检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Haopeng Deng, Andong Liu, Jun Rahmani, Hossein Guo, Yulan Schiele, Bernt Bennamoun, Mohammed Ke, Qiuhong School of Computing and Information Systems University of Melbourne Australia Center for Research in Computer Vision University of Central Florida United States Pillar Singapore University of Technology and Design Singapore School of Computing and Communications Lancaster University United Kingdom School of Electronics and Communication Engineering Sun Yat-sen University China Department of Computer Vision and Machine Learning Max Planck Institute for Informatics Saarland Informatics Campus Germany School of Physics Maths and Computing University of Western Australia Australia Department of Data Science & AI Monash University Australia

Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Novel ground reaction force-based parameters for monitoring rehabilitation in tibial fractures

引用

Gait & Posture 2024年 113卷 256-257页

作者： Christian Wolff Elke Warmerdam Tim Dahmen Tim Pohlemann Philipp Slusallek Bergita Ganse German Research Center for Artificial Intelligence Agents and Simulated Reality Saarbrücken Germany Saarland University Saarbrücken Graduate School of Computer Science Saarbrücken Germany Saarland University Werner Siemens-Endowed Chair for Innovative Implant Development Fracture Healing- Departments and Institutes of Surgery Homburg Germany Hochschule Aalen Chair for Computer Vision and Machine Learning Aalen Germany Saarland University Department of Trauma- Hand and Reconstructive Surgery- Departments and Institutes of Surgery Homburg Germany

来源：评论

学校读者我要写书评

暂无评论

Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy

arXiv

引用

arXiv 2023年

作者： Marinov, Zdravko Jäger, Paul F. Egger, Jan Kleesiek, Jens Stiefelhagen, Rainer The Computer Vision for Human-Computer Interaction Lab Department of Informatics Karlsruhe Institute of Technology Adenauerring 10 Karlsruhe76131 Germany Girardetstraße 2 Essen45131 Germany Heidelberg Interactive Machine Learning Group Im Neuenheimer Feld 223 Heidelberg69120 Germany The Helmholtz Imaging DKFZ Im Neuenheimer Feld 223 Heidelberg69120 Germany

Interactive segmentation is a crucial research area in medical image analysis aiming to boost the efficiency of costly annotations by incorporating human feedback. This feedback takes the form of clicks, scribbles, or masks and allows for iterative refinement of the model output so as to efficiently guide the system towards the desired behavior. In recent years, deep learning-based approaches have propelled results to a new level causing a rapid growth in the field with 121 methods proposed in the medical imaging domain alone. In this review, we provide a structured overview of this emerging field featuring a comprehensive taxonomy, a systematic review of existing methods, and an in-depth analysis of current practices. Based on these contributions, we discuss the challenges and opportunities in the field. For instance, we find that there is a severe lack of comparison across methods which needs to be tackled by standardized baselines and benchmarks. Appendixes are here. © 2023, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance

arXiv

引用

arXiv 2023年

作者： He, Chunming Li, Kai Xu, Guoxia Yan, Jiangpeng Tang, Longxiang Zhang, Yulun Li, Xiu Wang, Yaowei Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518055 China Machine Learning Department NEC Laboratories America Inc. NJ08540 United States Department of Computer Science Norwegian University of Science and Technology Gjovik2815 Norway The Computer Vision Lab ETH Zürich Zürich8092 Switzerland Peng Cheng Laboratory Shenzhen518066 China

Unpaired Medical Image Enhancement (UMIE) aims to transform a low-quality (LQ) medical image into a high-quality (HQ) one without relying on paired images for training. While most existing approaches are based on Pix2Pix/CycleGAN and are effective to some extent, they fail to explicitly use HQ information to guide the enhancement process, which can lead to undesired artifacts and structural distortions. In this paper, we propose a novel UMIE approach that avoids the above limitation of existing methods by directly encoding HQ cues into the LQ enhancement process in a variational fashion and thus model the UMIE task under the joint distribution between the LQ and HQ domains. Specifically, we extract features from an HQ image and explicitly insert the features, which are expected to encode HQ cues, into the enhancement network to guide the LQ enhancement with the variational normalization module. We train the enhancement network adversarially with a discriminator to ensure the generated HQ image falls into the HQ domain. We further propose a content-aware loss to guide the enhancement process with wavelet-based pixel-level and multi-encoder-based feature-level constraints. Additionally, as a key motivation for performing image enhancement is to make the enhanced images serve better for downstream tasks, we propose a bi-level learning scheme to optimize the UMIE task and downstream tasks cooperatively, helping generate HQ images both visually appealing and favorable for downstream tasks. Experiments on three medical datasets, including two newly collected datasets, verify that the proposed method outperforms existing techniques in terms of both enhancement quality and downstream task performance. We will make the code and the newly collected datasets publicly available for community study. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring

arXiv

引用

arXiv 2021年

作者： Dong, Jiangxin Roth, Stefan Schiele, Bernt School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Vision and Machine Learning Max Planck Institute for Informatics Germany Department of Computer Science TU Darmstadt Germany

We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning. In contrast to existing methods that deblur the image directly in the standard image space, we propose to perform an explicit deconvolution process in a feature space by integrating a classical Wiener deconvolution framework with learned deep features. A multi-scale cascaded feature refinement module then predicts the deblurred image from the deconvolved deep features, progressively recovering detail and small-scale structures. The proposed model is trained in an end-to-end manner and evaluated on scenarios with simulated Gaussian noise, saturated pixels, or JPEG compression artifacts as well as real-world images. Moreover, we present detailed analyses of the benefit of the feature-based Wiener deconvolution and of the multi-scale cascaded feature refinement as well as the robustness of the proposed approach. Our extensive experimental results show that the proposed deep Wiener deconvolution network facilitates deblurred results with visibly fewer artifacts and quantitatively outperforms state-of-the-art non-blind image deblurring methods by a wide margin. Copyright © 2021, The Authors. All rights reserved.

关键词： Deconvolution

来源：评论

学校读者我要写书评

暂无评论

Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks

arXiv

引用

arXiv 2022年

作者： Xu, Yonghao Yu, Weikang Ghamisi, Pedram Kopp, Michael Hochreiter, Sepp Vienna1030 Austria Computer Vision Laboratory Department of Electrical Engineering Linköping University Linköping58183 Sweden Helmholtz-Zentrum Dresden-Rossendorf Helmholtz Institute Freiberg for Resource Technology Machine Learning Group Freiberg09599 Germany ELLIS Unit Linz and LIT AI Lab Institute for Machine Learning Johannes Kepler University Linz4040 Austria

The synthesis of high-resolution remote sensing images based on text descriptions has great potential in many practical application scenarios. Although deep neural networks have achieved great success in many important remote sensing tasks, generating realistic remote sensing images from text descriptions is still very difficult. To address this challenge, we propose a novel text-to-image modern Hopfield network (Txt2Img-MHN). The main idea of Txt2Img-MHN is to conduct hierarchical prototype learning on both text and image embeddings with modern Hopfield layers. Instead of directly learning concrete but highly diverse text-image joint feature representations for different semantics, Txt2Img-MHN aims to learn the most representative prototypes from text-image embeddings, achieving a coarse-to-fine learning strategy. These learned prototypes can then be utilized to represent more complex semantics in the text-to-image generation task. To better evaluate the realism and semantic consistency of the generated images, we further conduct zero-shot classification on real remote sensing data using the classification model trained on synthesized images. Despite its simplicity, we find that the overall accuracy in the zero-shot classification may serve as a good metric to evaluate the ability to generate an image from text. Extensive experiments on the benchmark remote sensing text-image dataset demonstrate that the proposed Txt2Img-MHN can generate more realistic remote sensing images than existing methods. Code and pre-trained models are available online (https://***/YonghaoXu/Txt2Img-MHN). Copyright © 2022, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Optimising for Interpretability: Convolutional Dynamic Alignment Networks

arXiv

引用

arXiv 2021年

作者： Böhle, Moritz Fritz, Mario Schiele, Bernt The Department of Computer Vision and Machine Learning Max Planck Institute for Informatics Saarbrücken66123 Germany The CISPA Helmholtz Center for Information Security Saarbrücken66123 Germany

We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks are Dynamic Alignment Units (DAUs), which are optimised to transform their inputs with dynamically computed weight vectors that align with task-relevant patterns. As a result, CoDA Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions. Given the alignment of the DAUs, the resulting contribution maps align with discriminative input patterns. These model-inherent decompositions are of high visual quality and outperform existing attribution methods under quantitative metrics. Further, CoDA Nets constitute performant classifiers, achieving on par results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet. Lastly, CoDA Nets can be combined with conventional neural network models to yield powerful classifiers that more easily scale to complex datasets such as Imagenet whilst exhibiting an increased interpretable depth, i.e., the output can be explained well in terms of contributions from intermediate layers within the network. Copyright © 2021, The Authors. All rights reserved.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Estimating Polyp Size From a Single Colonoscopy Image Using a Shape-From-Shading Model

Estimating Polyp Size From a Single Colonoscopy Image Using ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Josué Ruano Diego Bravo Diana Giraldo Martín Gómez Fabio A. González Antoine Manzanera Eduardo Romero Computer Imaging and Medical Applications Laboratory (CIM@LAB) Universidad Nacional de Colombia Bogotá Colombia Department of Physics Imec-Vision Lab University of Antwerp Antwerp Belgium Unidad de Gastroenterología Hospital Universitario Nacional de Colombia Bogotá Colombia Machine Learning Perception and Discovery Lab (MindLab) ENSTA-Institut Polytechnique de Paris Unité d’Informatique et d’Ingénierie des Systémes France

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Colonoscopy (CO) is the most useful procedure to estimate the polyp size as part of surveillance and therapeutic management to prevent Colorectal cancer. Studies have reported a high rate of misestimated lesions by experts, reaching a relative accuracy of 67%. This work presents a method to estimate polyp size from a raw CO frame. A shape-from-shading model trained with synthetic images estimates a depth map to reconstruct the three-dimensional (3d) colon structure. Polyp is segmented in RGB image with a U-Net, to compute diameter in pixels. This diameter is projected onto the 3d surface to compute polyp size in millimeters. The method obtained a mean absolute error of 2.16 mm and relative accuracy of 88.17% in 2802 synthetic images, and 2.06 mm in 100 real images. In a binary classification task (< 10 mm or > 10 mm), the method achieved macro F1 scores of 89% and 72% in the synthetic and real databases respectively.

关键词： Surface reconstruction Solid modeling Image segmentation Three-dimensional displays Accuracy Surveillance Colonoscopy

来源：评论

学校读者我要写书评

暂无评论

Deep deterministic uncertainty for semantic segmentation

arXiv

引用

arXiv 2021年

作者： Mukhoti, Jishnu van Amersfoort, Joost Torr, Philip H.S. Gal, Yarin Oxford Applied & Theoretical Machine Learning Group Department of Computer Science University of Oxford Oxford United Kingdom Torr Vision Group Department of Engineering Science University of Oxford Oxford United Kingdom

We extend Deep Deterministic Uncertainty (DDU) (Mukhoti et al., 2021), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangling epistemic and aleatoric uncertainty in a single forward pass through the model. We study the similarity of feature representations of pixels at different locations for the same class and conclude that it is feasible to apply DDU location independently, which leads to a significant reduction in memory consumption compared to pixel dependent DDU. Using the DeepLab-v3+ architecture on Pascal VOC 2012, we show that DDU improves upon MC Dropout and Deep Ensembles while being significantly faster to compute. Copyright © 2021, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networks

arXiv

引用

arXiv 2024年

作者： Osuala, Richard Joshi, Smriti Tsirikoglou, Apostolia Garrucho, Lidia Pinaya, Walter H.L. Lang, Daniel M. Schnabel, Julia A. Diaz, Oliver Lekadir, Karim Departament de Matemàtiques i Informàtica Universitat de Barcelona Spain Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Munich Germany School of Computation Information and Technology Technical University of Munich Munich Germany Department of Oncology-Pathology Karolinska Institutet Stockholm Sweden King’s College London London United Kingdom Computer Vision Center Universitat Autònoma de Barcelona Bellaterra Spain Passeig Lluís Companys 23 Barcelona Spain

Purpose: Deep generative models and synthetic data generation have become essential for advancing computer-assisted diagnosis and treatment. We explore one such emerging and particularly promising application of deep generative models, namely, the generation of virtual contrast enhancement. This allows to predict and simulate contrast enhancement in breast magnetic resonance imaging (MRI) without physical contrast agent injection, thereby unlocking lesion localization and categorization even in patient populations where the lengthy, costly and invasive process of physical contrast agent injection is contraindicated. Approach: We define a framework for desirable properties of synthetic data, which leads us to propose the Scaled Aggregate Measure (SAMe) consisting of a balanced set of scaled complementary metrics for generative model training and convergence evaluation. We further adopt a conditional generative adversarial network to translate from non-contrast-enhanced T1-weighted fat-saturated breast MRI slices to their dynamic contrast-enhanced (DCE) counterparts, thus learning to detect, localize, and adequately highlight breast cancer lesions. Next, we extend our model approach to jointly generate multiple DCE-MRI timepoints, enabling the simulation of contrast enhancement across temporal DCE-MRI acquisitions. Additionally, 3D U-Net tumor segmentation models are implemented and trained on combinations of synthetic and real DCE-MRI data to investigate the effect of data augmentation with synthetic DCE-MRI volumes. Results: Conducting four main sets of experiments, (i) the variation across single metrics demonstrated the value of SAMe, and (ii) the quality and potential of virtual contrast injection for tumor detection and localization were shown. Segmentation models (iii) augmented with synthetic DCE-MRI data were more robust in the presence of domain shifts between pre-contrast and DCE-MRI domains. The joint synthesis approach of multi-sequence DCE-MRI (iv) resul

关键词： Generative adversarial networks

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：