检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

297 篇 会议

馆藏范围

297 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

297 篇 工学
- 297 篇 电气工程
- 297 篇 计算机科学与技术...
297 篇 医学
- 297 篇 临床医学

主题

297 篇 image recognitio...
297 篇 algorithms
126 篇 and algorithms
126 篇 machine learning...
126 篇 formulations
77 篇 applications
34 篇 vision + languag...
33 篇 datasets and eva...
25 篇 biomedical / hea...
25 篇 3d computer visi...
21 篇 video recognitio...
16 篇 remote sensing
15 篇 autonomous drivi...
14 篇 generative model...
14 篇 video
14 篇 3d
11 篇 gesture
11 篇 etc.
11 篇 face
11 篇 biometrics

机构

10 篇 tech univ munich...
6 篇 johns hopkins un...
5 篇 zhejiang univ pe...
5 篇 australian natl ...
4 篇 google res mount...
4 篇 korea adv inst s...
3 篇 peking univ peop...
3 篇 georgia inst tec...
3 篇 seoul natl univ
3 篇 munich ctr machi...
3 篇 ludwig maximilia...
3 篇 pohang univ sci ...
3 篇 univ calif berke...
2 篇 ets montreal dep...
2 篇 sungkyunkwan uni...
2 篇 univ copenhagen ...
2 篇 univ southern ca...
2 篇 duke univ durham...
2 篇 technol innovat ...
2 篇 univ birmingham ...

作者

4 篇 bagci ulas
4 篇 pedersoli marco
3 篇 granger eric
3 篇 chen liang-chieh
3 篇 biswas soma
3 篇 tresp volker
3 篇 kwak suha
3 篇 cho minsu
3 篇 okatani takayuki
2 篇 hekimoglu aral
2 篇 song shanshan
2 篇 phutke shruti s.
2 篇 jha debesh
2 篇 cucchiara rita
2 篇 banerjee biplab
2 篇 kortylewski adam
2 篇 van gool luc
2 篇 dubail thomas
2 篇 ray nilanjan
2 篇 erbilgin nadir

语言

297 篇 英文

检索条件"主题词=Image recognition and understanding"

共 297 条记录，以下是21-30 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Discriminator-free Unsupervised Domain Adaptation for Multi-label image Classification

Discriminator-free Unsupervised Domain Adaptation for Multi-...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Singh, Inder Pal Ghorbel, Enjie Kacem, Anis Rathinam, Arunkumar Aouada, Djamila Univ Luxembourg Interdisciplinary Ctr Secur Reliabil & Trust SnT Luxembourg Luxembourg Univ Manouba High Inst Multimedia Arts ISAMM Nasr Tunisia

ISBN: (纸本)9798350318920;9798350318937

In this paper, a discriminator-free adversarial-based Unsupervised Domain Adaptation (UDA) for Multi-Label image Classification (MLIC) referred to as DDA-MLIC is proposed. Recently, some attempts have been made for introducing adversarial-based UDA methods in the context of MLIC. However, these methods, which rely on an additional discriminator subnet present one major shortcoming. The learning of domain-invariant features may harm their task-specific discriminative power, since the classification and discrimination tasks are decoupled. Herein, we propose to overcome this issue by introducing a novel adversarial critic that is directly deduced from the task-specific classifier. Specifically, a two-component Gaussian Mixture Model (GMM) is fitted on the source and target predictions in order to distinguish between two clusters. This allows extracting a Gaussian distribution for each component. The resulting Gaussian distributions are then used for formulating an adversarial loss based on a Frechet distance. The proposed method is evaluated on several multi-label image datasets covering three different types of domain shift. The obtained results demonstrate that DDA-MLIC outperforms existing state-of-the-art methods in terms of precision while requiring a lower number of parameters. The code is publicly available at ***/cvi2snt/DDA-MLIC.(1)

关键词： adversarial attack and defense methods Adversarial learning Algorithms Algorithms image recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical image Segmentation

CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Vo...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Hung, Alex Ling Yu Zheng, Haoxin Zhao, Kai Du, Xiaoxi Pang, Kaifeng Miao, Qi Raman, Steven S. Terzopoulos, Demetri Sung, Kyunghyun Univ Calif Los Angeles Los Angeles CA 90024 USA

ISBN: (纸本)9798350318920;9798350318937

A large portion of volumetric medical data, especially magnetic resonance imaging (MRI) data, is anisotropic, as the through-plane resolution is typically much lower than the in-plane resolution. Both 3D and purely 2D deep learning-based segmentation methods are deficient in dealing with such volumetric data since the performance of 3D methods suffers when confronting anisotropic data, and 2D methods disregard crucial volumetric information. Insufficient work has been done on 2.5D methods, in which 2D convolution is mainly used in concert with volumetric information. These models focus on learning the relationship across slices, but typically have many parameters to train. We offer a Cross-Slice Attention Module (CSAM) with minimal trainable parameters, which captures information across all the slices in the volume by applying semantic, positional, and slice attention on deep feature maps at different scales. Our extensive experiments using different network architectures and tasks demonstrate the usefulness and generalizability of CSAM. Associated code is available at https://***/aL3x-O-o-Hung/CSAM.

关键词： Algorithms Applications Biomedical / healthcare / medicine image recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal image Matching on Limited Data

Reverse Knowledge Distillation: Training a Large Model using...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Nasser, Sahar Almahfouz Gupte, Nihar Sethi, Amit Indian Inst Technol Mumbai Maharashtra India

ISBN: (纸本)9798350318920;9798350318937

Retinal image matching (RIM) plays a crucial role in monitoring disease progression and treatment response as retina is the only tissue where blood vessels can be directly observed. However, datasets with matched keypoints between temporally separated pairs of images are not available in abundance to train transformer-based models. Firstly, we release keypoint annotations for retinal images from multiple datasets to aid further research on RIM. Secondly, we propose a novel approach based on reverse knowledge distillation to train large models with limited data while preventing overfitting. We propose architectural modifications to a CNN-based semi-supervised method called SuperRetina [22] that helps improve its results on a publicly available dataset. We train a computationally heavier model based on a vision transformer encoder, utilizing the lighter CNN-based model. This approach, which we call reverse knowledge distillation (RKD), further improves the matching results even though it contrasts with the conventional knowledge distillation where lighter models are trained based on heavier ones is the norm. Further, we show that our technique generalizes to other domains, such as facial landmark matching.

关键词： Algorithms Algorithms Applications Biomedical / healthcare / medicine Datasets and evaluations image recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

Object Aware Contrastive Prior for Interactive image Segmentation

Object Aware Contrastive Prior for Interactive Image Segment...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Mathur, Praful Parwani, Shashi Kumar Sen, Mrinmoy Sheshadri, Roopa Sharma, Aman Samsung R&D Inst India Bangalore Karnataka India

ISBN: (纸本)9798350318920;9798350318937

Interactive image Segmentation is a process of separating a user selected object from the background. This task requires building an effective class-agnostic segmentation model that performs well even on unseen categories. To achieve good accuracy with limited training dataset, it is important that the model has robust prior understanding of features of similar class objects. The model should also have good distinguishing capabilities of foreground objects with the background. In this paper, we propose Object Aware Click Embeddings (OACE) that represents user click aware foreground object features. OACE is obtained based on a prior network trained using the Contrastive Learning paradigm. The single-click object selection accuracy of our base interactive segmentation network is vastly improved with the OACE input. Additionally, we propose a Multi-Stage fusion approach to better utilize user click information. With the proposed method, we outperform existing state-of-the-art approaches by 21% on publicly available test-sets for click-based Interactive image Segmentation.

关键词： Algorithms Algorithms and algorithms formulations image recognition and understanding Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

CXR-IRGen: An Integrated Vision and Language Model for the Generation of Clinically Accurate Chest X-Ray image-Report Pairs

CXR-IRGen: An Integrated Vision and Language Model for the G...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Shentu, Junjie Al Moubayed, Noura Univ Durham Durham England

ISBN: (纸本)9798350318920;9798350318937

Chest X-Ray (CXR) images play a crucial role in clinical practice, providing vital support for diagnosis and treatment. Augmenting the CXR dataset with synthetically generated CXR images annotated with radiology reports can enhance the performance of deep learning models for various tasks. However, existing studies have primarily focused on generating unimodal data of either images or reports. In this study, we propose an integrated model, CXR-IRGen, designed specifically for generating CXR image-report pairs. Our model follows a modularized structure consisting of a vision module and a language module. Notably, we present a novel prompt design for the vision module by combining both text embedding and image embedding of a reference image. Additionally, we propose a new CXR report generation model as the language module, which effectively leverages a large language model and self-supervised learning strategy. Experimental results demonstrate that our new prompt is capable of improving the general quality (FID) and clinical efficacy (AUROC) of the generated images, with average improvements of 15.84% and 1.84%, respectively. Moreover, the proposed CXR report generation model outperforms baseline models in terms of clinical efficacy (F-1 score) and exhibits a high-level alignment of image and text, as the best F-1 score of our model is 6.93% higher than the state-of-the-art CXR report generation model. Our code is available at https://***/junjie-shentu/CXR-IRGen.

关键词： 3D Algorithms Algorithms etc. Generative models for image image recognition and understanding video

来源：评论

学校读者我要写书评

暂无评论

G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical image Segmentation

G-CASCADE: Efficient Cascaded Graph Convolutional Decoding f...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Rahman, Md Mostafijur Marculescu, Radu Univ Texas Austin Austin TX 78712 USA

ISBN: (纸本)9798350318920;9798350318937

In this paper, we are the first to propose a new graph convolution-based decoder namely, Cascaded Graph Convolutional Attention Decoder (G-CASCADE), for 2D medical image segmentation. G-CASCADE progressively refines multi-stage feature maps generated by hierarchical transformer encoders with an efficient graph convolution block. The encoder utilizes the self-attention mechanism to capture long-range dependencies, while the decoder refines the feature maps preserving long-range information due to the global receptive fields of the graph convolution block. Rigorous evaluations of our decoder with multiple transformer encoders on five medical image segmentation tasks (i.e., Abdomen organs, Cardiac organs, Polyp lesions, Skin lesions, and Retinal vessels) show that our model outperforms other state-of-the-art (SOTA) methods. We also demonstrate that our decoder achieves better DICE scores than the SOTA CASCADE decoder with 80.8% fewer parameters and 82.3% fewer FLOPs. Our decoder can easily be used with other hierarchical encoders for general-purpose semantic and medical image segmentation tasks. The implementation can be found at: https://***/SLDGroup/G-CASCADE.

关键词： Algorithms Algorithms and algorithms Applications Biomedical / healthcare / medicine formulations image recognition and understanding Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

Defending Object Detection Models against image Distortions

Defending Object Detection Models against Image Distortions

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Ofori-Oduro, Mark Amer, Maria Concordia Univ Dept Elect & Comp Engn Montreal PQ Canada

ISBN: (纸本)9798350318920;9798350318937

image distortions pose a significant challenge to object detection. To address this issue, our paper introduces a novel data augmentation method that generates new samples resembling the original training images. The new sample exhibits randomly altered pixels based on a pixel distribution obtained from multiple image distortions using kernel density estimation (KDE). The main steps of our method, GSES, are generating distorted versions of each pixel of an original training image, selecting a set of pixels in each version, and then, for each selected pixel, estimating its distribution using KDE and then sampling one pixel from this distribution. By employing this approach, the new samples possess distorted pixels while maintaining a certain degree of similarity to the original image. This degree of similarity is essential to balance the accuracy of object detection models under distorted and clean images. Our approach improves the accuracy of different object detection models under 15 image distortions, such as motion blur, fog, and noise. For example, the average accuracy of YOLOv4 improves by 9.19% and 9.54 % across all 15 distortions added to the COCO and PASCAL datasets, respectively. Our method surpasses other defence methods to combat image distortions. Our ablation and stability studies show why our method performs well. Moreover, we also show that our method can be well used to improve the accuracy of image classification under 15 distortions and cross-domains. Our code is available at https://***/moforio/GSES/.

关键词： adversarial attack and defense methods Adversarial learning Algorithms Algorithms Algorithms Datasets and evaluations image recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

Disentangled Pre-training for image Matting

Disentangled Pre-training for Image Matting

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Li, Yanda Huang, Zilong Yu, Gang Chen, Ling Wei, Yunchao Jiao, Jianbo Univ Technol Sydney Sydney NSW Australia Tencent Shenzhen Peoples R China Beijing Jiaotong Univ Beijing Peoples R China Univ Birmingham Birmingham W Midlands England

ISBN: (纸本)9798350318920;9798350318937

image matting requires high-quality pixel-level human annotations to support the training of a deep model in recent literature. Whereas such annotation is costly and hard to scale, significantly holding back the development of the research. In this work, we make the first attempt towards addressing this problem, by proposing a self-supervised pre-training approach that can leverage infinite numbers of data to boost the matting performance. The pre-training task is designed in a similar manner as image matting, where random trimap and alpha matte are generated to achieve an image disentanglement objective. The pre-trained model is then used as an initialisation of the downstream matting task for fine-tuning. Extensive experimental evaluations show that the proposed approach outperforms both the state-of-the-art matting methods and other alternative self-supervised initialisation approaches by a large margin. We also show the robustness of the proposed approach over different backbone architectures. Our project page is available at https://***/dpt_mat/.

关键词： Algorithms Algorithms image recognition and understanding Low-level and physics-based vision

来源：评论

学校读者我要写书评

暂无评论

Spectroformer: Multi-Domain Query Cascaded Transformer Network For Underwater image Enhancement

Spectroformer: Multi-Domain Query Cascaded Transformer Netwo...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Khan, M. D. Raqib Mishra, Priyanka Mehta, Nancy Phutke, Shruti S. Vipparthi, Santosh Kumar Nandi, Sukumar Murala, Subrahmanyam Trinity Coll Dublin Sch Comp Sci & Stat CVPR Lab Dublin Ireland Indian Inst Technol Ropar CVPR Lab Ropar India Univ Wurzburg Comp Vis Lab IFI CAIDAS Wurzburg Germany Griffith Univ Inst Integrated & Intelligent Syst Nathan Qld Australia Indian Inst Technol Guwahati Gauhati India

ISBN: (纸本)9798350318920;9798350318937

Underwater images often suffer from color distortion, haze, and limited visibility due to light refraction and absorption in water. These challenges significantly impact autonomous underwater vehicle applications, necessitating efficient image enhancement techniques. To address these challenges, we propose a Multi-Domain Query Cascaded Transformer Network for underwater image enhancement. Our approach includes a novel Multi-Domain Query Cascaded Attention mechanism that integrates localized transmission features and global illumination features. To improve feature propagation from the encoder to the decoder, we propose a Spatio-Spectro Fusion-Based Attention Block. Additionally, we introduce a Hybrid Fourier-Spatial Upsampling Block, which uniquely combines Fourier and spatial upsampling techniques to enhance feature resolution effectively. We evaluate our method on benchmark synthetic and real-world underwater image datasets, demonstrating its superiority through extensive ablation studies and comparative analysis. The testing code is available at: https://***/Mdraqibkhan/Spectroformer.

关键词： Algorithms Algorithms image recognition and understanding Video recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

Pruning from Scratch via Shared Pruning Module and Nuclear norm-based Regularization

Pruning from Scratch via Shared Pruning Module and Nuclear n...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Lee, Donghyeon Leek, Eunho Hwang, Youngbae Chungbuk Natl Univ Dept Intelligent Syst & Robot Cheongju South Korea

ISBN: (纸本)9798350318920;9798350318937

Most pruning methods focus on determining redundant channels from the pre-trained model. However, they overlook the cost of training large networks and the significance of selecting channels for effective reconfiguration. In this paper, we present a "pruning from scratch" framework that considers reconfiguration and expression capacity. Our Shared Pruning Module (SPM) handles a channel alignment problem in residual blocks for lossless reconfiguration after pruning. Moreover, we introduce nuclear norm-based regularization to preserve the representability of large networks during the pruning process. By combining it with MACs-based regularization, we achieve an efficient and powerful pruned network while compressing towards target MACs. The experimental results demonstrate that our method prunes redundant channels effectively to enhance representation capacity of the network. Our approach compresses ResNet50 on imageNet without requiring additional resources, achieving a top-1 accuracy of 75.25% with only 41% of the original model's MACs. Code is available at https://***/jsleeg98/NuSPM.

关键词： Algorithms Applications Embedded sensing / real-time techniques image recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共30页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：