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

17,064 篇 会议
72 篇 期刊文献
16 册 图书

馆藏范围

17,152 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,848 篇 工学
- 8,722 篇 计算机科学与技术...
- 4,145 篇 软件工程
- 3,358 篇 电气工程
- 2,102 篇 光学工程
- 1,636 篇 信息与通信工程
- 1,634 篇 控制科学与工程
- 1,155 篇 机械工程
- 1,023 篇 生物工程
- 547 篇 生物医学工程（可授...
- 434 篇 安全科学与工程
- 415 篇 电子科学与技术（可...
- 409 篇 仪器科学与技术
- 355 篇 交通运输工程
- 211 篇 化学工程与技术
- 201 篇 建筑学
- 197 篇 土木工程
- 177 篇 网络空间安全
3,522 篇 理学
- 2,302 篇 物理学
- 1,148 篇 数学
- 1,078 篇 生物学
- 322 篇 统计学（可授理学、...
- 281 篇 化学
- 167 篇 系统科学
2,751 篇 医学
- 2,683 篇 临床医学
- 297 篇 基础医学(可授医学...
- 203 篇 药学(可授医学、理...
1,233 篇 管理学
- 785 篇 管理科学与工程(可...
- 537 篇 图书情报与档案管...
- 280 篇 工商管理
173 篇 法学
- 162 篇 社会学
128 篇 农学
103 篇 经济学
84 篇 教育学
59 篇 艺术学
42 篇 军事学
29 篇 文学

主题

7,025 篇 computer vision
1,567 篇 training
1,216 篇 computational mo...
1,190 篇 cameras
996 篇 visualization
966 篇 computer archite...
947 篇 feature extracti...
845 篇 three-dimensiona...
822 篇 deep learning
781 篇 conferences
769 篇 image segmentati...
764 篇 object detection
707 篇 application soft...
523 篇 robustness
483 篇 algorithms
450 篇 benchmark testin...
432 篇 neural networks
430 篇 task analysis
389 篇 semantics
386 篇 accuracy

机构

45 篇 carnegie mellon ...
35 篇 swiss fed inst t...
32 篇 australian natl ...
30 篇 univ maryland co...
29 篇 university of ch...
29 篇 korea adv inst s...
28 篇 tech univ munich...
27 篇 adobe research
27 篇 tsinghua univ pe...
26 篇 zhejiang univers...
26 篇 shanghai jiao to...
25 篇 tsinghua univers...
25 篇 mit cambridge ma...
24 篇 univ chinese aca...
24 篇 univ tokyo
24 篇 imperial coll lo...
24 篇 adobe res san jo...
23 篇 microsoft resear...
23 篇 chinese univ hon...
22 篇 georgia inst tec...

作者

34 篇 van gool luc
30 篇 chen chen
27 篇 luc van gool
19 篇 horst bischof
17 篇 timofte radu
14 篇 torralba antonio
14 篇 rama chellappa
13 篇 liu yang
13 篇 darrell trevor
12 篇 escalera sergio
12 篇 vittorio murino
12 篇 samaras dimitris
12 篇 caputo barbara
12 篇 anon
11 篇 a. aydın alatan
11 篇 rahtu esa
11 篇 murino vittorio
11 篇 stiefelhagen rai...
11 篇 wang yang
10 篇 singh vikas

语言

16,564 篇 英文
501 篇 其他
50 篇 土耳其文
34 篇 中文
3 篇 葡萄牙文

检索条件"任意字段=IEEE Conference on Applications of Computer Vision"

共 17152 条记录，以下是81-90 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：

MGM-AE: Self-Supervised Learning on 3D Shape Using Mesh Graph Masked Autoencoders

MGM-AE: Self-Supervised Learning on 3D Shape Using Mesh Grap...

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Yang, Zhangsihao Ding, Kaize Liu, Huan Wang, Yalin Arizona State Univ Tempe AZ 85281 USA Northwestern Univ Evanston IL USA

ISBN: (纸本)9798350318920;9798350318937

The challenges of applying self-supervised learning to 3D mesh data include difficulties in explicitly modeling and leveraging geometric topology information and designing appropriate pretext tasks and augmentation methods for irregular mesh topology. In this paper, we propose a novel approach for pre-training models on large-scale, unlabeled datasets using graph masking on a mesh graph composed of faces. Our method, Mesh Graph Masked Autoencoders (MGM-AE), utilizes masked autoencoding to pre-train the model and extract important features from the data. Our pre-trained model outperforms prior state-of-the-art mesh encoders in shape classification and segmentation benchmarks, achieving 90.8% accuracy on ModelNet40 and 78.5 mIoU on ShapeNet. The best performance is obtained when the model is trained and evaluated under different masking ratios. Our approach demonstrates effectiveness in pre-training models on large-scale, unlabeled datasets and its potential for improving performance on downstream tasks.

关键词： 3D computer vision accountable Algorithms Algorithms Algorithms and algorithms ethical computer vision Explainable fair formulations Machine learning architectures privacy-preserving

来源：评论

学校读者我要写书评

暂无评论

Causal Feature Alignment: Learning to Ignore Spurious Background Features

Causal Feature Alignment: Learning to Ignore Spurious Backgr...

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Venkataramani, Rahul Dutta, Parag Melapudi, Vikram Dukkipati, Ambedkar Indian Inst Sci Bangalore India GE HealthCare Bangalore India

ISBN: (纸本)9798350318920;9798350318937

Deep neural networks are susceptible to spurious features strongly correlating with the target. This phenomenon leads to sub-optimal performance during real-world deployment where spurious correlations do not exist, leading to deployment challenges in safety-critical environments like healthcare. While spurious features can correlate with causal features in myriad ways, we propose a solution for a common manifestation in computer vision where the background corresponds to a spurious feature. In contrast to previous works, we do not require apriori knowledge of different groups in the data induced by the presence/absence of spurious features and corresponding access to samples. We propose a method, Causal Feature Alignment (CFA), to ignore the spurious background features by utilizing segmentations on a small subset of training data. To reduce the annotation burden, we reduce the pixel-wise annotation task of segmentation to a review task of selecting the best mask by utilizing the recently released foundation model and a feature attribution method. We demonstrate our method on a wide range of datasets, including the semi-synthetic ColoredMNIST, WaterBirds, and ImageNet Backgrounds Challenge, and obtain significant gains over state-of-the-art methods.

关键词： accountable Algorithms Algorithms and algorithms ethical computer vision Explainable fair formulations Machine learning architectures privacy-preserving

来源：评论

学校读者我要写书评

暂无评论

CLID: Controlled-Length Image Descriptions with Limited Data

CLID: Controlled-Length Image Descriptions with Limited Data

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Hirsch, Elad Tal, Ayellet Technion Israel Inst Technol Haifa Israel

ISBN: (纸本)9798350318920;9798350318937

Controllable image captioning models generate human-like image descriptions, enabling some kind of control over the generated captions. This paper focuses on controlling the caption length, i.e. a short and concise description or a long and detailed one. Since existing image captioning datasets contain mostly short captions, generating long captions is challenging. To address the shortage of long training examples, we propose to enrich the dataset with varying-length self-generated captions. These, however, might be of varying quality and are thus unsuitable for conventional training. We introduce a novel training strategy that selects the data points to be used at different times during the training. Our method dramatically improves the length-control abilities, while exhibiting SoTA performance in terms of caption quality. Our approach is general and is shown to be applicable also to paragraph generation. Our code is publicly available (1).

关键词： Algorithms vision + language and/or other modalities

来源：评论

学校读者我要写书评

暂无评论

TextAug: Test time Text Augmentation for Multimodal Person Re-identification

TextAug: Test time Text Augmentation for Multimodal Person R...

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Fawakherji, Mulham Vazquez, Eduard Giampa, Pasquale Bhattarai, Binod Fogsphere London England Univ Aberdeen Aberdeen Scotland

ISBN: (纸本)9798350370287;9798350370713

Multimodal Person Re-identification is gaining popularity in the research community due to its effectiveness compared to counter-part unimodal frameworks. However, the bottleneck for multimodal deep learning is the need for a large volume of multimodal training examples. Data augmentation techniques such as cropping, flipping, rotation, etc. are often employed in the image domain to improve the generalization of deep learning models. Augmenting in other modalities than images, such as text, is challenging and requires significant computational resources and external data sources. In this study, we investigate the effectiveness of two computer vision data augmentation techniques: "cutout" and "cutmix", for text augmentation in multi-modal person re-identification. Our approach merges these two augmentation strategies into one strategy called "CutMixOut" which involves randomly removing words or sub-phrases from a sentence (Cutout) and blending parts of two or more sentences to create diverse examples (CutMix) with a certain probability assigned to each operation. This augmentation was implemented at inference time without any prior training. Our results demonstrate that the proposed technique is simple and effective in improving the performance on multiple multimodal person re-identification benchmarks.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Learning to Read Analog Gauges from Synthetic Data

Learning to Read Analog Gauges from Synthetic Data

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Leon-Alcazar, Juan Alnumay, Yazeed Zheng, Cheng Trigui, Hassane Patel, Sahejad Ghanem, Bernard KAUST Thuwal Saudi Arabia Aramco Thuwal Saudi Arabia

ISBN: (纸本)9798350318920;9798350318937

Manually reading and logging gauge data is time-inefficient, and the effort increases according to the number of gauges available. We present a pipeline that automates the reading of analog gauges. We propose a two-stage CNN pipeline that identifies the key structural components of an analog gauge and outputs an angular reading. To facilitate the training of our approach, a synthetic dataset is generated thus obtaining a set of realistic analog gauges with their corresponding annotation. To validate our proposal, an additional real-world dataset was collected with 4.813 manually curated images. When compared against state-of-the-art methodologies, our method shows a significant improvement of 4.55 degrees in the average error, which is a 52% relative improvement. The resources for this project will be made available at: https://***/fuankarion/automatic-gauge-reading.

关键词： applications Structural engineering / civil engineering

来源：评论

学校读者我要写书评

暂无评论

Automated Camera Calibration via Homography Estimation with GNNs

Automated Camera Calibration via Homography Estimation with ...

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： D'Amicantonio, Giacomo Bondarev, Egor De With, Peter H. N. Eindhoven Univ Technol Eindhoven Netherlands

ISBN: (纸本)9798350318920;9798350318937

Over the past few decades, a significant rise of camera-based applications for traffic monitoring has occurred. Governments and local administrations are increasingly relying on the data collected from these cameras to enhance road safety and optimize traffic conditions. However, for effective data utilization, it is imperative to ensure accurate and automated calibration of the involved cameras. This paper proposes a novel approach to address this challenge by leveraging the topological structure of intersections. We propose a framework involving the generation of a set of synthetic intersection viewpoint images from a bird's-eye-view image, framed as a graph of virtual cameras to model these images. Using the capabilities of Graph Neural Networks, we effectively learn the relationships within this graph, thereby facilitating the estimation of a homography matrix. This estimation leverages the neighbourhood representation for any real-world camera and is enhanced by exploiting multiple images instead of a single match. In turn, the homography matrix allows the retrieval of extrinsic calibration parameters. As a result, the proposed framework demonstrates superior performance on both synthetic datasets and real-world cameras, setting a new state-of-the-art benchmark.

关键词： applications applications applications Autonomous Driving Structural engineering / civil engineering Visualization

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Multi-Object Tracking with Transformers

Contrastive Learning for Multi-Object Tracking with Transfor...

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： De Plaen, Pierre-Francois Marinello, Nicola Proesmans, Marc Tuytelaars, Tinne Van Gool, Luc Katholieke Univ Leuven ESAT PSI Leuven Belgium Swiss Fed Inst Technol CVL Zurich Switzerland TRACE Vzw Leuven Belgium

ISBN: (纸本)9798350318920;9798350318937

The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to perform Multi-Object Tracking (MOT), resulting in more complicated architectures. We instead show how DETR can be turned into a MOT model by employing an instance-level contrastive loss, a revised sampling strategy and a lightweight assignment method. Our training scheme learns object appearances while preserving detection capabilities and with little overhead. Its performance surpasses the previous state-of-the-art by +2.6 mMOTA on the challenging BDD100K dataset and is comparable to existing transformer-based methods on the MOT17 dataset.

关键词： Algorithms Algorithms applications Autonomous Driving 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

Can vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning

Can Vision-Language Models be a Good Guesser? Exploring VLMs...

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Zhang, Gengyuan Zhang, Yurui Zhang, Kerui Tresp, Volker Ludwig Maximilians Univ Munchen Munich Germany Munich Ctr Machine Learning Munich Germany Tech Univ Munich Munich Germany

ISBN: (纸本)9798350318920;9798350318937

vision-Language Models (VLMs) are expected to be capable of reasoning with commonsense knowledge as human beings. One example is that humans can reason where and when an image is taken based on their knowledge. This makes us wonder if, based on visual cues, vision-Language Models that are pre-trained with large-scale image-text resources can achieve and even surpass human capability in reasoning times and location. To address this question, we propose a two-stage RECOGNITION & REASONING probing task applied to discriminative and generative VLMs to uncover whether VLMs can recognize times and location-relevant features and further reason about it. To facilitate the studies, we introduce WikiTiLo, a well-curated image dataset compromising images with rich socio-cultural cues. In extensive evaluation experiments, we find that although VLMs can effectively retain times and location-relevant features in visual encoders, they still fail to make perfect reasoning with context-conditioned visual features. The dataset is available at https://***/gengyuanmax/WikiTiLo.

关键词： Algorithms Algorithms Algorithms Datasets and evaluations Image recognition and understanding vision + language and/or other modalities

来源：评论

学校读者我要写书评

暂无评论

Auto-BPA: An Enhanced Ball-Pivoting Algorithm with Adaptive Radius using Contextual Bandits

Auto-BPA: An Enhanced Ball-Pivoting Algorithm with Adaptive ...

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Saffi, Houda Otberdout, Naima Hmamouche, Youssef Seghrouchni, Amal El Fallah Univ Mohammed VI Polytech Ai Movement Int Artificial Intelligence Ctr Moroc Rabat Morocco Sorbonne Univ LIP6 UMR CNRS 7606 Paris France

ISBN: (纸本)9798350318920;9798350318937

The Ball-Pivoting Algorithm (BPA) is a notable technique for 3D surface reconstruction from point clouds, heavily reliant on the ball radius. In practical application, determining the optimal radius for BPA often necessitates iterative experimentation to achieve better reconstruction quality. BPA entails geometric computations like iterative pivoting, inherently lacking differentiability. In this paper, we tackle the dual challenges of radius selection and non-differentiability in BPA. Inspired by contextual bandits, we propose an innovative approach that learns the optimal radius based on local geometric features within point clouds. We validate our method on the ModelNet10 and ShapeNet datasets, showcasing superior surface reconstruction compared to manual tuning and other classic methods both for low and high point cloud densities. Our code is available at https://github. com/ houda- pixel/ AutoBPA.

关键词： 3D computer vision Algorithms

来源：评论

学校读者我要写书评

暂无评论

A generic and flexible regularization framework for NeRFs

A generic and flexible regularization framework for NeRFs

引用

ieee/CVF Winter conference on applications of computer vision (WACV)

作者： Ehret, Thibaud Mari, Roger Facciolo, Gabriele Univ Paris Saclay Ctr Borelli ENS Paris Saclay CNRS F-91190 Gif Sur Yvette France

ISBN: (纸本)9798350318920;9798350318937

Neural radiance fields, or NeRF, represent a breakthrough in the field of novel view synthesis and 3D modeling of complex scenes from multi-view image collections. Numerous recent works have shown the importance of making NeRF models more robust, by means of regularization, in order to train with possibly inconsistent and/or very sparse data. In this work, we explore how differential geometry can provide elegant regularization tools for robustly training NeRF-like models, which are modified so as to represent continuous and infinitely differentiable functions. In particular, we present a generic framework for regularizing different types of NeRFs observations to improve the performance in challenging conditions. We also show how the same formalism can also be used to natively encourage the regularity of surfaces by means of Gaussian or mean curvatures.

关键词： 3D computer vision Algorithms

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500页 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：