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

1,928 篇 会议
241 册 图书
24 篇 期刊文献

馆藏范围

2,192 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,607 篇 工学
- 1,334 篇 计算机科学与技术...
- 466 篇 软件工程
- 250 篇 电气工程
- 235 篇 机械工程
- 186 篇 光学工程
- 179 篇 信息与通信工程
- 120 篇 控制科学与工程
- 96 篇 生物工程
- 62 篇 生物医学工程（可授...
- 42 篇 仪器科学与技术
- 39 篇 电子科学与技术（可...
- 30 篇 化学工程与技术
- 21 篇 安全科学与工程
- 18 篇 材料科学与工程（可...
- 15 篇 交通运输工程
- 13 篇 建筑学
444 篇 理学
- 257 篇 物理学
- 202 篇 数学
- 110 篇 生物学
- 57 篇 统计学（可授理学、...
- 22 篇 化学
228 篇 医学
- 200 篇 临床医学
- 26 篇 基础医学(可授医学...
- 22 篇 特种医学
137 篇 管理学
- 83 篇 图书情报与档案管...
- 60 篇 管理科学与工程(可...
- 19 篇 工商管理
27 篇 艺术学
- 27 篇 设计学（可授艺术学...
16 篇 农学
- 15 篇 作物学
15 篇 法学
- 13 篇 社会学
9 篇 教育学
7 篇 经济学
5 篇 文学
5 篇 军事学

主题

320 篇 computer vision
286 篇 pattern recognit...
166 篇 artificial intel...
122 篇 computer imaging...
119 篇 feature extracti...
101 篇 image processing...
82 篇 face recognition
68 篇 training
61 篇 object detection
60 篇 image segmentati...
57 篇 computer applica...
54 篇 deep learning
51 篇 robustness
47 篇 computer graphic...
46 篇 cameras
45 篇 visualization
43 篇 semantics
38 篇 machine learning
38 篇 object recogniti...
37 篇 shape

机构

89 篇 univ chinese aca...
67 篇 chinese acad sci...
60 篇 national laborat...
56 篇 chinese acad sci...
50 篇 univ chinese aca...
36 篇 chinese univ hon...
36 篇 university of ch...
31 篇 institute of aut...
27 篇 chinese acad sci...
26 篇 school of artifi...
23 篇 univ sci & techn...
22 篇 chinese academy ...
18 篇 chinese acad sci...
17 篇 chinese univ hon...
16 篇 chinese acad sci...
16 篇 univ chinese aca...
15 篇 national laborat...
15 篇 computer vision ...
14 篇 tsinghua univers...
14 篇 department of in...

作者

32 篇 wang xiaogang
29 篇 lu hanqing
28 篇 tan tieniu
28 篇 wang jinqiao
23 篇 li stan z.
22 篇 pal umapada
21 篇 huang kaiqi
21 篇 lei zhen
21 篇 qiao yu
19 篇 tieniu tan
19 篇 hu weiming
18 篇 tang xiaoou
17 篇 xilin chen
15 篇 wang liang
15 篇 chen xilin
15 篇 cheng jian
14 篇 liu jing
14 篇 tang ming
13 篇 xiaoou tang
13 篇 shiguang shan

语言

2,162 篇 英文
19 篇 中文
17 篇 其他
1 篇 土耳其文

检索条件"任意字段=7th Chinese Conference on Pattern Recognition and Computer Vision"

共 2193 条记录，以下是921-930 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：

Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description 30

Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Desc...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhang, Xishan Gao, Ke Zhang, Yongdong Zhang, Dongming Li, Jintao Tian, Qi Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Univ Texas San Antonio Dept Comp Sci San Antonio TX USA

ISBN: (纸本)9781538604571

Integrating complementary features from multiple channels is expected to solve the description ambiguity problem in video captioning, whereas inappropriate fusion strategies often harm rather than help the performance. Existing static fusion methods in video captioning such as concatenation and summation cannot attend to appropriate feature channels, thus fail to adaptively support the recognition of various kinds of visual entities such as actions and objects. this paper contributes to: 1) the first in-depth study of the weakness inherent in data-driven static fusion methods for video captioning. 2) the establishment of a task-driven dynamic fusion (TDDF) method. It can adaptively choose different fusion patterns according to model status. 3) the improvement of video captioning. Extensive experiments conducted on two well-known benchmarks demonstrate that our dynamic fusion method outperforms the state-of-the-art results on MSVD with METEOR scores 0.333, and achieves superior METEOR scores 0.278 on MSR-VTT-10K. Compared to single features, the relative improvement derived from our fusion method are 10.0% and 5.7% respectively on two datasets.

关键词： Visualization Dynamics Feature extraction Adaptation models Artificial neural networks Decoding

来源：评论

学校读者我要写书评

暂无评论

Hard Mixtures of Experts for Large ScaleWeakly Supervised vision 30

Hard Mixtures of Experts for Large ScaleWeakly Supervised Vi...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Gross, Sam Ranzato, Marc'Aurelio Szlam, Arthur Facebook AI Res Menlo Pk CA USA

ISBN: (纸本)9781538604571

Training convolutional networks (CNN's) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective method for training large CNN's that do not fit in the memory of a few GPU cards, or for parallelizing CNN training. In this work we show that a simple hard mixture of experts model can be efficiently trained to good effect on large scale hashtag (multilabel) prediction tasks. Mixture of experts models are not new [7, 3], but in the past, researchers have had to devise sophisticated methods to deal with data fragmentation. We show empirically that modern weakly supervised data sets are large enough to support naive partitioning schemes where each data point is assigned to a single expert. Because the experts are independent, training them in parallel is easy, and evaluation is cheap for the size of the model. Furthermore, we show that we can use a single decoding layer for all the experts, allowing a unified feature embedding space. We demonstrate that it is feasible (and in fact relatively painless) to train far larger models than could be practically trained with standard CNN architectures, and that the extra capacity can be well used on current datasets.

关键词： Professional personnel model size Dataset Functional training GRAPPER PICK UP Graphics Processing Unit expert model

来源：评论

学校读者我要写书评

暂无评论

Same-style products mining for clothes retrieval

Same-style products mining for clothes retrieval

引用

9th International conference on Internet Multimedia Computing and Service, ICIMCS 2017

作者： Shen, Zhenwei Fang, Zhiwei Liu, Jing Shandong University of Science and Technology Qingdao China National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789811085291

Same-style clothes retrieval is a task to search images which contain exactly the same designing style clothes. For such a task, too limited training data makes the problem of how to gain suitable same-style feature representations challenging but significant. In this paper, we adopt a memory-augmented deep neural network, also called as a few-shot learning model, to collect possibly same-style images. Besides, we present an object-aware clothes retrieval framework to further enhance the same-style feature representations, in which object focusing regions through object detection are first obtained, and a multi-task Siamese network is designed for ranking feature learning provided with some same-style or non-same-style image pairs. Experiments results show that our proposed solution is effective to discover more same-style images precisely, and further achieve the satisfied performance on same-style clothes retrieval. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Re-ranking Person Re-identification with k-reciprocal Encoding 30

Re-ranking Person Re-identification with <i>k</i>-reciprocal...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhong, Zhun Zheng, Liang Cao, Donglin Li, Shaozi Xiamen Univ Cognit Sci Dept Xiamen Peoples R China Univ Technol Sydney Sydney NSW Australia Xiamen Univ Fujian Key Lab Brain Inspired Comp Tech & Applica Xiamen Peoples R China

ISBN: (纸本)9781538604571

When considering person re-identification (re-ID) as a retrieval process, re-ranking is a critical step to improve its accuracy. Yet in the re-ID community, limited effort has been devoted to re-ranking, especially those fully automatic, unsupervised solutions. In this paper, we propose a k-reciprocal encoding method to re-rank the re-ID results. Our hypothesis is that if a gallery image is similar to the probe in the k-reciprocal nearest neighbors, it is more likely to be a true match. Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance. the final distance is computed as the combination of the original distance and the Jaccard distance. Our re-ranking method does not require any human interaction or any labeled data, so it is applicable to large-scale datasets. Experiments on the large-scale Market-1501, CUHK03, MARS, and PRW datasets confirm the effectiveness of our method(1).

关键词： Probes Encoding Measurement Feature extraction computer vision Robustness

来源：评论

学校读者我要写书评

暂无评论

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade 30

<i>Not All Pixels Are Equal</i>: Difficulty-Aware Semantic S...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Li, Xiaoxiao Liu, Ziwei Luo, Ping Loy, Chen Change Tang, Xiaoou Chinese Univ Hong Kong Dept Informat Engn Hong Kong Hong Kong Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab Comp Vis & Pat Rec Beijing Peoples R China

ISBN: (纸本)9781538604571

We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a cascade of several sub-models. Earlier sub-models are trained to handle easy and confident regions, and they progressively feed-forward harder regions to the next sub-model for processing. Convolutions are only calculated on these regions to reduce computations. the proposed method possesses several advantages. First, LC classifies most of the easy regions in the shallow stage and makes deeper stage focuses on a few hard regions. Such an adaptive and 'difficulty-aware' learning improves segmentation performance. Second, LC accelerates both training and testing of deep network thanks to early decisions in the shallow stage. third, in comparison to MC, LC is an end-to-end trainable framework, allowing joint learning of all sub-models. We evaluate our method on PASCAL VOC and Cityscapes datasets, achieving state-of-the-art performance and fast speed.

关键词： Difficulty-Aware Semantic Segmentation Deep Layer Cascade cascades Deep layer submodel line controller segmentation Segmentation Semantics urban landscape

来源：评论

学校读者我要写书评

暂无评论

Detecting Masked Faces in the Wild with LLE-CNNs 30

Detecting Masked Faces in the Wild with LLE-CNNs

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Ge, Shiming Li, Jia Ye, Qiting Luo, Zhao Chinese Acad Sci Beijing Key Lab IOT Informat Secur Inst Informat Engn Beijing Peoples R China Beihang Univ Sch Comp Sci & Engn State Key Lab Virtual Real Technol & Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9781538604571

Detecting faces with occlusions is a challenging task due to two main reasons: 1) the absence of large datasets of masked faces, and 2) the absence of facial cues from the masked regions. To address these two issues, this paper first introduces a dataset, denoted as MAFA, with 30, 811 Internet images and 35, 806 masked faces. Faces in the dataset have various orientations and occlusion degrees, while at least one part of each face is occluded by mask. Based on this dataset, we further propose LLE-CNNs for masked face detection, which consist of three major modules. the Proposal module first combines two pre-trained CNNs to extract candidate facial regions from the input image and represent them with high dimensional descriptors. After that, the Embedding module is incorporated to turn such descriptors into a similarity-based descriptor by using locally linear embedding (LLE) algorithm and the dictionaries trained on a large pool of synthesized normal faces, masked faces and non-faces. In this manner, many missing facial cues can be largely recovered and the influences of noisy cues introduced by diversified masks can be greatly alleviated. Finally, the Verification module is incorporated to identify candidate facial regions and refine their positions by jointly performing the classification and regression tasks within a unified CNN. Experimental results on the MAFA dataset show that the proposed approach remarkably outperforms 6 state-of-the-arts by at least 15.6%.

关键词： Face detection Detectors Feature extraction Deformable models Proposals Training

来源：评论

学校读者我要写书评

暂无评论

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification 30

Learning Deep Context-aware Features over Body and Latent Pa...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Li, Dangwei Chen, Xiaotang Zhang, Zhang Huang, Kaiqi CASIA CRIPAC Beijing Peoples R China CASIA NLPR Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing Peoples R China

ISBN: (纸本)9781538604571

Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc. How to extract powerful features is a fundamental problem in ReID and is still an open problem today. In this paper, we design a Multi-Scale Context-Aware Network (MSCAN) to learn powerful features over full body and body parts, which can well capture the local context knowledge by stacking multi-scale convolutions in each layer. Moreover, instead of using predefined rigid parts, we propose to learn and localize deformable pedestrian parts using Spatial Transformer Networks (STN) with novel spatial constraints. the learned body parts can release some difficulties, e.g. pose variations and background clutters, in part-based representation. Finally, we integrate the representation learning processes of full body and body parts into a unified framework for person ReID through multi-class person identification tasks. Extensive evaluations on current challenging large-scale person ReID datasets, including the image-based Market1501, CUHK03 and sequence-based MARS datasets, show that the proposed method achieves the state-of-the-art results.

关键词： Kernel Visualization Machine learning Clutter Feature extraction Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Learning Multifunctional Binary Codes for Both Category and Attribute Oriented Retrieval Tasks 30

Learning Multifunctional Binary Codes for Both Category and ...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Liu, Haomiao Wang, Ruiping Shan, Shiguang Chen, Xilin Chinese Acad Sci Key Lab Intelligent Informat Proc Inst Comp Technol Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Cooperat Medianet Innovat Ctr Beijing Peoples R China

ISBN: (纸本)9781538604571

In this paper we propose a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes. Considering the scale of modern datasets, hashing is favorable for its low complexity. However, most existing hashing methods are designed to preserve one single kind of similarity, thus incapable of dealing with the different tasks simultaneously. To overcome this limitation, we propose a new hashing method, named Dual Purpose Hashing (DPH), which jointly preserves the category and attribute similarities by exploiting the convolutional networks (CNN) to hierarchically capture the correlations between category and attributes. Since images with both category and attribute labels are scarce, our method is designed to take the abundant partially labelled images on the Internet as training inputs. With such a framework, the binary codes of new-coming images can be readily obtained by quantizing the network outputs of a binary-like layer, and the attributes can be recovered from the codes easily. Experiments on two large-scale datasets show that our dual purpose hash codes can achieve comparable or even better performance than those state-of-the-art methods specifically designed for each individual retrieval task, while being more compact than the compared methods.

关键词： Learning Multifunctional Binary Codes Both Category Attribute Oriented Retrieval Tasks Category binary code hashing method hashing Religious Missions retrieval

来源：评论

学校读者我要写书评

暂无评论

Oriented Response Networks 30

Oriented Response Networks

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhou, Yanzhao Ye, Qixiang Qiu, Qiang Jiao, Jianbin Univ Chinese Acad Sci Beijing Peoples R China Duke Univ Durham NC 27706 USA

ISBN: (纸本)9781538604571

Deep Convolution Neural Networks (DCNNs) are capable of learning unprecedentedly effective image representations. However, their ability in handling significant local and global image rotations remains limited. In this paper, we propose Active Rotating Filters (ARFs) that actively rotate during convolution and produce feature maps with location and orientation explicitly encoded. An ARF acts as a virtual filter bank containing the filter itself and its multiple unmaterialised rotated versions. During back-propagation, an ARF is collectively updated using errors from all its rotated versions. DCNNs using ARFs, referred to as Oriented Response Networks (ORNs), can produce within-class rotation-invariant deep features while maintaining inter-class discrimination for classification tasks. the oriented response produced by ORNs can also be used for image and object orientation estimation tasks. Over multiple state-of-the-art DCNN architectures, such as VGG, ResNet, and STN, we consistently observe that replacing regular filters with the proposed ARFs leads to significant reduction in the number of network parameters and improvement in classification performance. We report the best results on several commonly used benchmarks(1).

关键词： feature map image representation Convolution Filters Oriented network parameters super twisted nematic images Imagery (Psychotherapy) reduction index object orientation

来源：评论

学校读者我要写书评

暂无评论

A Generative Model for Depth-based Robust 3D Facial Pose Tracking 30

A Generative Model for Depth-based Robust 3D Facial Pose Tra...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Sheng, Lu Cai, Jianfei Cham, Tat-Jen Pavlovic, Vladimir Ngan, King Ngi Chinese Univ Hong Kong Hong Kong Hong Kong Peoples R China Nanyang Technol Univ Singapore Singapore Rutgers State Univ New Brunswick NJ USA

ISBN: (纸本)9781538604571

We consider the problem of depth-based robust 3D facial pose tracking under unconstrained scenarios with heavy occlusions and arbitrary facial expression variations. Unlike the previous depth-based discriminative or data-driven methods that require sophisticated training or manual intervention, we propose a generative framework that unifies pose tracking and face model adaptation on-the-fly. Particularly, we propose a statistical 3D face model that owns the flexibility to generate and predict the distribution and uncertainty underlying the face model. Moreover, unlike prior arts employing the ICP-based facial pose estimation, we propose a ray visibility constraint that regularizes the pose based on the face model's visibility against the input point cloud, which augments the robustness against the occlusions. the experimental results on Biwi and ICT-3DHP datasets reveal that the proposed framework is effective and outperforms the state-of-the-art depth-based methods.

关键词： face modeling tracking Face Face visibility Occlusion Robustness entry point symbol

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220页 << < 89 90 91 92 93 94 95 96 97 98 > >>

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：