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741-750 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：

Long-term Action Forecasting Using Multi-headed Attention-based Variational Recurrent Neural Networks

Long-term Action Forecasting Using Multi-headed Attention-ba...

引用

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

作者： Loh, Siyuan Brandon Roy, Debaditya Fernando, Basura ASTAR IHPC SCC Singapore Singapore ASTAR IHPC CFAR Singapore Singapore

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Systems developed for predicting both the action and the amount of time someone might take to perform that action need to be aware of the inherent uncertainty in what humans do. Here, we present a novel hybrid generative model for action anticipation that attempts to capture the uncertainty in human actions. Our model uses a multi-headed attention-based variational generative model for action prediction (MAVAP), and Gaussian log-likelihood maximization to predict the corresponding action's duration. During training, we optimise three losses: a variational loss, a negative log-likelihood loss, and a discriminative cross-entropy loss. We evaluate our model on benchmark datasets (i.e., Breakfast and 50Salads) for action forecasting tasks and demonstrate improvements over prior methods using both ground truth observations and predicted features from an action segmentation network (i.e., MS-TCN++). We also show that factorizing the latent space across multiple Gaussian heads predicts better plausible future action sequences compared to a single Gaussian.

关键词： Training computer vision Uncertainty Recurrent neural networks conferences Predictive models Hybrid power systems

来源：评论

学校读者我要写书评

暂无评论

Pseudo-label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection

Pseudo-label Generation and Various Data Augmentation for Se...

引用

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

作者： Yu, Jun Zhang, Liwen Du, Shenshen Chang, Hao Lu, Keda Zhang, Zhong Yu, Ye Wang, Lei Ling, Qiang Univ Sci & Technol China Hefei Anhui Peoples R China Hefei ZhanDa Intelligence Technol Co Ltd Hefei Anhui Peoples R China Hefei Univ Technol Hefei Anhui Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Semi-supervised learning is a highly researched problem, but existing semi-supervised object detection frameworks are based on RGB images, and existing pre-trained models cannot be used for hyperspectral images. To overcome these difficulties, this paper first select fewer but suitable data augmentation methods to improve the accuracy of the supervised model based on the labeled training set, which is suitable for the characteristics of hyperspectral images. Next, in order to make full use of the unlabeled training set, we generate pseudo-labels with the model trained in the first stage and mix the obtained pseudo-labels with the labeled training set. Then, a large number of strong data augmentation methods are added to make the final model better. We achieve the SOTA, with an AP of 26.35, on the Semi-Supervised Hyperspectral Object Detection Challenge (SSHODC) in the CVPR 2022 Perception Beyond the Visible Spectrum Workshop, and win the first place in this Challenge.

关键词： Training computer vision conferences Object detection Semisupervised learning Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Ex-Model: Continual Learning from a Stream of Trained Models

Ex-Model: Continual Learning from a Stream of Trained Models

引用

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

作者： Carta, Antonio Cossu, Andrea Lomonaco, Vincenzo Bacciu, Davide Univ Pisa Pisa Italy Scuola Normale Super Pisa Pisa Italy

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years. Being able to learn, adapt, and generalize continually in an efficient, effective, and scalable way is fundamental for a sustainable development of Artificial Intelligent systems. However, an agent-centric view of continual learning requires learning directly from raw data, which limits the interaction between independent agents, the efficiency, and the privacy of current approaches. Instead, we argue that continual learning systems should exploit the availability of compressed information in the form of trained models. In this paper, we introduce and formalize a new paradigm named "Ex-Model Continual Learning" (ExML), where an agent learns from a sequence of previously trained models instead of raw data. We further contribute with three ex-model continual learning algorithms and an empirical setting comprising three datasets (MNIST, CIFAR-10 and CORe50), and eight scenarios, where the proposed algorithms are extensively tested. Finally, we highlight the peculiarities of the ex-model paradigm and we point out interesting future research directions.

关键词： Learning systems Data privacy computer vision conferences Computational modeling Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

TDT: Teaching Detectors to Track without Fully Annotated Videos

TDT: Teaching Detectors to Track without Fully Annotated Vid...

引用

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

作者： Yu, Shuzhi Wu, Guanhang Gu, Chunhui Fathy, Mohammed E. Duke Univ Durham NC 27706 USA Google LLC Mountain View CA USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks. However, their success depends on the availability of videos that are fully annotated with tracking data, which is expensive and hard to obtain. This can limit the model generalization. In comparison, the two-stage approach, which performs detection and embedding separately, is slower but easier to train as their data are easier to annotate. We propose to combine the best of the two worlds through a data distillation approach. Specifically, we use a teacher embedder, trained on Re-ID datasets, to generate pseudo appearance embedding labels for the detection datasets. Then, we use the augmented dataset to train a detector that is also capable of regressing these pseudo-embeddings in a fully-convolutional fashion. Our proposed one-stage solution matches the two-stage counterpart in quality but is 3 times faster. Even though the teacher embedder has not seen any tracking data during training, our proposed tracker achieves competitive performance with some popular trackers (e.g. JDE) trained with fully labeled tracking data.

关键词： Training computer vision Annotations conferences Detectors Predictive models Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity

Revisiting Vicinal Risk Minimization for Partially Supervise...

引用

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

作者： Dong, Nanqing Wang, Jiayi Voiculescu, Irina Univ Oxford Dept Comp Sci Oxford England Univ Oxford Math Inst Oxford England

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Due to the high human cost of annotation, it is non-trivial to curate a large-scale medical dataset that is fully labeled for all classes of interest. Instead, it would be convenient to collect multiple small partially labeled datasets from different matching sources, where the medical images may have only been annotated for a subset of classes of interest. This paper offers an empirical understanding of an under-explored problem, namely partially supervised multi-label classification (PSMLC), where a multi-label classifier is trained with only partially labeled medical images. In contrast to the fully supervised counterpart, the partial supervision caused by medical data scarcity has non-trivial negative impacts on the model performance. A potential remedy could be augmenting the partial labels. Though vicinal risk minimization (VRM) has been a promising solution to improve the generalization ability of the model, its application to PSMLC remains an open question. To bridge the methodological gap, we provide the first VRM-based solution to PSMLC. The empirical results also provide insights into future research directions on partially supervised learning under data scarcity.

关键词： Bridges computer vision Costs conferences Supervised learning Entropy Data models

来源：评论

学校读者我要写书评

暂无评论

Material Swapping for 3D Scenes using a Learnt Material Similarity Measure

Material Swapping for 3D Scenes using a Learnt Material Simi...

引用

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

作者： Perroni-Scharf, Maxine Sunkavalli, Kalyan Eisenmann, Jonathan Hold-Geoffroy, Yannick Princeton Univ Princeton NJ 08544 USA Adobe Res San Jose CA USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We present a method for augmenting photo-realistic 3D scene assets by automatically recognizing, matching, and swapping their materials. Our method proposes a material matching pipeline for the efficient replacement of unknown materials with perceptually similar PBR materials from a database, enabling the quick creation of many variations of a given 3D synthetic scene. At the heart of this method is a novel material similarity feature that is learnt, in conjunction with optimal lighting conditions, by fine-tuning a deep neural network on a material classification task using our proposed dataset. Our evaluation demonstrates that lighting optimization improves CNN-based texture feature extraction methods and better estimates material properties. We conduct a series of experiments showing our method's ability to augment photo-realistic indoor scenes using both standard and procedurally generated PBR materials.

关键词： Training Three-dimensional displays Pipelines Neural networks Lighting Feature extraction Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Shake-Shake Network for Long-Tailed recognition of SAR Aerial View Objects

A Two-Stage Shake-Shake Network for Long-Tailed Recognition ...

引用

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

作者： Li, Gongzhe Pan, Linpeng Qiu, Linwei Tan, Zhiwen Xie, Fengying Zhang, Haopeng Beihang Univ Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Synthetic Aperture Radar (SAR) has received more attention due to its complementary superiority on capturing significant information in the remote sensing area. However, for an Aerial View Object Classification (AVOC) task, SAR images still suffer from the long-tailed distribution of the aerial view objects. This disparity limit the performance of classification methods, especially for the data-sensitive deep learning models. In this paper, we propose a two-stage shake-shake network to tackle the long-tailed learning problem. Specifically, it decouples the learning procedure into the representation learning stage and the classification learning stage. Moreover, we apply the test time augmentation (TTA) and the classification with alternating normalization (CAN) to improve the accuracy. In the PBVS 1 2022 Multi-modal Aerial View Object Classification Challenge Track 1, our method achieves 21.82% and 27.97% accuracy in the development phase and testing phase respectively, which wins the top-tier among all the participants.

关键词： Training Representation learning Feature extraction Radar tracking Radar polarimetry pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Cell Selection-based Data Reduction Pipeline for Whole Slide Image Analysis of Acute Myeloid Leukemia

Cell Selection-based Data Reduction Pipeline for Whole Slide...

引用

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

作者： Kockwelp, Jacqueline Thiele, Sebastian Kockwelp, Pascal Bartsch, Jannis Schliemann, Christoph Angenendt, Linus Risse, Benjamin Univ Munster Munster Germany Univ Med Ctr Munster Munster Germany

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

computer-aided analyses of cells in Whole Slide Images (WSIs) have become an important topic in digital pathology. Despite the recent success of deep learning in biomedical research, these methods are still difficult to apply to multi-gigabyte WSIs. To overcome this difficulty, a variety of patch-based solutions have been introduced, which however all suffer from certain limitations compared to manual examinations and often fail to meet the specificities of cytological inspections. Here we introduce an alternative scheme which incorporates clinical expertise in the selection process to automatically identify the clinically relevant areas. By using a bone marrow smear dataset containing 22-gigapixel images of 153 patients, we introduce a novel pipeline combining unsupervised and supervised methodologies to gradually select the most appropriate single-cell regions, which are subsequently used in multiple medically crucial Acute Myeloid Leukemia (AML) predictions. Our approach is capable of dealing with a variety of common WSI challenges, massively limits the manual annotation effort, reduces the data by a factor of up to 99.9% and achieves super-human performance on the final cytological prediction tasks.

关键词： Deep learning Pathology computer vision Image analysis conferences Pipelines Manuals

来源：评论

学校读者我要写书评

暂无评论

Towards a Deeper Understanding of Skeleton-based Gait recognition

Towards a Deeper Understanding of Skeleton-based Gait Recogn...

引用

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

作者： Teepe, Torben Gilg, Johannes Herzog, Fabian Hoermann, Stefan Rigoll, Gerhard Tech Univ Munich Munich Germany

ISBN: (纸本)9781665487399

Gait recognition is a promising biometric with unique properties for identifying individuals from a long distance by their walking patterns. In recent years, most gait recognition methods used the person's silhouette to extract the gait features. However, silhouette images can lose fine-grained spatial information, suffer from (self) occlusion, and be challenging to obtain in real-world scenarios. Furthermore, these silhouettes also contain other visual clues that are not actual gait features and can be used for identification, but also to fool the system. Model-based methods do not suffer from these problems and are able to represent the temporal motion of body joints, which are actual gait features. The advances in human pose estimation started a new era for model-based gait recognition with skeleton-based gait recognition. In this work, we propose an approach based on Graph Convolutional Networks (GCNs) that combines higher-order inputs, and residual networks to an efficient architecture for gait recognition. Extensive experiments on the two popular gait datasets, CASIA-B and OUMVLP-Pose, show a massive improvement (3x) of the state-of-the-art (SotA) on the largest gait dataset OUMVLP-Pose and strong temporal modeling capabilities. Finally, we visualize our method to understand skeleton-based gait recognition better and to show that we model real gait features.

关键词： Training Visualization Pose estimation computer architecture Performance gain Feature extraction pattern recognition

来源：评论

学校读者我要写书评

暂无评论

CNLL: A Semi-supervised Approach For Continual Noisy Label Learning

CNLL: A Semi-supervised Approach For Continual Noisy Label L...

引用

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

作者： Karim, Nazmul Khalid, Umar Esmaeili, Ashkan Rahnavard, Nazanin Univ Cent Florida Dept Elect & Comp Engn Orlando FL 32816 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The task of continual learning requires careful design of algorithms that can tackle catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario, seems to exacerbate the situation. While very few studies have addressed the issue of continual learning under noisy labels, long training time and complicated training schemes limit their applications in most cases. In contrast, we propose a simple purification technique to effectively cleanse the online data stream that is both cost-effective and more accurate. After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples. Training in this fashion helps us learn a better representation that results in state-of-the-art (SOTA) performance. Through extensive experimentation on 3 benchmark datasets, MNIST, CIFAR10 and CIFAR100, we show the effectiveness of our proposed approach. We achieve a 24.8% performance gain for CIFAR10 with 20% noise over previous SOTA methods. Our code is publicly available.(1)

关键词： Training computer vision Codes Purification conferences Benchmark testing Performance gain

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 << < 71 72 73 74 75 76 77 78 79 80 > >>

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：