetz, Thomas Soukup, Daniel Pock, Thomas Center for Vision Automation and Control Austrian Institute of Technology Institute of Computer Graphics and Vision Graz University of Technology Austria

Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets. GANs are notoriuos for training diffculties and their dependence on arbitrary hyperparameters. One recent improvement in GAN literature is to use the Wasserstein distance as loss function leading to Wasserstein Generative Adversarial Networks (WGANs). Using this as a basis, we show various ways in which the Wasserstein distance is estimated for the task of generative modelling. Additionally, the secrets in training such models are shown and summarized at the end of this work. Where applicable, we extend current works to different algorithms, different cost functions, and different regularization schemes to improve generative models. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

An Adaptive Weighted QITE-VQE Algorithm for Combinatorial Optimization Problems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xie, Ningyi Lee, Xinwei Chen, Tiejin Saito, Yoshiyuki Asai, Nobuyoshi Cai, Dongsheng Graduate School of Science and Technology University of Tsukuba Ibaraki Japan School of Computing and Information Systems Singapore Management University Singapore Singapore School of Computing and Augmented Intelligence Arizona State University Tempe United States ARGO GRAPHICS Inc. Tokyo Japan School of Computer Science and Engineering University of Aizu Fukushima Japan Faculty of Engineering Information and Systems University of Tsukuba Ibaraki Japan

The variational quantum eigensolver (VQE) is a promising algorithm for finding the ground states of a given Hamiltonian. Its application to binary-formulated combinatorial optimization (CO) has been intensively studied in recent years. However, typical VQE approaches for CO problems often suffer from local minima or barren plateaus, limiting their ability to achieve optimal solutions. The quantum imaginary time evolution (QITE) offers an alternative approach for effective ground-state preparation but requires large circuits to approximate non-unitary operations. Although compressed QITE (cQITE) reduces circuit depth, accumulated errors eventually cause energy increases. To address these challenges, we propose an Adaptive Weighted QITE-VQE (AWQV) algorithm that integrates the VQE gradients with the cQITE updates through an adaptive weighting scheme during optimization. In numerical experiments of MaxCut on unweighted regular graphs, AWQV achieves near-optimal approximation ratios, while for weighted ErdősRényi instances, it outperforms the classical Goemans-Williamson algorithm. © 2025, CC BY.

关键词： Combinatorial optimization

Evaluating the effects of highlighting text animations on the attention distribution of students with math learning difficulties 125

学校读者我要写书评

暂无评论

Evaluating the effects of highlighting text animations on th...

125th ASEE Annual Conference and Exposition

作者： Wei, Shuang Lei, Qingli Chen, Yingjie Xin, Yan Ping Kastberg, Signe Department of Computer Graphics Technology Purdue University West Lafayette United States

computer-assisted learning benefits students by providing a great number of multimedia resources for improving response strength, streamlining information acquisition, and promoting knowledge construction [1]. Highlighting techniques have been widely used and, within the framework of cognitive load theory, are recognized as effective methods guiding students' attention and reducing extraneous cognitive processes. This research study was designed to examine the effects of highlighting text animations (including blinking animation, popping out animation, and intense animation) on the attention distribution of students with math learning difficulties (MLD). As predicted, the results suggest that highlighting text animations are able to guide the attention allocation of students with MLD. In particular, intense animation significantly improved students' fixation duration ratios on the key information areas in comparison to situations without highlighting text animation. © American Society for Engineering Education, 2018.

关键词：