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

50,667 篇 会议
1,420 册 图书
1,040 篇 期刊文献
1 篇 学位论文

馆藏范围

53,125 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,959 篇 工学
- 24,945 篇 计算机科学与技术...
- 12,662 篇 软件工程
- 5,168 篇 光学工程
- 4,781 篇 电气工程
- 4,528 篇 信息与通信工程
- 4,271 篇 机械工程
- 4,075 篇 控制科学与工程
- 2,477 篇 生物工程
- 1,730 篇 生物医学工程（可授...
- 1,597 篇 仪器科学与技术
- 1,330 篇 电子科学与技术（可...
- 796 篇 化学工程与技术
- 724 篇 安全科学与工程
- 567 篇 交通运输工程
- 383 篇 建筑学
- 335 篇 土木工程
11,916 篇 理学
- 6,479 篇 物理学
- 5,450 篇 数学
- 2,763 篇 生物学
- 1,922 篇 统计学（可授理学、...
- 838 篇 化学
- 668 篇 系统科学
5,349 篇 医学
- 5,118 篇 临床医学
- 727 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,416 篇 管理学
- 1,991 篇 图书情报与档案管...
- 1,595 篇 管理科学与工程(可...
- 484 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
438 篇 法学
- 411 篇 社会学
298 篇 农学
202 篇 教育学
165 篇 经济学
70 篇 文学
49 篇 军事学

主题

17,437 篇 computer vision
9,033 篇 pattern recognit...
4,198 篇 training
3,834 篇 feature extracti...
3,136 篇 cameras
2,873 篇 computational mo...
2,791 篇 image segmentati...
2,623 篇 visualization
2,576 篇 shape
2,538 篇 face recognition
2,177 篇 robustness
2,125 篇 computer science
1,983 篇 object detection
1,960 篇 computer archite...
1,882 篇 layout
1,855 篇 object recogniti...
1,801 篇 three-dimensiona...
1,724 篇 neural networks
1,706 篇 humans
1,699 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
135 篇 national laborat...
105 篇 univ sci & techn...
104 篇 zhejiang univers...
103 篇 shanghai jiao to...
94 篇 university of sc...
94 篇 microsoft resear...
85 篇 zhejiang univ pe...
84 篇 shanghai ai lab ...
74 篇 school of comput...
69 篇 computer vision ...
68 篇 peking univ peop...
68 篇 chinese acad sci...
65 篇 chinese univ hon...
63 篇 institute of inf...
62 篇 google res mount...
61 篇 univ oxford oxfo...
59 篇 univ toronto on
57 篇 swiss fed inst t...

作者

92 篇 van gool luc
86 篇 umapada pal
77 篇 zhang lei
64 篇 lee seong-whan
50 篇 vittorio murino
42 篇 yang yi
34 篇 nassir navab
33 篇 ling haibin
33 篇 li xin
33 篇 jie yang
32 篇 liu yang
31 篇 escalera sergio
31 篇 loy chen change
30 篇 h. bischof
29 篇 zhou jie
29 篇 vasconcelos nuno
29 篇 jan-michael frah...
28 篇 blumenstein mich...
27 篇 jia yunde
27 篇 luo ping

语言

50,125 篇 英文
2,767 篇 其他
253 篇 中文
22 篇 土耳其文
4 篇 西班牙文
2 篇 日文
2 篇 葡萄牙文
2 篇 俄文

检索条件"任意字段=IEEE Conference on Computer Vision and Pattern Recognition"

共 53128 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：

Discriminative pattern Calibration Mechanism for Source-Free Domain Adaptation

Discriminative Pattern Calibration Mechanism for Source-Free...

引用

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

作者： Xia, Haifeng Xia, Siyu Ding, Zhengming Southeast Univ Sch Automat Dhaka Bangladesh Tulane Univ Dept Comp Sci New Orleans LA 70118 USA

ISBN: (纸本)9798350353006

Source-free domain adaptation (SFDA) assumes that model adaptation only accesses the well-learned source model and unlabeled target instances for knowledge transfer. However, cross-domain distribution shift easily triggers invalid discriminative semantics from source model on recognizing the target samples. Hence, understanding the specific content of discriminative pattern and adjusting their representation in target domain become the important key to overcome SFDA. To achieve such a vision, this paper proposes a novel explanation paradigm "Discriminative pattern Calibration (DPC)" mechanism on solving SFDA issue. Concretely, DPC first utilizes learning network to infer the discriminative regions on the target images and specifically emphasizes them in feature space to enhance their representation. Moreover, DPC relies on the attention-reversed mixup mechanism to augment more samples and improve the robustness of the classifier. Considerable experimental results and studies suggest that the effectiveness of our DPC in enhancing the performance of existing SFDA baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Style Aligned Image Generation via Shared Attention

Style Aligned Image Generation via Shared Attention

引用

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

作者： Hertz, Amir Voynov, Andrey Fruchter, Shlomi Cohen-Or, Daniel Google Res Mountain View CA 94043 USA Tel Aviv Univ Tel Aviv Israel

ISBN: (纸本)9798350353013;9798350353006

Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts. However, controlling these models to ensure consistent style remains challenging, with existing methods necessitating fine-tuning and manual intervention to disentangle content and style. In this paper, we introduce StyleAligned, a novel technique designed to establish style alignment among a series of generated images. By employing minimal 'attention sharing' during the diffusion process, our method maintains style consistency across images within T2I models. This approach allows for the creation of style-consistent images using a reference style through a straightforward inversion operation. Our method's evaluation across diverse styles and text prompts demonstrates high-quality synthesis and fidelity, underscoring its efficacy in achieving consistent style across various inputs.

关键词： computer vision Generative models Machine Learning Style Transfer

来源：评论

学校读者我要写书评

暂无评论

Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data

Good at captioning, bad at counting: Benchmarking GPT-4V on ...

引用

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

作者： Zhang, Chenhui Wang, Sherrie MIT Inst Data Syst & Soc 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (纸本)9798350365474

Large vision-Language Models (VLMs) have demonstrated impressive performance on complex tasks involving visual input with natural language instructions. However, it remains unclear to what extent capabilities on natural images transfer to Earth observation (EO) data, which are predominantly satellite and aerial images less common in VLM training data. In this work, we propose a comprehensive benchmark to gauge the progress of VLMs toward being useful tools for EO data by assessing their abilities on scene understanding, localization and counting, and change detection. Motivated by real-world applications, our benchmark includes scenarios like urban monitoring, disaster relief, land use, and conservation. We discover that, although state-of-the-art VLMs like GPT-4V possess world knowledge that leads to strong performance on location understanding and image captioning, their poor spatial reasoning limits usefulness on object localization and counting. Our benchmark is publicly available on this website. A full version of this paper can be found here.

关键词： benchmark Earth observation foundation model vision-language model

来源：评论

学校读者我要写书评

暂无评论

FairDeDup: Detecting and Mitigating vision-Language Fairness Disparities in Semantic Dataset Deduplication

FairDeDup: Detecting and Mitigating Vision-Language Fairness...

引用

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

作者： Slyman, Eric Lee, Stefan Cohen, Scott Kafle, Kushal Oregon State Univ Dept EECS Corvallis OR 97331 USA Adobe Res San Francisco CA 94107 USA

ISBN: (纸本)9798350353006

Worst-GroupRecent dataset deduplication techniques have demonstrated that content-aware dataset pruning can dramatically reduce the cost of training vision-Language Pre-trained (VLP) models without significant performance losses compared to training on the original dataset. These results have been based on pruning commonly used image-caption datasets collected from the web - datasets that are known to harbor harmful social biases that may then be codified in trained models. In this work, we evaluate how deduplication affects the prevalence of these biases in the resulting trained models and introduce an easy-to-implement modification to the recent SemDeDup algorithm that can reduce the negative effects that we observe. When examining CLIP-style models trained on deduplicated variants of LAION-400M, we find our proposed FairDeDup algorithm consistently leads to improved fairness metrics over SemDeDup on the FairFace and FACET datasets while maintaining zero-shot performance on CLIP benchmarks.

关键词： deduplication fairness foundation models human-centered ai language multimodal pretraining vision vision-language

来源：评论

学校读者我要写书评

暂无评论

Semantic Shield: Defending vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

Semantic Shield: Defending Vision-Language Models Against Ba...

引用

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

作者： Ishmam, Alvi Md Thomas, Christopher Virginia Tech Blacksburg VA 24061 USA

ISBN: (纸本)9798350353006

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential security threats, such as backdooring and poisoning attacks. In this paper, we propose a method for mitigating such attacks on contrastively trained vision-language models. Our approach leverages external knowledge extracted from a language model to prevent models from learning correlations between image regions which lack strong alignment with external knowledge. We do this by imposing constraints to enforce that attention paid by the model to visual regions is proportional to the alignment of those regions with external knowledge. We conduct extensive experiments using a variety of recent backdooring and poisoning attacks on multiple datasets and architectures. Our results clearly demonstrate that our proposed approach is highly effective at defending against such attacks across multiple settings, while maintaining model utility and without requiring any changes at inference time.

关键词： Adversarial attack and defense vision languge model

来源：评论

学校读者我要写书评

暂无评论

HaLViT: Half of the Weights are Enough

HaLViT: Half of the Weights are Enough

引用

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

作者： Koyun, Onur Can Toreyin, Behcet Ugur Istanbul Tech Univ Dept Artificial Intelligence & Data Engn Signal Proc Computat Intelligence Res Grp SP4CING Inst Informat Istanbul Turkiye

ISBN: (纸本)9798350365474

Deep learning architectures like Transformers and Convolutional Neural Networks (CNNs) have led to ground-breaking advances across numerous fields. However, their extensive need for parameters poses challenges for implementation in environments with limited resources. In our research, we propose a strategy that focuses on the utilization of the column and row spaces of weight matrices, significantly reducing the number of required model parameters without substantially affecting performance. This technique is applied to both Bottleneck and Attention layers, achieving a notable reduction in parameters with minimal impact on model efficacy. Our proposed model, HaLViT, exemplifies a parameter-efficient vision Transformer. Through rigorous experiments on the ImageNet dataset and COCO dataset, HaLViT's performance validates the effectiveness of our method, offering results comparable to those of conventional models.

关键词： CNN computer vision deep learning Efficient Parameter Transformer vision Transformer ViT

来源：评论

学校读者我要写书评

暂无评论

SkipPLUS: Skip the First Few Layers to Better Explain vision Transformers

SkipPLUS: Skip the First Few Layers to Better Explain Vision...

引用

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

作者： Mehri, Faridoun Fayyaz, Mohsen Baghshah, Mahdieh Soleymani Pilehvar, Mohammad Taher Sharif Univ Technol Tehran Iran Univ Tehran Tehran Iran Cardiff Univ Cardiff Wales

ISBN: (纸本)9798350365474

Despite their remarkable performance, the explainability of vision Transformers (ViTs) remains a challenge. While forward attention-based token attribution techniques have become popular in text processing, their suitability for ViTs hasn't been extensively explored. In this paper, we compare these methods against state-of-the-art input attribution methods from the vision literature, revealing their limitations due to improper aggregation of information across layers. To address this, we introduce two general techniques, PLUS and SkipPLUS, that can be composed with any input attribution method to more effectively aggregate information across layers while handling noisy layers. Through comprehensive and quantitative evaluations of faithfulness and human interpretability on a variety of ViT architectures and datasets, we demonstrate the effectiveness of PLUS and SkipPLUS, establishing a new state-of-the-art in white-box token attribution. We conclude with a comparative analysis highlighting the strengths and weaknesses of the best versions of all the studied methods. The code used in this paper is freely available at https://***/NightMachinery/SkipPLUS-CVPR-2024.

关键词： Explainable AI Forward Attention-Based Token Attribution Interpretability Neural Network Visualization vision Transformers White-Box Input Attribution Methods xAI

来源：评论

学校读者我要写书评

暂无评论

Can Biases in ImageNet Models Explain Generalization?

Can Biases in ImageNet Models Explain Generalization?

引用

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

作者： Gavrikov, Paul Keuper, Janis Offenburg Univ IMLA Offenburg Germany Univ Mannheim Mannheim Germany

ISBN: (纸本)9798350353006

The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning methods. For image classification, this manifests in the existence of adversarial attacks, the performance drops on distorted images, and a lack of generalization to concepts such as sketches. The current understanding of generalization in neural networks is very limited, but some biases that differentiate models from human vision have been identified and might be causing these limitations. Consequently, several attempts with varying success have been made to reduce these biases during training to improve generalization. We take a step back and sanity-check these attempts. Fixing the architecture to the well-established ResNet-50, we perform a large-scale study on 48 ImageNet models obtained via different training methods to understand how and if these biases - including shape bias, spectral biases, and critical bands - interact with generalization. Our extensive study results reveal that contrary to previous findings, these biases are insufficient to accurately predict the generalization of a model holistically. We provide access to all checkpoints and evaluation code at https://***/paulgavrikov/biases_vs_generalization/

关键词： bias computer vision generalization imagenet robustness

来源：评论

学校读者我要写书评

暂无评论

A stroke of genius: Predicting the next move in badminton

A stroke of genius: Predicting the next move in badminton

引用

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

作者： Ibh, Magnus Grasshof, Stella Hansen, Dan Witzner IT Univ Copenhagen Machine Learning Grp Copenhagen Denmark

ISBN: (纸本)9798350365474

This paper presents, RallyTemPose, a transformer encoder-decoder model for predicting future badminton strokes based on previous rally actions. The model uses court position, skeleton poses, and player-specific embeddings to learn stroke and player-specific latent representations in a spatiotemporal encoder module. The representations are then used to condition the subsequent strokes in a decoder module through rally-aware fusion blocks, which provide additional relevant strategic and technical considerations to make more informed predictions. RallyTemPose shows improved forecasting accuracy compared to traditional sequential methods on two real-world badminton datasets. The performance boost can also be attributed to the inclusion of improved stroke embeddings extracted from the latent representation of a pre-trained large-language model subjected to detailed text descriptions of stroke descriptions. In the discussion, the latent representations learned by the encoder module show useful properties regarding player analysis and comparisons. The code can be found at: This https url.

关键词： Action Forecasting computer vision Encoder-Decoder Skeleton-data Sports Application

来源：评论

学校读者我要写书评

暂无评论

Adapters Strike Back

Adapters Strike Back

引用

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

作者： Steitz, Jan-Martin Roth, Stefan Tech Univ Darmstadt Dept Comp Sci Darmstadt Germany Hessian AI Darmstadt Germany

ISBN: (纸本)9798350353006

Adapters provide an efficient and lightweight mechanism for adapting trained transformer models to a variety of different tasks. However, they have often been found to be outperformed by other adaptation mechanisms including low-rank adaptation. In this paper, we provide an in-depth study of adapters, their internal structure, as well as various implementation choices. We uncover pitfalls for using adapters and suggest a concrete, improved adapter architecture, called Adapter+, that not only outperforms previous adapter implementations but surpasses a number of other, more complex adaptation mechanisms in several challenging settings. Despite this, our suggested adapter is highly robust and, unlike previous work, requires little to no manual intervention when addressing a novel scenario. Adapter+ reaches state-of-the-art average accuracy on the VTAB benchmark, even without a per-task hyperparameter optimization.(1)

关键词： adapters deep learning image classification parameter-efficient transfer learning transfer learning vision transformer

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：