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

50,499 篇 会议
1,418 册 图书
1,019 篇 期刊文献
1 篇 学位论文

馆藏范围

52,934 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,785 篇 工学
- 24,773 篇 计算机科学与技术...
- 12,556 篇 软件工程
- 5,155 篇 光学工程
- 4,742 篇 电气工程
- 4,428 篇 信息与通信工程
- 4,255 篇 机械工程
- 3,948 篇 控制科学与工程
- 2,475 篇 生物工程
- 1,729 篇 生物医学工程（可授...
- 1,579 篇 仪器科学与技术
- 1,305 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
11,835 篇 理学
- 6,437 篇 物理学
- 5,401 篇 数学
- 2,762 篇 生物学
- 1,910 篇 统计学（可授理学、...
- 797 篇 化学
- 668 篇 系统科学
5,301 篇 医学
- 5,094 篇 临床医学
- 727 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,345 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...
- 480 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

17,316 篇 computer vision
8,990 篇 pattern recognit...
4,200 篇 training
3,816 篇 feature extracti...
3,128 篇 cameras
2,868 篇 computational mo...
2,780 篇 image segmentati...
2,615 篇 visualization
2,543 篇 shape
2,536 篇 face recognition
2,179 篇 robustness
2,115 篇 computer science
1,969 篇 object detection
1,966 篇 computer archite...
1,855 篇 layout
1,835 篇 object recogniti...
1,788 篇 three-dimensiona...
1,730 篇 neural networks
1,710 篇 humans
1,685 篇 image recognitio...

机构

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

作者

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

语言

50,670 篇 英文
2,031 篇 其他
246 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 52937 条记录，以下是4381-4390 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：

ICDAR 2024 Competition on Handwritten Text recognition in Brazilian Essays - BRESSAY 18th

ICDAR 2024 Competition on Handwritten Text Recognition in Br...

引用

18th International conference on Document Analysis and recognition (ICDAR)

作者： Neto, Arthur F. S. Bezerra, Byron L. D. Araujo, Savio S. Souza, Wiliane M. A. S. Alves, Kleberson F. Oliveira, Macileide F. Lins, Samara V. S. Hazin, Hugo J. F. Rocha, Pedro H., V Toselli, Alejandro H. Univ Pernambuco Recife PE Brazil Univ Fed Agreste Pernambuco Garanhuns Brazil Univ Fed Vale Sao Francisco Petrolina Brazil Univ Politecn Valencia Valencia Spain

ISBN: (纸本)9783031705519;9783031705526

This paper describes the "Handwritten Text recognition in Brazilian Essays - BRESSAY" competition, held at the 18th International conference on Document Analysis and recognition (ICDAR 2024). The competition aimed to advance Handwritten Text recognition (HTR) by addressing challenges specific to Brazilian Portuguese academic essays, such as diverse handwriting styles and document irregularities like smudges and erasures. Participants were encouraged to develop robust algorithms capable of accurately transcribing handwritten texts at line, paragraph, and page levels using the new BRESSAY dataset. The competition attracted 14 participants from different countries, with 4 research groups submitting a total of 11 proposals in the three challenges by the end of the competition. These proposals achieved impressive recognition rates and demonstrated advancements over traditional baseline models by using key strategies such as preprocessing techniques, synthetic data approaches, and advanced deep learning models. The evaluation metrics used were Character Error Rate (CER) and Word Error Rate (WER), with error rates reaching up to 2.88% CER and 9.39% WER for line-level recognition, 3.75% CER and 10.48% WER for paragraph-level recognition, and 3.77% CER and 10.08% WER for page-level recognition. The competition highlight the potential for continued improvements in HTR and underscore the BRESSAY dataset as a resource for future researches. The dataset is available in the repository (https://***/arthurflor23/handwritten-text-recognition).

关键词： dataset brazilian portuguese essays computer vision deep learning handwritten text recognition

来源：评论

学校读者我要写书评

暂无评论

Transformer Interpretability Beyond Attention Visualization

Transformer Interpretability Beyond Attention Visualization

引用

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

作者： Chefer, Hila Gur, Shir Wolf, Lior Tel Aviv Univ Sch Comp Sci Tel Aviv Israel Facebook AI Res FAIR Tel Aviv Israel

ISBN: (纸本)9781665445092

Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In order to visualize the parts of the image that led to a certain classification, existing methods either rely on the obtained attention maps or employ heuristic propagation along the attention graph. In this work, we propose a novel way to compute relevancy for Transformer networks. The method assigns local relevance based on the Deep Taylor Decomposition principle and then propagates these relevancy scores through the layers. This propagation involves attention layers and skip connections, which challenge existing methods. Our solution is based on a specific formulation that is shown to maintain the total relevancy across layers. We benchmark our method on very recent visual Transformer networks, as well as on a text classification problem, and demonstrate a clear advantage over the existing explainability methods.

关键词： Visualization computer vision Head Text categorization Neural networks Transformers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Video Representations of Human Motion from Synthetic Data

Learning Video Representations of Human Motion from Syntheti...

引用

2022 ieee/CVF conference on computer vision and pattern recognition, CVPR 2022

作者： Guo, Xi Wu, Wei Wang, Dongliang Su, Jing Su, Haisheng Gan, Weihao Huang, Jian Yang, Qin Beihang University China SenseTime Research

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

In this paper, we take an early step towards video representation learning of human actions with the help of large-scale synthetic videos, particularly for human motion representation enhancement. Specifically, we first introduce an automatic action-related video synthesis pipeline based on a photorealistic video game. A large-scale human action dataset named GATA (GTA Animation Transformed Actions) is then built by the proposed pipeline, which includes 8.1 million action clips spanning over 28K action classes. Based on the presented dataset, we design a contrastive learning framework for human motion representation learning, which shows significant performance improvements on several typical video datasets for action recognition, e.g., Charades, HAA 500 and NTU-RGB. Besides, we further explore a domain adaptation method based on cross-domain positive pairs mining to alleviate the domain gap between synthetic and realistic data. Extensive properties analyses of learned representation are conducted to demonstrate the effectiveness of the proposed dataset for enhancing human motion representation learning. © 2022 ieee.

关键词： Representation learning computer vision Pipelines Games Animation Data mining

来源：评论

学校读者我要写书评

暂无评论

Positive-Congruent Training: Towards Regression-Free Model Updates

Positive-Congruent Training: Towards Regression-Free Model U...

引用

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

作者： Yan, Sijie Xiong, Yuanjun Kundu, Kaustav Yang, Shuo Deng, Siqi Wang, Meng Xia, Wei Soatto, Stefano Amazon AI AWS Seattle WA 98195 USA

ISBN: (纸本)9781665445092

Reducing inconsistencies in the behavior of different versions of an AI system can be as important in practice as reducing its overall error. In image classification, sample-wise inconsistencies appear as "negative flips": A new model incorrectly predicts the output for a test sample that was correctly classified by the old (reference) model. Positive-congruent (PC) training aims at reducing error rate while at the same time reducing negative flips, thus maximizing congruency with the reference model only on positive predictions, unlike model distillation. We propose a simple approach for PC training, Focal Distillation, which enforces congruence with the reference model by giving more weights to samples that were correctly classified. We also found that, if the reference model itself can be chosen as an ensemble of multiple deep neural networks, negative flips can be further reduced without affecting the new model's accuracy.

关键词： Training Deep learning computer vision Error analysis Computational modeling Predictive models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SiamMOT: Siamese Multi-Object Tracking

SiamMOT: Siamese Multi-Object Tracking

引用

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

作者： Shuai, Bing Berneshawi, Andrew Li, Xinyu Modolo, Davide Tighe, Joseph Amazon Web Serv AWS Seattle WA 98109 USA

ISBN: (纸本)9781665445092

In this paper, we focus on improving online multi-object tracking (MOT). In particular, we introduce a region-based Siamese Multi-Object Tracking network, which we name SiamMOT. SiamMOT includes a motion model that estimates the instance's movement between two frames such that detected instances are associated. To explore how the motion modelling affects its tracking capability, we present two variants of Siamese tracker, one that implicitly models motion and one that models it explicitly. We carry out extensive quantitative experiments on three different MOT datasets: MOT17, TAO-person and Caltech Roadside Pedestrians, showing the importance of motion modelling for MOT and the ability of SiamMOT to substantially outperform the state-of-the-art. Finally, SiamMOT also outperforms the winners of ACM MM'20 HiEve Grand Challenge on HiEve dataset. Moreover, SiamMOT is efficient, and it runs at 17 FPS for 720P videos on a single modern GPU.

关键词： computer vision Tracking Graphics processing units pattern recognition Videos

来源：评论

学校读者我要写书评

暂无评论

Learning optical flow from still images

Learning optical flow from still images

引用

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

作者： Aleotti, Filippo Poggi, Matteo Mattoccia, Stefano Univ Bologna Bologna Italy

ISBN: (纸本)9781665445092

This paper deals with the scarcity of data for training optical flow networks, highlighting the limitations of existing sources such as labeled synthetic datasets or unlabeled real videos. Specifically, we introduce a framework to generate accurate ground-truth optical flow annotations quickly and in large amounts from any readily available single real picture. Given an image, we use an off-the-shelf monocular depth estimation network to build a plausible point cloud for the observed scene. Then, we virtually move the camera in the reconstructed environment with known motion vectors and rotation angles, allowing us to synthesize both a novel view and the corresponding optical flow field connecting each pixel in the input image to the one in the new frame. When trained with our data, state-of-the-art optical flow networks achieve superior generalization to unseen real data compared to the same models trained either on annotated synthetic datasets or unlabeled videos, and better specialization if combined with synthetic images.

关键词： Training computer vision Computational modeling Training data Estimation Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

PDET: Progressive Diversity Expansion Transformer for Cross-Modality Visible-Infrared Person Re-identification 27th

PDET: Progressive Diversity Expansion Transformer for Cross...

引用

27th International conference on pattern recognition, ICPR 2024

作者： Xiong, Mingfu Liang, Jingbang Guo, Yifei Lee, Ik Hyun Bakshi, Sambit Muhammad, Khan School of Computer Science and Artificial Intelligence Wuhan Textile University Hubei Wuhan430200 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China Department of Mechatronics Engineering Tech University of Korea and IKLAB Inc. Seoul Korea Republic of Department of Computer Science and Engineering National Institute of Technology Rourkela Rourkela India School of Convergence Sungkyunkwan University Seoul03063 Korea Republic of

ISBN: (纸本)9783031783401

Visible-Infrared Person Re-identification (VI-ReID) would effectively improve the recognition performance in weak-lighting and nighttime scenes, which is an important research direction in pattern recognition and computer vision. However, existing methods usually focus on reducing the image differences between modalities (visible and infrared) to extract more reliable features, while neglecting the ability to discriminate the different identities with similar appearances. To address this problem, we propose a framework called "Progressive Diversity Expansion Transformer (PDET)", which includes a Diversity Distinguishing vision Transformer Module (DDViTM) and a Cross-Modality Similarity Matching (CMSM) module for VI-ReID in this study. The DDViTM is proposed to implement the multiple embedded output vectors for a single input, learning feature representations of individual pedestrians in different modalities. The second module (CMSM) is used to improve the feature similarity between visible and infrared images, and dynamically adjust the image sequence weights of the two modalities to complete the training and optimization efficiency for the entire network. We conducted extensive experiments on the SYSU-MM01 and RegDB datasets, widely recognized public datasets for VR-ReID. The results demonstrate that the algorithm presented in this work has achieved promising performance compared to state-of-the-art methods. The code is available at https://***/jxsiaj/***. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Information-Theoretic Segmentation by Inpainting Error Maximization

Information-Theoretic Segmentation by Inpainting Error Maxim...

引用

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

作者： Savarese, Pedro Kim, Sunnie S. Y. Maire, Michael Shakhnarovich, Greg McAllester, David TTI Chicago Chicago IL 60637 USA Princeton Univ Princeton NJ 08544 USA Univ Chicago Chicago IL 60637 USA

ISBN: (纸本)9781665445092

We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into foreground and background, with the goal of minimizing predictability of one set from the other. An easily computed loss drives a greedy search process to maximize inpainting error over these partitions. Our method does not involve training deep networks, is computationally cheap, class-agnostic, and even applicable in isolation to a single unlabeled image. Experiments demonstrate that it achieves a new state-of-the-art in unsupervised segmentation quality, while being substantially faster and more general than competing approaches.

关键词： Training Deep learning Image segmentation computer vision Computational modeling pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Leaf recognition Using K-Nearest Neighbors Algorithm with Zernike Moments 8

Leaf Recognition Using K-Nearest Neighbors Algorithm with Ze...

引用

8th International conference on Image, vision and Computing, ICIVC 2023

作者： Jia, Zhuohao Liao, Simon The University of Winnipeg Department of Applied Computer Science Winnipeg Canada

ISBN: (纸本)9798350335231

Leaf recognition is a vital component of plant classification, which is crucial in agricultural automation. Previous studies have employed various machine learning algorithms, ranging from deep learning methods such as Convolutional Neural Network (CNN) to traditional methods like Support Vector Machine (SVM), and demonstrated success in leaf recognition. This study introduces a method for leaf recognition that employs the k-Nearest Neighbors (k-NN) algorithm as the classifier and utilizes Zernike moments as the image features. The proposed method is evaluated on the Flavia leaf dataset, and the results affirm the effectiveness of the approach. Furthermore, while Zernike moments have been extensively studied by researchers in the image recognition domain, they have predominantly been limited to a maximum order of 10. This study explores the use of Zernike moments with different maximum orders, including higher orders, to evaluate their classification abilities for leaf recognition. © 2023 ieee.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts

VDSM: Unsupervised Video Disentanglement with State-Space Mo...

引用

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

作者： Vowels, Matthew J. Camgoz, Necati Cihan Bowden, Richard Univ Surrey Ctr Vis Speech & Signal Proc Guildford Surrey England

ISBN: (纸本)9781665445092

Disentangled representations support a range of downstream tasks including causal reasoning, generative modeling, and fair machine learning. Unfortunately, disentanglement has been shown to be impossible without the incorporation of supervision or inductive bias. Given that supervision is often expensive or infeasible to acquire, we choose to incorporate structural inductive bias and present an unsupervised, deep State-Space-Model for Video Disentanglement (VDSM). The model disentangles latent time-varying and dynamic factors via the incorporation of hierarchical structure with a dynamic prior and a Mixture of Experts decoder. VDSM learns separate disentangled representations for the identity of the object or person in the video, and for the action being performed. We evaluate VDSM across a range of qualitative and quantitative tasks including identity and dynamics transfer;sequence generation, Frechet Inception Distance, and factor classification. VDSM achieves state-of-the-art performance and exceeds adversarial methods, even when the methods use additional supervision.

关键词： computer vision Computational modeling Machine learning Cognition pattern recognition Decoding Task analysis

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 << < 435 436 437 438 439 440 441 442 443 444 > >>

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：