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

50,480 篇 会议
1,421 册 图书
1,042 篇 期刊文献
1 篇 学位论文

馆藏范围

52,941 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,809 篇 工学
- 24,802 篇 计算机科学与技术...
- 12,567 篇 软件工程
- 5,155 篇 光学工程
- 4,748 篇 电气工程
- 4,432 篇 信息与通信工程
- 4,257 篇 机械工程
- 3,950 篇 控制科学与工程
- 2,474 篇 生物工程
- 1,729 篇 生物医学工程（可授...
- 1,580 篇 仪器科学与技术
- 1,310 篇 电子科学与技术（可...
- 793 篇 化学工程与技术
- 697 篇 安全科学与工程
- 541 篇 交通运输工程
- 379 篇 建筑学
- 331 篇 土木工程
11,837 篇 理学
- 6,435 篇 物理学
- 5,405 篇 数学
- 2,761 篇 生物学
- 1,911 篇 统计学（可授理学、...
- 797 篇 化学
- 669 篇 系统科学
5,303 篇 医学
- 5,095 篇 临床医学
- 729 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,345 篇 管理学
- 1,951 篇 图书情报与档案管...
- 1,533 篇 管理科学与工程(可...
- 479 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
428 篇 法学
- 401 篇 社会学
298 篇 农学
197 篇 教育学
163 篇 经济学
63 篇 文学
49 篇 军事学

主题

17,384 篇 computer vision
9,016 篇 pattern recognit...
4,195 篇 training
3,814 篇 feature extracti...
3,134 篇 cameras
2,870 篇 computational mo...
2,790 篇 image segmentati...
2,621 篇 visualization
2,573 篇 shape
2,533 篇 face recognition
2,171 篇 robustness
2,123 篇 computer science
1,972 篇 object detection
1,959 篇 computer archite...
1,878 篇 layout
1,852 篇 object recogniti...
1,802 篇 three-dimensiona...
1,725 篇 neural networks
1,708 篇 humans
1,691 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
136 篇 national laborat...
107 篇 univ sci & techn...
104 篇 zhejiang univers...
100 篇 shanghai jiao to...
95 篇 microsoft resear...
94 篇 university of sc...
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

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

语言

51,872 篇 英文
835 篇 其他
241 篇 中文
22 篇 土耳其文
5 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 52944 条记录，以下是4671-4680 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：

Audio-Visual Instance Discrimination with Cross-Modal Agreement

Audio-Visual Instance Discrimination with Cross-Modal Agreem...

引用

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

作者： Morgado, Pedro Vasconcelos, Nuno Misra, Ishan Univ Calif San Diego La Jolla CA 92093 USA Facebook AI Res New York NY USA

ISBN: (纸本)9781665445092

We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for cross-modal discrimination, rather than withinmodal discrimination, is important to learn good representations from video and audio. With this simple but powerful insight, our method achieves highly competitive performance when finetuned on action recognition tasks. Furthermore, while recent work in contrastive learning defines positive and negative samples as individual instances, we generalize this definition by exploring cross-modal agreement. We group together multiple instances as positives by measuring their similarity in both the video and audio feature spaces. Cross-modal agreement creates better positive and negative sets, which allows us to calibrate visual similarities by seeking within-modal discrimination of positive instances, and achieve significant gains on downstream tasks.

关键词： Visualization computer vision Extraterrestrial measurements pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Local Neighborhood Average pattern: A Handcrafted Feature Descriptor for Hand Gesture recognition 3

Local Neighborhood Average Pattern: A Handcrafted Feature De...

引用

3rd International conference on Secure Cyber Computing and Communications, ICSCCC 2023

作者： Bahuguna, Arti Namchyo, Shalom Ben Tenzing Chaudhary, Deepak Kumar Bhaumik, Gopa Govil, Mahesh Chandra National Institute of Technology Sikkim Computer Science and Engineering Sikkim India National Institute of Technology Jamshedpur Computer Science and Engineering Jharkhand India

ISBN: (纸本)9798350300710

This paper proposes a handcrafted feature-based descriptor namely Local neighborhood average pattern (LNAP) for static hand gesture recognition. The fact, that the local descriptors are important in numerous computer vision applications and show great performance cannot be overstated. This is accentuated further in difficult environments. This is the major driving force behind continued research in this field. We developed a feature descriptor LNAP in this paper, with the aim of extracting complete microstructural features achieved by evaluating excitation in different ways and directional relevant data based on connections between pixels taken at various spatial configurations inside each 3 × 3 neighborhood. An LNAP descriptor represents the structure of hand textures in a simple and compact coding manner, resulting in its unique code in less time and memory than existing approaches. The proposed LNAP descriptor extracts the dominant features from the hand region which are further classified using SVM. The proposed LNAP's performance is assessed using three benchmark datasets: Massey University Dataset (MUGD), ASL Digit Datasets, and Ouhands Dataset in respect of accuracy and F1-score and found to achieve an accuracy of 93% (MUGD Set1), 96% (MUGD Set2), 92 % (MUGD Set 3), 89% (MUGD Set4), 71% (MUGD Set5), 99%, and 47% respectively. The experimental findings show that the suggested LNAP produces better outcomes than existing techniques. © 2023 ieee.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Table Tennis Stroke recognition Using Two-Dimensional Human Pose Estimation

Table Tennis Stroke Recognition Using Two-Dimensional Human ...

引用

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

作者： Kulkarni, Kaustubh Milind Shenoy, Sucheth

ISBN: (纸本)9781665448994

We introduce a novel method for collecting table tennis video data and perform stroke detection and classification. A diverse dataset containing video data of 11 basic strokes obtained from 14 professional table tennis players, summing up to a total of 22111 videos has been collected using the proposed setup. The temporal convolutional neural network model developed using 2D pose estimation performs multiclass classification of these 11 table tennis strokes with a validation accuracy of 99.37%. Moreover, the neural network generalizes well over the data of a player excluded from the training and validation dataset, classifying the fresh strokes with an overall best accuracy of 98.72%. Various model architectures using machine learning and deep learning based approaches have been trained for stroke recognition and their performances have been compared and benchmarked. Inferences such as performance monitoring and stroke comparison of the players using the model have been discussed. Therefore, we are contributing to the development of a computer vision based sports analytics system for the sport of table tennis that focuses on the previously unexploited aspect of the sport i.e., a player's strokes, which is extremely insightful for performance improvement.

关键词： Training Deep learning computer vision Computational modeling Pose estimation Neural networks Stroke (medical condition)

来源：评论

学校读者我要写书评

暂无评论

Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

Neural Scene Flow Fields for Space-Time View Synthesis of Dy...

引用

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

作者： Li, Zhengqi Niklaus, Simon Snavely, Noah Wang, Oliver Cornell Tech New York NY 10044 USA Adobe Res San Jose CA USA

ISBN: (纸本)9781665445092

We present a method to perform novel view and time synthesis of dynamic scenes, requiring only a monocular video with known camera poses as input. To do this, we introduce Neural Scene Flow Fields, a new representation that models the dynamic scene as a time-variant continuous function of appearance, geometry, and 3D scene motion. Our representation is optimized through a neural network to fit the observed input views. We show that our representation can be used for varieties of in-the-wild scenes, including thin structures, view-dependent effects, and complex degrees of motion. We conduct a number of experiments that demonstrate our approach significantly outperforms recent monocular view synthesis methods, and show qualitative results of space-time view synthesis on a variety of real-world videos.

关键词： Geometry Solid modeling computer vision Three-dimensional displays Dynamics Neural networks Cameras

来源：评论

学校读者我要写书评

暂无评论

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

Interpretable Social Anchors for Human Trajectory Forecastin...

引用

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

作者： Kothari, Parth Sifringer, Brian Alahi, Alexandre EPFL VITA Lab CH-1015 Lausanne Switzerland

ISBN: (纸本)9781665445092

Human trajectory forecasting in crowds, at its core, is a sequence prediction problem with specific challenges of capturing inter-sequence dependencies (social interactions) and consequently predicting socially-compliant multi-modal distributions. In recent years, neural network-based methods have been shown to outperform hand-crafted methods on distance-based metrics. However, these data-driven methods still suffer from one crucial limitation: lack of interpretability. To overcome this limitation, we leverage the power of discrete choice models to learn interpretable rule-based intents, and subsequently utilise the expressibility of neural networks to model scene-specific residual. Extensive experimentation on the interaction-centric benchmark TrajNet++ demonstrates the effectiveness of our proposed architecture to explain its predictions without compromising the accuracy.

关键词： Measurement computer vision Neural networks Knowledge based systems Predictive models Data models Trajectory

来源：评论

学校读者我要写书评

暂无评论

Limitations of Post-Hoc Feature Alignment for Robustness

Limitations of Post-Hoc Feature Alignment for Robustness

引用

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

作者： Burns, Collin Steinhardt, Jacob Univ Calif Berkeley Berkeley CA 94720 USA

ISBN: (纸本)9781665445092

Feature alignment is an approach to improving robustness to distribution shift that matches the distribution of feature activations between the training distribution and test distribution. A particularly simple but effective approach to feature alignment involves aligning the batch normalization statistics between the two distributions in a trained neural network. This technique has received renewed interest lately because of its impressive performance on robustness benchmarks. However, when and why this method works is not well understood. We investigate the approach in more detail and identify several limitations. We show that it only significantly helps with a narrow set of distribution shifts and we identify several settings in which it even degrades performance. We also explain why these limitations arise by pinpointing why this approach can be so effective in the first place. Our findings call into question the utility of this approach and Unsupervised Domain Adaptation more broadly for improving robustness in practice.

关键词： Training Knowledge engineering computer vision Neural networks Buildings Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation

Data-Efficient Language-Supervised Zero-Shot Learning with S...

引用

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

作者： Cheng, Ruizhe Wu, Bichen Zhang, Peizhao Vajda, Peter Gonzalez, Joseph E. Univ Calif Berkeley Berkeley CA 94720 USA Facebook Real Labs Redmond WA USA

ISBN: (纸本)9781665448994

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts than supervised "gold" labels. Previous works, such as CLIP, use a simple pretraining task of predicting the pairings between images and text captions. CLIP, however, is data hungry and requires more than 400M image text pairs for training. We propose a data-efficient contrastive distillation method that uses soft labels to learn from noisy image-text pairs. Our model transfers knowledge from pre-trained image and sentence encoders and achieves strong performance with only 3M image text pairs, 133x smaller than CLIP. Our method exceeds the previous SoTA of general zero-shot learning on ImageNet 21k+1k by 73% relatively with a ResNet50 image encoder and DeCLUTR text encoder. We also beat CLIP by 10.5% relatively on zeroshot evaluation on Google Open Images (19,958 classes).

关键词： Training computer vision Visualization Natural languages Predictive models pattern recognition Internet

来源：评论

学校读者我要写书评

暂无评论

SDD: A Benchmark for Empowering Shadow Detection 7

SDD: A Benchmark for Empowering Shadow Detection

引用

7th International conference on Artificial Intelligence and Big Data (ICAIBD)

作者： Zhang, Hao Wu, You Guo, Xiaoyu Huang, Ling Ye, Hengzhou Li, Shuiwang Guilin Univ Technol Coll Comp Sci & Engn Guilin Peoples R China

ISBN: (纸本)9798350385113;9798350385106

In the field of computer vision, shadow detection has been a topic of considerable interest. Shadows encapsulate a wealth of information about the underlying light conditions and scene geometry, making them invaluable for a wide range of visual perception tasks, from understanding the physical properties of light to interpreting the structure and layout of the surrounding environment. Moreover, shadows affect image quality, thereby influencing the results of computer vision algorithms such as object detection, recognition, and tracking. Therefore, identifying and eliminating shadows contributes to improving algorithm performance. However, shadow detection research faces the challenge of scarce high-quality annotated datasets. To address this problem, we introduce a novel shadow detection dataset called Shadow Detection Dataset (SDD), consisting of 2638 images covering various scenes including urban streets, natural landscapes, and indoor spaces. Additionally, we evaluate the performance of eight state-of-the-art object detection methods on SDD to compare and reveal their effectiveness in shadow detection tasks. Through comparative experimental results, we find significant differences in the performance of different methods across various scenes, underscoring the significance of the proposed dataset in assessing the performance of shadow detection techniques. In the future, we look forward to further expanding this dataset and exploring more effective shadow detection methods to meet the growing demands of applications and advance the field. The dataset is available to the public at https://***/hhaozhang/SDD.

关键词： computer vision shadow detection evaluation dataset

来源：评论

学校读者我要写书评

暂无评论

CL-Gym: Full-Featured PyTorch Library for Continual Learning

CL-Gym: Full-Featured PyTorch Library for Continual Learning

引用

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

作者： Mirzadeh, Seyed Iman Ghasemzadeh, Hassan Washington State Univ Pullman WA 99164 USA

ISBN: (纸本)9781665448994

Continual learning (CL) has become one of the most active research venues within the artificial intelligence community in recent years. Given the significant amount of attention paid to continual learning, the need for a library that facilitates both research and development in this field is more visible than ever. However, CL algorithms' codes are currently scattered over isolated repositories written with different frameworks, making it difficult for researchers and practitioners to work with various CL algorithms and benchmarks using the same interface. In this paper, we introduce CL-Gym, a full-featured continual learning library that overcomes this challenge and accelerates the research and development. In addition to the necessary infrastructure for running end-to-end continual learning experiments, CL-Gym includes benchmarks for various CL scenarios and several state-of-the-art CL algorithms. In this paper, we present the architecture, design philosophies, and technical details behind CL-Gym (1).

关键词： computer vision Philosophical considerations conferences computer architecture Learning (artificial intelligence) Benchmark testing Libraries

来源：评论

学校读者我要写书评

暂无评论

Facial Action Unit Detection With Transformers

Facial Action Unit Detection With Transformers

引用

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

作者： Jacob, Geethu Miriam Stenger, Bjorn Rakuten Inst Technol Tokyo Japan

ISBN: (纸本)9781665445092

The Facial Action Coding System is a taxonomy for fine-grained facial expression analysis. This paper proposes a method for detecting Facial Action Units (FAU), which define particular face muscle activity, from an input image. FAU detection is formulated as a multi-task learning problem, where image features and attention maps are input to a branch for each action unit to extract discriminative feature embeddings, using a new loss function, the center contrastive (CC) loss. We employ a new FAU correlation network, based on a transformer encoder architecture, to capture the relationships between different action units for the wide range of expressions in the training data. The resulting features are shown to yield high classification performance. We validate our design choices, including the use of CC-loss and Tversky loss functions, in ablative experiments. We show that the proposed method outperforms state-of-the-art techniques on two public datasets, BP4D and DISFA, with an absolute improvement of the F I-score of over 2% on each.

关键词： Correlation Face recognition Taxonomy Training data computer architecture Muscles Transformers

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 << < 464 465 466 467 468 469 470 471 472 473 > >>

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：