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

100 篇 会议
6 篇 期刊文献
3 册 图书

馆藏范围

109 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

35 篇 工学
- 28 篇 计算机科学与技术...
- 13 篇 电气工程
- 7 篇 软件工程
- 5 篇 机械工程
- 3 篇 光学工程
- 3 篇 信息与通信工程
- 3 篇 控制科学与工程
- 2 篇 交通运输工程
- 1 篇 力学（可授工学、理...
- 1 篇 仪器科学与技术
- 1 篇 土木工程
- 1 篇 测绘科学与技术
- 1 篇 航空宇航科学与技...
- 1 篇 生物工程
8 篇 理学
- 4 篇 物理学
- 3 篇 数学
- 1 篇 地理学
- 1 篇 大气科学
- 1 篇 生物学
- 1 篇 统计学（可授理学、...
4 篇 医学
- 3 篇 临床医学
- 1 篇 基础医学(可授医学...
- 1 篇 医学技术（可授医学...
1 篇 法学
- 1 篇 社会学
1 篇 艺术学
- 1 篇 设计学（可授艺术学...

主题

43 篇 computer vision
23 篇 training
13 篇 robustness
12 篇 object detection
12 篇 cameras
11 篇 feature extracti...
10 篇 image segmentati...
10 篇 computational mo...
9 篇 semantics
9 篇 accuracy
8 篇 computer archite...
8 篇 transformers
7 篇 visualization
6 篇 three-dimensiona...
6 篇 lighting
6 篇 diffusion models
6 篇 shape
6 篇 data models
6 篇 adaptation model...
5 篇 conferences

机构

2 篇 department of co...
2 篇 univ nevada dept...
2 篇 univ houston dep...
2 篇 norwegian univer...
2 篇 espol polytech u...
2 篇 ipai seoul natio...
2 篇 honeywell techno...
2 篇 ece seoul nation...
1 篇 general atomics ...
1 篇 university of sc...
1 篇 mbzuai uae
1 篇 georgia inst tec...
1 篇 department of co...
1 篇 éts montreal int...
1 篇 applied computer...
1 篇 school of physic...
1 篇 department of el...
1 篇 department of co...
1 篇 univ michigan an...
1 篇 huazhong univers...

作者

3 篇 pavlidis i
2 篇 wang lei
2 篇 keda lu
2 篇 j.m. keller
2 篇 du shenshen
2 篇 yu ye
2 篇 zhang zhong
2 篇 lu keda
2 篇 yu jun
2 篇 zhang liwen
2 篇 i. pavlidis
2 篇 niki trigoni
2 篇 andrew markham
2 篇 shenshen du
2 篇 chang hao
2 篇 bebis g
2 篇 dowdall j
2 篇 jun yu
2 篇 ling qiang
2 篇 raghavendra rama...

语言

109 篇 英文

检索条件"任意字段=IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications"

共 109 条记录，以下是31-40 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：

Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images

Generative Model-Based Fusion for Improved Few-Shot Semantic...

引用

ieee workshop on applications of computer vision (WACV)

作者： Junno Yun Mehmet Akçakaya University of Minnesota

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Infrared (IR) imaging is commonly used in various scenarios, including autonomous driving, fire safety and defense applications. Thus, semantic segmentation of such images is of great interest. However, this task faces several challenges, including data scarcity, differing contrast and input channel number compared to natural images, and emergence of classes not represented in databases in certain scenarios, such as defense applications. Few-shot segmentation (FSS) provides a framework to overcome these issues by segmenting query images using a few labeled support samples. However, existing FSS models for IR images require paired visible RGB images, which is a major limitation since acquiring such paired data is difficult or impossible in some applications. In this work, we develop new strategies for FSS of IR images by using generative modeling and fusion techniques. To this end, we propose to synthesize auxiliary data to provide additional channel information to complement the limited contrast in the IR images, as well as IR data synthesis for data augmentation. Here, the former helps the FSS model to better capture the relationship between the support and query sets, while the latter addresses the issue of data scarcity. Finally, to further improve the former aspect, we propose a novel fusion ensemble module for integrating the two different modalities. Our methods are evaluated on different IR datasets, and improve upon the state-of-the-art (SOTA) FSS models.

关键词： Training computer vision Databases Semantic segmentation Imaging Data augmentation Data models Faces Autonomous vehicles Fire safety

来源：评论

学校读者我要写书评

暂无评论

Re-Evaluating Group Robustness via Adaptive Class-Specific Scaling

Re-Evaluating Group Robustness via Adaptive Class-Specific S...

引用

ieee workshop on applications of computer vision (WACV)

作者： Seonguk Seo Bohyung Han ECE Seoul National University IPAI Seoul National University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Group distributionally robust optimization, which aims to improve robust accuracies-worst-group and unbiased accuracies-is a prominent algorithm used to mitigate spu-rious correlations and address dataset bias. Although ex-isting approaches have reported improvements in robust accuracies, these gains often come at the cost of average accuracy due to inherent trade-offs. To control this trade-off flexibly and efficiently, we propose a simple class-specific scaling strategy, directly applicable to existing debiasing algorithms with no additional training. We further develop an instance-wise adaptive scaling technique to alleviate this trade-off, even leading to improvements in both robust and average accuracies. Our approach reveals that a naive ERM baseline matches or even outperforms the recent debi-asing methods by simply adopting the class-specific scaling technique. Additionally, we introduce a novel unified metric that quantifies the trade-off between the two accuracies as a scalar value, allowing for a comprehensive evaluation of existing algorithms. By tackling the inherent trade-off and offering a performance landscape, our approach provides valuable insights into robust techniques beyond just robust accuracy. We validate the effectiveness of our framework through experiments across datasets in computer vision and natural language processing domains.

关键词： Training Measurement computer vision Accuracy Costs Correlation Pareto optimization Robustness Natural language processing Optimization

来源：评论

学校读者我要写书评

暂无评论

DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal Object Re-Identification

DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal...

引用

ieee workshop on applications of computer vision (WACV)

作者： Minghui Lin Shu Wang Xiang Wang Jianhua Tang Longbin Fu Zhengrong Zuo Nong Sang Huazhong University of Science and Technology Shandong University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance. However, these methods usually adopt the standard full fine-tuning paradigm, which requires the optimization of considerable backbone parameters, causing extensive computational and storage requirements. In this work, we propose an efficient prompt-tuning framework tailored for multi-modal object re-identification; dubbed DMPT, which freezes the main backbone and only optimizes several newly added decoupled modality-aware parameters. Specifically, we explicitly decouple the visual prompts into modality-specific prompts which leverage prior modality knowledge from a powerful text encoder and modality-independent semantic prompts which extract semantic information from multi-modal inputs, such as visible, near-infrared, and thermal-infrared. Built upon the extracted features, we further design a Prompt Inverse Bind (PromptIBind) strategy that employs bind prompts as a medium to connect the semantic prompt tokens of different modalities and facilitates the exchange of complementary multi-modal information, boosting final re-identification results. Experimental results on multiple common benchmarks demonstrate that our DMPT can achieve competitive results to existing state-of-the-art methods while requiring only 6.5% fine-tuning of the backbone parameters.

关键词： Visualization computer vision Foundation models Computational modeling Semantics Feature extraction Data mining Tuning Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

CIRCOD: Co-Saliency Inspired Referring Camouflaged Object Discovery

CIRCOD: Co-Saliency Inspired Referring Camouflaged Object Di...

引用

ieee workshop on applications of computer vision (WACV)

作者： Avi Gupta Koteswar Rao Jerripothula Tammam Tillo Indraprastha Institute of Information Technology Delhi (IIIT-Delhi) Indian Institute of Technology Kanpur (IIT Kanpur)

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Camouflaged object detection (COD), the task of identifying objects concealed within their surroundings, is often quite challenging due to the similarity that exists between the foreground and background. By incorporating an additional referring image where the target object is clearly visible, we can leverage the similarities between the two images to detect the camouflaged object. In this paper, we propose a novel problem setup: referring camouflaged object discovery (RCOD). In RCOD, segmentation occurs only when the object in the referring image is also present in the camouflaged image; otherwise, a blank mask is returned. This setup is particularly valuable when searching for specific camouflaged objects. Current COD methods are often generic, leading to numerous false positives in applications focused on specific objects. To address this, we introduce a new framework called Co-Saliency Inspired Referring Camouflaged Object Discovery (CIRCOD). Our approach consists of two main components: Co-Saliency-Aware Image Transformation (CAIT) and Co-Salient Object Discovery (CSOD). The CAIT module reduces the appearance and structural variations between the camouflaged and referring images, while the CSOD module utilizes the similarities between them to segment the camouflaged object, provided the images are semantically similar. Covering all semantic categories in current COD benchmark datasets, we collected over 1,000 referring images to validate our approach. Our extensive experiments demonstrate the effectiveness of our method and show that it achieves superior results compared to existing methods. Code is available at https://***/avigupta2798/CIRCOD/.

关键词： Image segmentation Image transformation computer vision Codes Semantics Object detection Benchmark testing Search problems Object recognition

来源：评论

学校读者我要写书评

暂无评论

Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm

Low-Frequency Black-Box Backdoor Attack via Evolutionary Alg...

引用

ieee workshop on applications of computer vision (WACV)

作者： Yanqi Qiao Dazhuang Liu Rui Wang Kaitai Liang Delft University of Technology

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Convolutional Neural Networks (CNNs) that have excelled in diverse computer vision tasks are vulnerable to backdoor attacks, enabling attacker-controlled predictions via specific triggers. Restricted to spatial domains, recent research exploits perceptual traits by embedding triggers in the frequency domain, yielding pixel-level indistinguishable perturbations. In black-box settings, restricted access to model and training process necessitates advanced trigger designs. Current frequency-based attacks manipulate magnitude spectra, introducing discrepancies between clean and poisoned data, though vulnerable to common image processing operations like compression and filtering. In this paper, we propose a robust low-frequency backdoor attack (LFBA) in black-box setup that minimally perturbs spectrum components and maintains the perceptual similarity in spatial space simultaneously. Our methodology capitalizes on the insight that optimal triggers can be located in low-frequency regions to maximize attack effectiveness, robustness against image transformation operations, and stealthiness in dual space. To effectively explore the discrete frequency space, we utilize simulated annealing (SA), a form of evolutionary algorithm, to optimize the properties of trigger including the frequency bands to be manipulated and the perturbation of each band under restricted attack scenario. Extensive experiments on both CNNs and vision Transformers (ViT) confirm the effectiveness and robustness of LFBA against image processing operations and state-of-the-art backdoor defenses. Furthermore, LFBA exhibits inherent stealthiness in both spatial and frequency spaces, making it resistant to human and frequency inspection.

关键词： Training computer vision Perturbation methods Closed box Evolutionary computation Simulated annealing Inspection Transformers Robustness Space exploration

来源：评论

学校读者我要写书评

暂无评论

Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization

Domain-Guided Weight Modulation for Semi-Supervised Domain G...

引用

ieee workshop on applications of computer vision (WACV)

作者： Chamuditha Jayanaga Galappaththige Zachary Izzo Xilin He Honglu Zhou Muhammad Haris Khan MBZUAI UAE NEC Labs USA Shenzhen University China Salesforce AI Research USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Unarguably, deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor, we study the challenging problem of semi-supervised domain generalization (SSDG), where the goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data. Domain generalization (DG) methods show subpar performance under the SSDG setting, whereas semi-supervised learning (SSL) methods demonstrate relatively better performance, however, they are considerably poor compared to the fully-supervised DG methods. Towards handling this new, but challenging problem of SSDG, we propose a novel method that can facilitate the generation of accurate pseudo-labels under various domain shifts. This is accomplished by retaining the domain-level specialism in the classifier during training corresponding to each source domain. Specifically, we first create domain-level information vectors on the fly which are then utilized to learn a domain-aware mask for modulating the classifier's weights. We provide a mathematical interpretation for the effect of this modulation procedure on both pseudo-labeling and model training. Our method is plug-and-play and can be readily applied to different SSL baselines for SSDG. Extensive experiments on six challenging datasets in two different SSDG settings show that our method provides visible gains over the various strong SSL-based SSDG baselines. Our code is available at ***/DGWM.

关键词： Training Deep learning computer vision Costs Modulation Semisupervised learning Search problems Data models Vectors Mathematical models

来源：评论

学校读者我要写书评

暂无评论

CAMS: Convolution and Attention-Free Mamba-Based Cardiac Image Segmentation

CAMS: Convolution and Attention-Free Mamba-Based Cardiac Ima...

引用

ieee workshop on applications of computer vision (WACV)

作者： Abbas Khan Muhammad Asad Martin Benning Caroline Roney Gregory Slabaugh Queen Mary University of London Digital Environment Research Institute University College London

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Convolutional Neural Networks (CNNs) and Transformer-based self-attention models have become the standard for medical image segmentation. This paper demonstrates that convolution and self-attention, while widely used, are not the only effective methods for segmentation. Breaking with convention, we present a Convolution and self-Attention-free Mamba-based seman-tic Segmentation Network named CAMS-Net. Specifically, we design Mamba-based Channel Aggregator and Spatial Aggregator, which are applied independently in each encoder-decoder stage. The Channel Aggregator extracts information across different channels, and the Spatial Ag-gregator learns features across different spatial locations. We also propose a Linearly Interconnected Factorized Mamba (LIFM) block to reduce the computational complexity of a Mamba block and to enhance its decision function by introducing a non-linearity between two factor-ized Mamba blocks. Our model outperforms the existing state-of-the-art CNN, self-attention, and Mamba-based methods on CMR and M&Ms-2 Cardiac segmentation datasets, showing how this innovative, convolution, and self-attention-free method can inspire further research beyond CNN and Transformer paradigms, achieving linear complexity and reducing the number of parameters. Source code and pre-trained models are available at: https://***/kabbas570/CAMS-Net.

关键词： Image segmentation computer vision Convolution Computational modeling Source coding Transformers Feature extraction Convolutional neural networks Data mining Standards

来源：评论

学校读者我要写书评

暂无评论

SpotDiffusion: A Fast Approach for Seamless Panorama Generation Over Time

SpotDiffusion: A Fast Approach for Seamless Panorama Generat...

引用

ieee workshop on applications of computer vision (WACV)

作者： Stanislav Frolov Brian B. Moser Andreas Dengel German Research Center for Artificial Intelligence (DFKI) Germany RPTU Kaiserslautern-Landau Germany

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further pushed image generation beyond training resolutions, i.e., from square images to panorama, by merging multiple overlapping diffusion paths or employing gradient descent to maintain perceptual coherence. However, these methods suffer from significant computational inefficiencies due to generating and averaging numerous predictions, which is required in practice to produce high-quality and seamless images. This work addresses this limitation and presents a novel approach that eliminates the need to generate and average numerous overlapping denoising predictions. Our method shifts non-overlapping denoising windows over time, ensuring that seams in one timestep are corrected in the next. This results in coherent, high-resolution images with fewer over-all steps. We demonstrate the effectiveness of our approach through qualitative and quantitative evaluations, comparing it with MultiDijfusion, SyncDiffusion, and StitchDijfusion. Our method offers several key benefits, including improved computational efficiency and faster inference times while producing comparable or better image quality.

关键词： Training Image quality computer vision Image resolution Image synthesis Noise reduction Merging Coherence Diffusion models Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

引用

ieee workshop on applications of computer vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TLDR: Text Based Last-Layer Retraining for Debiasing Image Classifiers

TLDR: Text Based Last-Layer Retraining for Debiasing Image C...

引用

ieee workshop on applications of computer vision (WACV)

作者： Juhyeon Park Seokhyeon Jeong Taesup Moon IPAI Seoul National University ECE Seoul National University ASRI / INMC / AIIS Seoul National University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

An image classifier may depend on incidental features stemming from a strong correlation between the feature and the classification target in the training dataset. Recently, Last Layer Retraining (LLR) with group-balanced datasets is shown to be efficient in mitigating the spurious correlation of classifiers. However, the acquisition of image-based group-balanced datasets is costly, which hinders the general applicability of the LLR method. In this work, we propose to perform LLR based on text datasets built with large language models to debias a general image classifier. To that end, we demonstrate that text can generally be a proxy for its corresponding image beyond the image-text joint embedding space, which is achieved with a linear projector that ensures orthogonality between its weight and the modality gap of the joint embedding space. In addition, we propose a systematic validation procedure that checks whether the generated words are compatible with the embedding space of CLIP and the image classifier, which is shown to be effective for improving debiasing performance. We dub these procedures as TLDR (Text-based Last layer retraining for Debiasing image classifieRs) and show our method achieves the performance that is competitive with the LLR methods that require group-balanced image dataset for retraining. Furthermore, TLDR outperforms other baselines that involve training the last layer without any group annotated dataset. Codes: https://***/beotborry/TLDR

关键词： Training computer vision Correlation Systematics Codes Large language models

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11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：