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

4,653 篇 会议
2 篇 期刊文献

馆藏范围

4,655 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,715 篇 工学
- 1,623 篇 计算机科学与技术...
- 182 篇 软件工程
- 142 篇 机械工程
- 133 篇 光学工程
- 41 篇 生物工程
- 29 篇 信息与通信工程
- 18 篇 电气工程
- 9 篇 电子科学与技术（可...
- 9 篇 化学工程与技术
- 9 篇 交通运输工程
- 8 篇 控制科学与工程
- 8 篇 生物医学工程（可授...
- 7 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
- 4 篇 建筑学
- 3 篇 土木工程
- 3 篇 农业工程
173 篇 理学
- 135 篇 物理学
- 42 篇 生物学
- 30 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
- 2 篇 大气科学
14 篇 管理学
- 7 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 3 篇 工商管理
10 篇 医学
- 10 篇 临床医学
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
3 篇 教育学
- 3 篇 教育学
2 篇 农学
1 篇 经济学

主题

2,867 篇 computer vision
1,227 篇 training
1,038 篇 pattern recognit...
870 篇 computational mo...
794 篇 conferences
693 篇 visualization
593 篇 three-dimensiona...
469 篇 codes
460 篇 benchmark testin...
422 篇 semantics
420 篇 computer archite...
349 篇 accuracy
301 篇 adaptation model...
282 篇 feature extracti...
267 篇 transformers
242 篇 cameras
225 篇 diffusion models
223 篇 solid modeling
214 篇 pipelines
210 篇 measurement

机构

72 篇 tsinghua univers...
69 篇 zhejiang univers...
58 篇 university of sc...
57 篇 shanghai jiao to...
52 篇 google research
47 篇 nanyang technolo...
44 篇 national univers...
40 篇 shanghai ai labo...
39 篇 university of ch...
37 篇 adobe research
37 篇 the university o...
37 篇 the chinese univ...
35 篇 stanford univers...
34 篇 harbin institute...
34 篇 shanghai artific...
34 篇 carnegie mellon ...
33 篇 university of el...
30 篇 peng cheng labor...
30 篇 sun yat-sen univ...
29 篇 s-lab nanyang te...

作者

75 篇 timofte radu
24 篇 yu qiao
22 篇 luc van gool
19 篇 ying shan
16 篇 van gool luc
15 篇 radu timofte
14 篇 xin li
13 篇 li xin
12 篇 chen chen
12 篇 zhang zhao
12 篇 boxin shi
11 篇 lizhuang ma
11 篇 fan haoqiang
11 篇 loy chen change
11 篇 zheng-jun zha
11 篇 liu shuaicheng
11 篇 kai zhang
11 篇 marcos v. conde
11 篇 chen wei-ting
11 篇 ziwei liu

语言

4,654 篇 英文
1 篇 中文

检索条件"任意字段=2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024"

共 4655 条记录，以下是991-1000 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：

Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery

Lost in Compression: the Impact of Lossy Image Compression o...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Bhowmik, Neelanjan Barker, Jack W. Gaus, Yona Falinie A. Breckon, Toby P. Univ Durham Dept Comp Sci Durham England Univ Durham Dept Engn Durham England

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression can cause severe decline in performance of deep Convolution Neural Network (CNN) architectures even when mild compression is applied and the resulting compressed imagery is visually identical. In this work, we apply the lossy JPEG compression method with six discrete levels of increasing compression {95, 75, 50, 15, 10, 5} to infrared band (thermal) imagery. Our study quantitatively evaluates the affect that increasing levels of lossy compression has upon the performance of characteristically diverse object detection architectures (Cascade-RCNN, FSAF and Deformable DETR) with respect to varying sizes of objects present in the dataset. When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0.823 with Cascade R-CNN across the FLIR dataset, outperforming prior work. The impact of the lossy compression is more extreme at higher compression levels (15, 10, 5) across all three CNN architectures. However, re-training models on lossy compressed imagery notably ameliorated performances for all three CNN models with an average increment of similar to 76% (at higher compression level 5). Additionally, we demonstrate the relative sensitivity of differing object areas {tiny, small, medium, large} with respect to the compression level. We show that tiny and small objects are more sensitive to compression than medium and large objects. Overall, Cascade R-CNN attains the maximal mAP across most of the object area categories.

关键词： Training Image coding Sensitivity Transform coding Object detection computer architecture Transformers

来源：评论

学校读者我要写书评

暂无评论

t-RAIN: Robust generalization under weather-aliasing label shift attacks

t-RAIN: Robust generalization under weather-aliasing label s...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Marathe, Aboli Prabhu, Sanjana Carnegie Mellon University Machine Learning Department PittsburghPA15213 United States Carnegie Mellon University Department of Electrical and Computer Engineering PittsburghPA15213 United States

ISBN: (纸本)9798350302493

In the classical supervised learning settings, classifiers are fit with the assumption of balanced label distributions and produce remarkable results on the same. In the real world, however, these assumptions often bend and in turn adversely impact model performance. Identifying bad learners in skewed target distributions is even more challenging. Thus achieving model robustness under these "label shift"settings is an important task in autonomous perception. In this paper, we analyze the impact of label shift on the task of multi-weather classification for autonomous vehicles. We use this information as a prior to better assess pedestrian detection in adverse weather. We model the classification performance as an indicator of robustness under 4 label shift scenarios and study the behavior of multiple classes of models. We propose t-RAIN a similarity mapping technique for synthetic data augmentation using large scale generative models and evaluate the performance on DAWN dataset. This mapping boosts model test accuracy by 2.1, 4.4, 1.9, 2.7 % in no-shift, fog, snow, dust shifts respectively. We present state-of-the-art pedestrian detection results on real and synthetic weather domains with best performing 82.69 AP (snow) and 62.31 AP (fog) respectively. © 2023 ieee.

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

CoVIO: Online Continual Learning for Visual-Inertial Odometry

CoVIO: Online Continual Learning for Visual-Inertial Odometr...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Vödisch, Niclas Cattaneo, Daniele Burgard, Wolfram Valada, Abhinav University of Freiburg Germany University of Technology Nuremberg Germany

ISBN: (纸本)9798350302493

Visual odometry is a fundamental task for many applications on mobile devices and robotic platforms. Since such applications are oftentimes not limited to predefined target domains and learning-based vision systems are known to generalize poorly to unseen environments, methods for continual adaptation during inference time are of significant interest. In this work, we introduce CoVIO for online continual learning of visual-inertial odometry. CoVIO effectively adapts to new domains while mitigating catastrophic forgetting by exploiting experience replay. In particular, we propose a novel sampling strategy to maximize image diversity in a fixed-size replay buffer that targets the limited storage capacity of embedded devices. We further provide an asynchronous version that decouples the odometry estimation from the network weight update step enabling continuous inference in real time. We extensively evaluate CoVIO on various real-world datasets demonstrating that it successfully adapts to new domains while outperforming previous methods. The code of our work is publicly available at http://***. © 2023 ieee.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Video Similarity Learning

Self-Supervised Video Similarity Learning

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Kordopatis-Zilos, Giorgos Tolias, Giorgos Tzelepis, Christos Kompatsiaris, Ioannis Patras, Ioannis Papadopoulos, Symeon Czech Technical University VRG FEE Prague Czech Republic Queen Mary University London United Kingdom Information Technologies Institute CERTH Greece

ISBN: (纸本)9798350302493

We introduce S2VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks after fine-tuning. Here, in contrast to prior work, SSL is used to perform video similarity learning and address multiple retrieval and detection tasks at once with no use of labeled data. This is achieved by learning via instance-discrimination with task-tailored augmentations and the widely used InfoNCE loss together with an additional loss operating jointly on self-similarity and hard-negative similarity. We benchmark our method on tasks where video relevance is defined with varying granularity, ranging from video copies to videos depicting the same incident or event. We learn a single universal model that achieves state-of-the-art performance on all tasks, surpassing previously proposed methods that use labeled data. The code and pretrained models are publicly available at: https://***/gkordo/s2vs © 2023 ieee.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning from Synthetic In-vitro Soybean Pods Dataset for In-situ Segmentation of On-branch Soybean Pods

Transfer Learning from Synthetic In-vitro Soybean Pods Datas...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Yang, Si Zheng, Lihua Chen, Xieyuanli Zabawa, Laura Zhang, Man Wang, Minjuan China Agr Univ Coll Informat & Elect Engn Beijing Peoples R China China Agr Univ Minist Educ Key Lab Smart Agr Syst Beijing Peoples R China Univ Bonn Inst Geodesy & Geoinformat Bonn Germany

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The mature soybean plants are of complex architecture with pods frequently touching each other, posing a challenge for in-situ segmentation of on-branch soybean pods. Deep learning-based methods can achieve accurate training and strong generalization capabilities, but it demands massive labeled data, which is often a limitation, especially for agricultural applications. As lacking the labeled data to train an in-situ segmentation model for on-branch soybean pods, we propose a transfer learning from synthetic in-vitro soybean pods. First, we present a novel automated image generation method to rapidly generate a synthetic in-vitro soybean pods dataset with plenty of annotated samples. The in-vitro soybean pods samples are overlapped to simulate the frequently physically touching of on-branch soybean pods. Then, we design a two-step transfer learning. In the first step, we finetune an instance segmentation network pretrained by a source domain (MS COCO dataset) with a synthetic target domain (in-vitro soybean pods dataset). In the second step, transferring from simulation to reality is performed by finetuning on a few real-world mature soybean plant samples. The experimental results show the effectiveness of the proposed two-step transfer learning method, such that AP50 was 0.80 for the real-world mature soybean plant test dataset, which is higher than that of direct adaptation and its AP50 was 0.77. Furthermore, the visualizations of in-situ segmentation results of on-branch soybean pods show that our method performs better than other methods, especially when soybean pods overlap densely.

关键词： Deep learning Transfer learning computer vision Instance segmentation Plant phenotyping

来源：评论

学校读者我要写书评

暂无评论

BinaryViT: Pushing Binary vision Transformers Towards Convolutional Models

BinaryViT: Pushing Binary Vision Transformers Towards Convol...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Le, Phuoc-Hoan Charles Li, Xinlin Huawei Noah's Ark Lab Montreal Research Center Canada Huawei Noah's Ark Lab Canada

ISBN: (纸本)9798350302493

With the increasing popularity and the increasing size of vision transformers (ViTs), there has been an increasing interest in making them more efficient and less computationally costly for deployment on edge devices with limited computing resources. Binarization can be used to help reduce the size of ViT models and their computational cost significantly, using popcount operations when the weights and the activations are in binary. However, ViTs suffer a larger performance drop when directly applying convolutional neural network (CNN) binarization methods or existing binarization methods to binarize ViTs compared to CNNs on datasets with a large number of classes such as ImageNet-1k. With extensive analysis, we find that binary vanilla ViTs such as DeiT miss out on a lot of key architectural properties that CNNs have that allow binary CNNs to have much higher representational capability than binary vanilla ViT. Therefore, we propose BinaryViT, in which inspired by the CNN architecture, we include operations from the CNN architecture into a pure ViT architecture to enrich the representational capability of a binary ViT without introducing convolutions. These include an average pooling layer instead of a token pooling layer, a block that contains multiple average pooling branches, an affine transformation right before the addition of each main residual connection, and a pyramid structure. Experimental results on the ImageNet-1k dataset show the effectiveness of these operations that allow a fully-binary pure ViT model to be competitive with previous state-of-the-art binary (SOTA) CNN models. © 2023 ieee.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach based on Dynamic Mode Decomposition for Efficient Encoding of Dynamic Light Fields

A Data-Driven Approach based on Dynamic Mode Decomposition f...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Ravishankar, Joshitha Khaidem, Sally Sharma, Mansi Indian Institute of Technology Madras Department of Electrical Engineering India Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350302493

Dynamic light fields provide a richer, more realistic 3D representation of a moving scene. However, this leads to higher data rates since excess storage and transmission requirements are needed. We propose a novel approach to efficiently represent and encode dynamic light field data for display applications based on dynamic mode decomposition (DMD). Acquired images are firstly obtained through optimized coded aperture patterns for each temporal frame/camera viewpoint of a dynamic light field. The underlying spatial, angular, and temporal correlations are effectively exploited by a data-driven DMD on these acquired images arranged as time snapshots. Next, High Efficiency Video Coding (HEVC) removes redundancies in light field data, including intra-frame and inter-frame redundancies, while maintaining high reconstruction quality. The proposed scheme is the first of its kind to treat light field videos as mathematical dynamical systems, leverage on dynamic modes of acquired images, and gain flexible coding at various bitrates. Experimental results demonstrate our scheme's superior compression efficiency and bitrate savings compared to the direct encoding of acquired images using HEVC codec. © 2023 ieee.

关键词： Dynamic mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Robustness of Visual Explanations to Common Data Augmentation Methods

Robustness of Visual Explanations to Common Data Augmentatio...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Tětková, Lenka Hansen, Lars Kai Technical University of Denmark Department of Applied Mathematics and Computer Science Richard Petersens Plads 321 Lyngby2800 Kgs. Denmark

ISBN: (纸本)9798350302493

As the use of deep neural networks continues to grow, understanding their behaviour has become more crucial than ever. Post-hoc explainability methods are a potential solution, but their reliability is being called into question. Our research investigates the response of post-hoc visual explanations to naturally occurring transformations, often referred to as augmentations. We anticipate explanations to be invariant under certain transformations, such as changes to the colour map while responding in an equivariant manner to transformations like translation, object scaling, and rotation. We have found remarkable differences in robustness depending on the type of transformation, with some explainability methods (such as LRP composites and Guided Backprop) being more stable than others. We also explore the role of training with data augmentation. We provide evidence that explanations are typically less robust to augmentation than classification performance, regardless of whether data augmentation is used in training or not. © 2023 ieee.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework

OpenFed: A Comprehensive and Versatile Open-Source Federated...

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Chen, Dengsheng Tan, Vince Junkai Lu, Zhilin Wu, Enhua Hu, Jie Meituan China Bytedance Inc. China Tsinghua University China University of Macau China State Key Lab of Computer Science Iscas China University of Chinese Academy of Sciences China

ISBN: (纸本)9798350302493

Recent developments in Artificial Intelligence techniques have enabled their successful application across a spectrum of commercial and industrial settings. However, these techniques require large volumes of data to be aggregated in a centralized manner, forestalling their applicability to scenarios wherein the data is sensitive or the cost of data transmission is prohibitive. Federated Learning alleviates these problems by decentralizing model training, thereby removing the need for data transfer and aggregation. To advance the adoption of Federated Learning, more research and development needs to be conducted to address some important open questions. In this work, we propose OpenFed, an open-source software framework for end-to-end Federated Learning. OpenFed reduces the barrier to entry for both researchers and downstream users of Federated Learning by the targeted removal of existing pain points. For researchers, OpenFed provides a framework wherein new methods can be easily implemented and fairly evaluated against an extensive suite of benchmarks. For downstream users, OpenFed allows Federated Learning to be plugged and play within different subject-matter contexts, removing the need for deep expertise in Federated Learning. The source code of OpenFed is publicly available online at https://***/FederalLab/OpenFed. © 2023 ieee.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Towards Real-Time 4K Image Super-Resolution

Towards Real-Time 4K Image Super-Resolution

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Zamfir, Eduard Conde, Marcos V. Timofte, Radu University of Würzburg Computer Vision Lab Caidas Ifi Germany

ISBN: (纸本)9798350302493

Over the past few years, high-definition videos and images in 720p (HD), 1080p (FHD), and 4K (UHD) resolution have become standard. While higher resolutions offer improved visual quality for users, they pose a significant challenge for super-resolution networks to achieve real-time performance on commercial GPUs. This paper presents a comprehensive analysis of super-resolution model designs and techniques aimed at efficiently upscaling images from 720p and 1080p resolutions to 4K. We begin with a simple, effective baseline architecture and gradually modify its design by focusing on extracting important high-frequency details efficiently. This allows us to subsequently downscale the resolution of deep feature maps, reducing the overall computational footprint, while maintaining high reconstruction fidelity. We enhance our method by incorporating pixel-unshuffling, a simplified and speed-up reinterpretation of the basic block proposed by NAFNet, along with structural re-parameterization. We assess the performance of the fastest version of our method in the new NTIRE 2023 Real-Time 4K Super-Resolution challenge and demonstrate its potential in comparison with state-of-the-art efficient super-resolution models when scaled up. Our method was tested successfully on high-quality content from photography, digital art, and gaming content. © 2023 ieee.

关键词： Optical resolving power

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466页 << < 96 97 98 99 100 101 102 103 104 105 > >>

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：