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

5,349 篇 会议
128 册 图书
29 篇 期刊文献

馆藏范围

5,506 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,747 篇 工学
- 2,253 篇 计算机科学与技术...
- 926 篇 软件工程
- 478 篇 光学工程
- 399 篇 控制科学与工程
- 332 篇 机械工程
- 261 篇 仪器科学与技术
- 250 篇 信息与通信工程
- 128 篇 电气工程
- 122 篇 生物工程
- 90 篇 生物医学工程（可授...
- 70 篇 电子科学与技术（可...
- 39 篇 安全科学与工程
- 33 篇 化学工程与技术
- 31 篇 建筑学
- 27 篇 土木工程
- 25 篇 交通运输工程
- 24 篇 航空宇航科学与技...
858 篇 理学
- 526 篇 物理学
- 439 篇 数学
- 155 篇 统计学（可授理学、...
- 133 篇 生物学
- 28 篇 化学
- 21 篇 系统科学
242 篇 艺术学
- 242 篇 设计学（可授艺术学...
196 篇 管理学
- 101 篇 图书情报与档案管...
- 97 篇 管理科学与工程(可...
- 27 篇 工商管理
96 篇 医学
- 96 篇 临床医学
- 21 篇 基础医学(可授医学...
28 篇 法学
- 26 篇 社会学
8 篇 教育学
6 篇 经济学
5 篇 农学
2 篇 军事学

主题

2,165 篇 computer vision
915 篇 pattern recognit...
890 篇 conferences
640 篇 training
565 篇 cameras
410 篇 feature extracti...
373 篇 computational mo...
364 篇 image segmentati...
350 篇 visualization
338 篇 face recognition
321 篇 computer archite...
309 篇 robustness
290 篇 computer science
287 篇 shape
280 篇 humans
266 篇 object detection
234 篇 layout
196 篇 neural networks
191 篇 application soft...
191 篇 lighting

机构

20 篇 swiss fed inst t...
19 篇 institute for co...
18 篇 university of sc...
18 篇 microsoft resear...
18 篇 swiss fed inst t...
16 篇 carnegie mellon ...
16 篇 chinese acad sci...
14 篇 tsinghua univers...
14 篇 univ sci & techn...
14 篇 carnegie mellon ...
12 篇 harbin inst tech...
12 篇 tsinghua univ pe...
12 篇 department of co...
11 篇 megvii technol p...
11 篇 computer vision ...
11 篇 computer vision ...
10 篇 indian statistic...
10 篇 comp vis ctr bar...
10 篇 school of comput...
10 篇 univ modena & re...

作者

58 篇 timofte radu
17 篇 van gool luc
17 篇 luc van gool
17 篇 horst bischof
16 篇 rita cucchiara
16 篇 radu timofte
14 篇 escalera sergio
14 篇 bischof horst
14 篇 sergio escalera
13 篇 zhigang zhu
13 篇 hugo jair escala...
12 篇 murino vittorio
12 篇 li stan z.
12 篇 chen wei-ting
12 篇 qiang ji
11 篇 cucchiara rita
11 篇 fan haoqiang
11 篇 umapada pal
11 篇 marcos v. conde
11 篇 bowyer kevin w.

语言

5,492 篇 英文
10 篇 中文
5 篇 其他

检索条件"任意字段=2006 Conference on Computer Vision and Pattern Recognition Workshops"

共 5506 条记录，以下是4841-4850 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：

Block Selective Reprogramming for On-device Training of vision Transformers

Block Selective Reprogramming for On-device Training of Visi...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Sreetama Sarkar Souvik Kundu Kai Zheng Peter A. Beerel Universiy of Southern California Los Angeles USA Intel Labs San Diego USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

The ubiquity of vision transformers (ViTs) for various edge applications, including personalized learning, has created the demand for on-device fine-tuning. However, training with the limited memory and computation power of edge devices remains a significant challenge. In particular, the memory required for training is much higher than that needed for inference, primarily due to the need to store activations across all layers in order to compute the gradients needed for weight updates. Previous works have explored reducing this memory requirement via frozen-weight training as well storing the activations in a compressed format. However, these methods are deemed inefficient due to their inability to provide training or inference speedup. In this paper, we first investigate the limitations of existing on-device training methods aimed at reducing memory and compute requirements. We then present block selective reprogramming (BSR) in which we fine-tune only a fraction of total blocks of a pre-trained model and selectively drop tokens based on self-attention scores of the frozen layers. To show the efficacy of BSR, we present extensive evaluations on ViT-B and DeiT-S with five different datasets. Compared to the existing alternatives, our approach simultaneously reduces training memory by up to 1.4× and compute cost by up to 2× while maintaining similar accuracy. We also showcase results for Mixture-of-Expert (MoE) models, demonstrating the effectiveness of our approach in multitask learning scenarios. Code will be available at: https://***/sreetamasarkar/BSR.

关键词： Training computer vision Costs Quantization (signal) Codes Computational modeling conferences

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation for Thermal Images: A Comparative Survey

Semantic Segmentation for Thermal Images: A Comparative Surv...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Zü lfiye Kü tü k Gö rkem Algan Dept. of Image Proc. &#x0026 Computer Vis. Technologies Aselsan Inc. Turkey

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487405

Semantic segmentation is a challenging task since it requires excessively more low-level spatial information of the image compared to other computer vision problems. The accuracy of pixel-level classification can be affected by many factors, such as imaging limitations and the ambiguity of object boundaries in an image. Conventional methods exploit three-channel RGB images captured in the visible spectrum with deep neural networks (DNN). Thermal images can significantly contribute during the segmentation since thermal imaging cameras are capable of capturing details despite the weather and illumination conditions. Using infrared spectrum in semantic segmentation has many real-world use cases, such as autonomous driving, medical imaging, agriculture, defense industry, etc. Due to this wide range of use cases, designing accurate semantic segmentation algorithms with the help of infrared spectrum is an important challenge. One approach is to use both visible and infrared spectrum images as inputs. These methods can accomplish higher accuracy due to enriched input information, with the cost of extra effort for the alignment and processing of multiple inputs. Another approach is to use only thermal images, enabling less hardware cost for smaller use cases. Even though there are multiple surveys on semantic segmentation methods, the literature lacks a comprehensive survey centered explicitly around semantic segmentation using infrared spectrum. This work aims to fill this gap by presenting algorithms in the literature and categorizing them by their input images.

关键词： Image segmentation computer vision Costs Semantics Neural networks Lighting Robustness

来源：评论

学校读者我要写书评

暂无评论

A Statistical Assessment of Subject Factors in the PCA recognition of Human Faces

A Statistical Assessment of Subject Factors in the PCA Recog...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Geof Givens J Ross Beveridge Bruce A. Draper David Bolme Statistics Department Colorado State University CO Computer Science Department Colorado State University Fort Collins CO USA

Some people's faces are easier to recognize than others, but it is not obvious what subject-specific factors make individual faces easy or difficult to recognize. This study considers 11 factors that might make recognition easy or difficult for 1,072 human subjects in the FERET dataset. The specific factors are: race (white, Asian, African-American, or other), gender, age (young or old), glasses (present or absent), facial hair (present or absent), bangs (present or absent), mouth (closed or other), eyes (open or other), complexion (clear or other), makeup (present or absent), and expression (neutral or other). An ANOVA is used to determine the relationship between these subject covariates and the distance between pairs of images of the same subject in a standard Eigenfaces subspace. Some results are not terribly surprising. For example, the distance between pairs of images of the same subject increases for people who change their appearance, e.g., open and close their eyes, open and close their mouth or change expression. Thus changing appearance makes recognition harder. Other findings are surprising. Distance between pairs of images for subjects decreases for people who consistently wear glasses, so wearing glasses makes subjects more recognizable. Pairwise distance also decreases for people who are either Asian or African-American rather than white. A possible shortcoming of our analysis is that minority classifications such as African-Americans and wearers-of-glasses are underrepresented in training. Followup experiments with balanced training addresses this concern and corroborates the original findings. Another possible shortcoming of this analysis is the novel use of pairwise distance between images of a single person as the predictor of recognition difficulty. A separate experiment confirms that larger distances between pairs of subject images implies a larger recognition rank for that same pair of images, thus confirming that the subject is harder to recog

关键词： Distance measurement Glass Image recognition Hair Principal component analysis Mouth Training

来源：评论

学校读者我要写书评

暂无评论

Tracking of the Articulated Upper Body on Multi-View Stereo Image Sequences

Tracking of the Articulated Upper Body on Multi-View Stereo ...

引用

conference on computer vision and pattern recognition (CVPR)

作者： J. Ziegler Kai Nickel R. Stiefelhagen Interactive Systems Laboratories Universität Karlsruhe Germany

We propose a novel method for tracking an articulated model in a 3D-point cloud. The tracking problem is formulated as the registration of two point sets, one of them parameterised by the model’s state vector and the other acquired from a 3D-sensor system. Finding the correct parameter vector is posed as a linear estimation problem, which is solved by means of a scaled unscented Kalman filter. Our method draws on concepts from the widely used iterative closest point registration algorithm (ICP), basing the measurement model on point correspondences established between the synthesised model point cloud and the measured 3D-data. We apply the algorithm to kinematically track a model of the human upper body on a point cloud obtained through stereo image processing from one or more stereo cameras. We determine torso position and orientation as well as joint angles of shoulders and elbows. The algorithm has been successfully tested on thousands of frames of real image data. Challenging sequences of several minutes length where tracked correctly. Complete processing time remains below one second per frame.

关键词： Image sequences Clouds Biological system modeling Vectors Iterative algorithms Iterative methods Iterative closest point algorithm Humans Stereo vision Cameras

来源：评论

学校读者我要写书评

暂无评论

Principled Hybrids of Generative and Discriminative Models

Principled Hybrids of Generative and Discriminative Models

引用

conference on computer vision and pattern recognition (CVPR)

作者： J.A. Lasserre C.M. Bishop T.P. Minka University of Cambridge Cambridge UK Microsoft Research Limited Cambridge UK

When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications such as object recognition, hand labelling of data is expensive, and there is much interest in semi-supervised techniques based on generative models in which the majority of the training data is unlabelled. Although the generalization performance of generative models can often be improved by ‘training them discriminatively’, they can then no longer make use of unlabelled data. In an attempt to gain the benefit of both generative and discriminative approaches, heuristic procedure have been proposed [2, 3] which interpolate between these two extremes by taking a convex combination of the generative and discriminative objective functions. In this paper we adopt a new perspective which says that there is only one correct way to train a given model, and that a ‘discriminatively trained’ generative model is fundamentally a new model [7]. From this viewpoint, generative and discriminative models correspond to specific choices for the prior over parameters. As well as giving a principled interpretation of ‘discriminative training’, this approach opens door to very general ways of interpolating between generative and discriminative extremes through alternative choices of prior. We illustrate this framework using both synthetic data and a practical example in the domain of multi-class object recognition. Our results show that, when the supply of labelled training data is limited, the optimum performance corresponds to a balance between the purely generative and the purely discriminative.

关键词： Hybrid power systems Training data Object recognition computer vision Large-scale systems Labeling Machine learning Application software Parametric statistics Predictive models

来源：评论

学校读者我要写书评

暂无评论

The Dense Estimation of Motion and Appearance in Layers

The Dense Estimation of Motion and Appearance in Layers

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： H. Yalcin M.J. Black R. Fablet Division of Engineering Brown University Providence RI USA Computer Science Brown University Providence RI USA LASAA IFREMER Plouzane France

Segmenting image sequences into meaningful layers is fundamental to many applications such as surveillance, tracking, and video summarization. Background subtraction techniques are popular for their simplicity and, while they provide a dense (pixelwise) estimate of foreground/background, they typically ignore image motion which can provide a rich source of information about scene structure. Conversely, layered motion estimation techniques typically ignore the temporal persistence of image appearance and provide parametric (rather than dense) estimates of optical flow. Recent work adaptively combines motion and appearance estimation in a mixture model framework to achieve robust tracking. Here we extend mixture model approaches to cope with dense motion and appearance estimation. We develop a unified Bayesian framework to simultaneously estimate the appearance of multiple image layers and their corresponding dense flow fields from image sequences. Both the motion and appearance models adapt over time and the probabilistic formulation can be used to provideasegmentation of thescene into foreground/background regions. This extension of mixture models includes prior probability models for the spatial and temporal coherence of motion and appearance. Experimental results show that the simultaneous estimation of appearance models and flow fields in multiple layers improves the estimation of optical flow at motion boundaries.

关键词： Motion estimation Image motion analysis Image sequences Image segmentation Surveillance Subtraction techniques Pixel Information resources Layout Image converters

来源：评论

学校读者我要写书评

暂无评论

Exploring AI-Based Satellite Pose Estimation: from Novel Synthetic Dataset to In-Depth Performance Evaluation

Exploring AI-Based Satellite Pose Estimation: from Novel Syn...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Fabien Gallet Christophe Marabotto Thomas Chambon Institut de Recherche Technologique Saint Exupéry

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

vision-based pose estimation using deep learning offers a promising cost effective and versatile solution for relative satellite navigation purposes. Using such a solution in closed loop to control spacecraft position is challenging from validation and performance verification viewpoint, because of the complex specification and development process. The validation task entails bridging the gap between the dataset and real-world data. In particular, modelling of Sun power and spectrum, Earth albedo, and atmospheric absence effects, is costly to replicate on ground. This article suggests a novel approach to produce synthetic space scene images. Fine statistical balancing is ensured to train and assess pose estimation solutions. A physically based camera model is used. Synthetic images incorporate realistic light flux, radiometric properties, and texture scatterings. The dataset comprises 120000 images supplemented with masks, distance maps, celestial body positions, and precise camera parameters (dataset publicly available https://***/space_rendezvous/ created in the frame of a project called RAPTOR: Robotic and Artificial intelligence Processing Test On Representative target). An analysis method using a dedicated metric library has been developed to help the assessment of the solution performance and robustness. A deeper comprehension of algorithm behavior through distribution law fitting and outlier identification is then facilitated. Finally, it is shown that implementing Region-of-Interest (RoI) training can drastically increase the performance of the Convolutional Neural Networks (CNNs) for long-range satellite pose estimation tasks.

关键词： Training Space vehicles computer vision Atmospheric modeling Pose estimation Satellite broadcasting Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

Bilayer Segmentation of Live Video

Bilayer Segmentation of Live Video

引用

conference on computer vision and pattern recognition (CVPR)

作者： A. Criminisi G. Cross A. Blake V. Kolmogorov Microsoft Research Limited Cambridge UK

This paper presents an algorithm capable of real-time separation of foreground from background in monocular video sequences. Automatic segmentation of layers from colour/contrast or from motion alone is known to be error-prone. Here motion, colour and contrast cues are probabilistically fused together with spatial and temporal priors to infer layers accurately and efficiently. Central to our algorithm is the fact that pixel velocities are not needed, thus removing the need for optical flow estimation, with its tendency to error and computational expense. Instead, an efficient motion vs nonmotion classifier is trained to operate directly and jointly on intensity-change and contrast. Its output is then fused with colour information. The prior on segmentation is represented by a second order, temporal, Hidden Markov Model, together with a spatial MRF favouring coherence except where contrast is high. Finally, accurate layer segmentation and explicit occlusion detection are efficiently achieved by binary graph cut. The segmentation accuracy of the proposed algorithm is quantitatively evaluated with respect to existing groundtruth data and found to be comparable to the accuracy of a state of the art stereo segmentation algorithm. Foreground/ background segmentation is demonstrated in the application of live background substitution and shown to generate convincingly good quality composite video.

关键词： Image segmentation Image motion analysis Stereo vision Optical computing Data mining Application software Computational efficiency Cameras Image sequences Video sequences

来源：评论

学校读者我要写书评

暂无评论

Fake it to make it: Using synthetic data to remedy the data shortage in joint multi-modal speech-and-gesture synthesis

Fake it to make it: Using synthetic data to remedy the data ...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Shivam Mehta Anna Deichler Jim O’Regan Birger Moëll Jonas Beskow Gustav Eje Henter Simon Alexanderson KTH Royal Institute of Technology Sweden Motorica AB Sweden

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Although humans engaged in face-to-face conversation simultaneously communicate both verbally and non-verbally, methods for joint and unified synthesis of speech audio and co-speech 3D gesture motion from text are a new and emerging field. These technologies hold great promise for more human-like, efficient, expressive, and robust synthetic communication, but are currently held back by the lack of suitably large datasets, as existing methods are trained on parallel data from all constituent modalities. Inspired by student-teacher methods, we propose a straightforward solution to the data shortage, by simply synthesising additional training material. Specifically, we use uni-modal synthesis models trained on large datasets to create multi-modal (but synthetic) parallel training data, and then pre-train a joint synthesis model on that material. In addition, we propose a new synthesis architecture that adds better and more controllable prosody modelling to the state-of-the-art method in the field. Our results confirm that pre-training on large amounts of synthetic data improves the quality of both the speech and the motion synthesised by the multi-modal model, with the proposed architecture yielding further benefits when pre-trained on the synthetic data.

关键词： Training computer vision Three-dimensional displays conferences Training data computer architecture Oral communication

来源：评论

学校读者我要写书评

暂无评论

ELSA: Exploiting Layer-wise N:M Sparsity for vision Transformer Acceleration

ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transfor...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Ning-Chi Huang Chi-Chih Chang Wei-Cheng Lin Endri Taka Diana Marculescu Kai-Chiang Wu National Yang Ming Chiao Tung University University of Texas at Austin

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

N:M sparsity is an emerging model compression method supported by more and more accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing N:M sparsity methods compress neural networks with a uniform setting for all layers in a network or heuristically determine the layer-wise configuration by considering the number of parameters in each layer. However, very few methods have been designed for obtaining a layer-wise customized N:M sparse configuration for vision transformers (ViTs), which usually consist of transformer blocks involving the same number of *** this work, to address the challenge of selecting suitable sparse configuration for ViTs on N:M sparsity-supporting accelerators, we propose ELSA, Exploiting Layer-wise N:M Sparsity for ViTs. Considering not only all N:M sparsity levels supported by a given accelerator but also the expected throughput improvement, our methodology can reap the benefits of accelerators supporting mixed sparsity by trading off negligible accuracy loss with both memory usage and inference time reduction for ViT models. For instance, our approach achieves a noteworthy 2.9× reduction in FLOPs to both Swin-B and DeiT-B with only a marginal degradation of accuracy on ImageNet. Our code is publicly available at https://***/ningchihuang/ELSA.

关键词： Training Degradation computer vision Accuracy Transformers Throughput Software

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 << < 481 482 483 484 485 486 487 488 489 490 > >>

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：