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291-300 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：

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained vision Transformers

Calibrating Higher-Order Statistics for Few-Shot Class-Incre...

引用

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

作者： Goswami, Dipam Twardowski, Bartlomiej van de Weijer, Joost Univ Autonoma Barcelona Dept Comp Sci Barcelona Spain Comp Vis Ctr Barcelona Spain IDEAS NCBR Warsaw Poland

ISBN: (纸本)9798350365474

Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from very few data (5 samples) without forgetting the previously learned classes. Recent works in many-shot CIL (MSCIL) (using all available training data) exploited pre-trained models to reduce forgetting and achieve better plasticity. In a similar fashion, we use ViT models pre-trained on large-scale datasets for few-shot settings, which face the critical issue of low plasticity. FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards. While the focus of most recent studies is on how to learn the many-shot first task so that the model generalizes to all future few-shot tasks, we explore in this work how to better model the few-shot data using pre-trained models, irrespective of how the first task is trained. Inspired by recent works in MSCIL, we explore how using higher-order feature statistics can influence the classification of few-shot classes. We identify the main challenge of obtaining a good covariance matrix from few-shot data and propose to calibrate the covariance matrix for new classes based on semantic similarity to the many-shot base classes. Using the calibrated feature statistics in combination with existing methods significantly improves few-shot continual classification on several FSCIL benchmarks. Code is available at https://***/dipamgoswami/FSCIL-Calibration.

关键词： Continual Learning Few-Shot Class-Incremental Learning

来源：评论

学校读者我要写书评

暂无评论

Semantically Grounded Visual Embeddings for Zero-Shot Learning

Semantically Grounded Visual Embeddings for Zero-Shot Learni...

引用

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

作者： Nawaz, Shah Cavazza, Jacopo Del Bue, Alessio Ist Italiano Tecnol IIT Pattern Anal & Comp Vis PAVIS Genoa Italy Ist Italiano Tecnol IIT Visual Geometry & Modelling VGM Genoa Italy Deutsch Elektronen Synchrotron DESY Hamburg Germany

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learning frameworks as such disjoint embeddings fail to adequately associate visual and textual information to their shared semantic content. Therefore, we propose to learn semantically grounded and enriched visual information by computing a joint image and text model with a two-stream network on a proxy task. To improve this alignment between image and textual representations, provided by attributes, we leverage ancillary captions to provide grounded semantic information. Our method, dubbed joint embeddings for zero-shot learning is evaluated on several benchmark datasets, improving the performance of existing state-of-the-art methods in both standard (+1.6% on aPY, +2.6% on FLO) and generalized (+2.1% on AWA2, +2.2% on CUB) zero-shot recognition.

关键词： Learning systems Visualization Computational modeling Soft sensors conferences Semantics Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Multi-task Learning for Object Detection and Saliency Estimation

Cross-Domain Multi-task Learning for Object Detection and Sa...

引用

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

作者： Khattar, Apoorv Hegde, Srinidhi Hebbalaguppe, Ramya TCS Res Mumbai Maharashtra India

ISBN: (纸本)9781665448994

Multi-task learning (MTL) is a learning paradigm that aims at joint optimization of multiple tasks using a single neural network for better performance and generalization. In practice, MTL rests on the inherent assumption of availability of common datasets with ground truth labels for each of the downstream tasks. However, collecting such a common annotated dataset is laborious for complex computer vision tasks such as the saliency estimation which would require the eye fixation points as the ground truth data. To this end, we propose a novel MTL framework in the absence of common annotated dataset for joint estimation of important downstream tasks in computer vision - object detection and saliency estimation. Unlike many state-of-the-art methods, that rely on common annotated datasets for training, we consider the annotations from different datasets for jointly training different tasks, calling this setting as cross-domain MTL. We adapt MUTAN [3] framework to fuse features from different datasets to learn domain invariant features capturing the relatedness of different tasks. We demonstrate the improvement in the performance and generalizability of our MTL architecture. We also show that the proposed MTL network offers a 13% reduction in memory footprint due to parameter sharing between the related tasks.

关键词： Training computer vision Neural networks Estimation Object detection computer architecture pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SymDNN: Simple & Effective Adversarial Robustness for Embedded Systems

SymDNN: Simple & Effective Adversarial Robustness for Embedd...

引用

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

作者： Dey, Swarnava Dasgupta, Pallab Chakrabarti, Partha P. Indian Inst Technol Kharagpur Kharagpur 721302 W Bengal India

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We propose SymDNN, a Deep Neural Network (DNN) inference scheme, to segment an input image into small patches, replace those patches with representative symbols, and use the reconstructed image for CNN inference. This approach of deconstruction of images, and the reconstruction from cluster centroids trained on clean images, enhances robustness against adversarial attacks. The input transform used in SymDNN is learned from very large datasets, making it difficult to approximate for adaptive adversarial attacks. For example, SymDNN achieves 23% and 42% robust accuracy at L-infinity attack strengths of 8/255 and 4/255 respectively, against BPDA under a complete white box setting, where most input processing based defenses break completely. SymDNN is not a future-proof adversarial defense that can defend any attack, but it is one of the few readily usable defenses in resource-limited embedded systems that defends against a wide range of attacks.

关键词： computer vision Adaptation models Visualization Embedded systems Computational modeling Symbols Transforms

来源：评论

学校读者我要写书评

暂无评论

Multimodal Shape Completion via Implicit Maximum Likelihood Estimation

Multimodal Shape Completion via Implicit Maximum Likelihood ...

引用

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

作者： Arora, Himanshu Mishra, Saurabh Peng, Shichong Li, Ke Mahdavi-Amiri, Ali Simon Fraser Univ Burnaby BC Canada

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Shape completion is the problem of completing partial input shapes such as partial scans. This problem finds important applications in computer vision and robotics due to issues such as occlusion or sparsity in real-world data. However, most of the existing research related to shape completion has been focused on completing shapes by learning a one-to-one mapping which limits the diversity and creativity of the produced results. We propose a novel multimodal shape completion technique that is effectively able to learn a one-to-many mapping and generates diverse complete shapes. Our approach is based on the conditional Implicit Maximum Likelihood Estimation (IMLE) technique wherein we condition our inputs on partial 3D point clouds. We extensively evaluate our approach by comparing it to various baselines both quantitatively and qualitatively. We show that our method is superior to alternatives in terms of completeness and diversity of shapes.

关键词： Point cloud compression Maximum likelihood estimation computer vision Three-dimensional displays Shape conferences pattern recognition

来源：评论

学校读者我要写书评

暂无评论

When Kernel Methods meet Feature Learning: Log-Covariance Network for Action recognition from Skeletal Data 30

When Kernel Methods meet Feature Learning: Log-Covariance Ne...

引用

30th ieee/cvf conference on computer vision and pattern recognition workshops (cvprw)

作者： Cavazza, Jacopo Morerio, Pietro Murino, Vittorio Ist Italiano Tecnol Pattern Anal & Comp Vis PAVIS Genoa Italy Univ Genoa Electr Elect & Telecommun Engn Naval Architecture Genoa Italy Univ Verona Comp Sci Dept Verona Italy

ISBN: (纸本)9781538607336

Human action recognition from skeletal data is a hot research topic and important in many open domain applications of computer vision, thanks to recently introduced 3D sensors. In the literature, naive methods simply transfer off-the-shelf techniques from video to the skeletal representation. However, the current state-of-the-art is contended between to different paradigms: kernel-based methods and feature learning with (recurrent) neural networks. Both approaches show strong performances, yet they exhibit heavy, but complementary, drawbacks. Motivated by this fact, our work aims at combining together the best of the two paradigms, by proposing an approach where a shallow network is fed with a covariance representation. Our intuition is that, as long as the dynamics is effectively modeled, there is no need for the classification network to be deep nor recurrent in order to score favorably. We validate this hypothesis in a broad experimental analysis over 6 publicly available datasets.

关键词： Estimation Field programmable gate arrays OFDM Modulation Filtration Clocks Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Manipulation Detection in Satellite Images Using vision Transformer

Manipulation Detection in Satellite Images Using Vision Tran...

引用

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

作者： Horvath, Janos Baireddy, Sriram Hao, Hanxiang Montserrat, Daniel Mas Delp, Edward J. Purdue Univ Sch Elect & Comp Engn Video & Image Proc Lab VIPER W Lafayette IN 47907 USA

ISBN: (纸本)9781665448994

A growing number of commercial satellite companies provide easily accessible satellite imagery. Overhead imagery is used by numerous industries including agriculture, forestry, natural disaster analysis, and meteorology. Satellite images, just as any other images, can be tampered with image manipulation tools. Manipulation detection methods created for images captured by "consumer cameras" tend to fail when used on satellite images due to the differences in image sensors, image acquisition, and processing. In this paper we propose an unsupervised technique that uses a vision Transformer to detect spliced areas within satellite images. We introduce a new dataset which includes manipulated satellite images that contain spliced objects. We show that our proposed approach performs better than existing unsupervised splicing detection techniques.

关键词： Image sensors computer vision Satellites Splicing conferences Forestry Tools

来源：评论

学校读者我要写书评

暂无评论

Occlusion Guided Scene Flow Estimation on 3D Point Clouds

Occlusion Guided Scene Flow Estimation on 3D Point Clouds

引用

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

作者： Ouyang, Bojun Raviv, Dan Tel Aviv Univ Tel Aviv Israel

ISBN: (纸本)9781665448994

3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a new scene flow architecture called OGSF-Net which tightly couples the learning for both flow and occlusions between frames. Their coupled symbiosis results in a more accurate prediction of flow in space. Unlike a traditional multi-action network, our unified approach is fused throughout the network, boosting performances for both occlusion detection and flow estimation. Our architecture is the first to gauge the occlusion in 3D scene flow estimation on point clouds. In key datasets such as Flyingthings3D and KITTI, we achieve the state-of-the-art results.(1,2)

关键词： Symbiosis Measurement Deep learning Three-dimensional displays Estimation computer architecture Tools

来源：评论

学校读者我要写书评

暂无评论

Continual Hippocampus Segmentation with Transformers

Continual Hippocampus Segmentation with Transformers

引用

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

作者： Ranem, Amin Gonzalez, Camila Mukhopadhyay, Anirban Tech Univ Darmstadt GRIS Karolinenpl 5 D-64289 Darmstadt Germany

ISBN: (纸本)9781665487399

In clinical settings, where acquisition conditions and patient populations change over time, continual learning is key for ensuring the safe use of deep neural networks. Yet most existing work focuses on convolutional architectures and image classification. Instead, radiologists prefer to work with segmentation models that outline specific regions-of-interest, for which Transformer-based architectures are gaining traction. The self-attention mechanism of Transformers could potentially mitigate catastrophic forgetting, opening the way for more robust medical image segmentation. In this work, we explore how recently-proposed Transformer mechanisms for semantic segmentation behave in sequential learning scenarios, and analyse how best to adapt continual learning strategies for this setting. Our evaluation on hippocampus segmentation shows that Transformer mechanisms mitigate catastrophic forgetting for medical image segmentation compared to purely convolutional architectures, and demonstrates that regularising ViT modules should be done with caution.

关键词： Image segmentation Semantics Sociology computer architecture Artificial neural networks Transformers Task analysis

来源：评论

学校读者我要写书评

暂无评论

DarkLight Networks for Action recognition in the Dark

DarkLight Networks for Action Recognition in the Dark

引用

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

作者： Chen, Rui Chen, Jiajun Liang, Zixi Gao, Huaien Lin, Shan Guangzhou Xi Ma Informat Technol Co 101 Waihuan Xi Rd Guangzhou 510006 Guangdong Peoples R China

ISBN: (纸本)9781665448994

Human action recognition in the dark is a significant task with various applications, e.g., night surveillance and self-driving at night. However, the lack of video datasets for human actions in the dark hinders its development. Recently, a public dataset ARID has been introduced to stimulate progress for the task of human action recognition in dark videos. Currently, there are multiple models that perform well for action recognition in videos shot under normal illumination. However, research shows that these methods may not be effective in recognizing actions in dark videos. In this paper, we construct a novel neural network architecture: DarkLight Networks, which involves (i) a dual-pathway structure where both dark videos and its brightened counterpart are utilized for effective video representation;and (ii) a self-attention mechanism, which fuses and extracts corresponding and complementary features from the two pathways. Our approach achieves state-of-the-art results on ARID.

关键词： computer vision Fuses Surveillance conferences Neural networks Lighting Feature extraction

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 << < 26 27 28 29 30 31 32 33 34 35 > >>

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：