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

33 篇 会议

馆藏范围

33 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

33 篇 工学
- 33 篇 计算机科学与技术...

主题

33 篇 rgbd sensors and...
18 篇 deep learning
13 篇 3d from multivie...
6 篇 robotics + drivi...
5 篇 3d from single i...
5 篇 scene analysis a...
4 篇 categorization
4 篇 representation l...
4 篇 action recogniti...
4 篇 recognition: det...
4 篇 retrieval
4 篇 datasets and eva...
3 篇 and body pose
3 篇 gesture
3 篇 low-level vision
3 篇 face
2 篇 segmentation
2 篇 motion and track...
2 篇 optimization met...
2 篇 vision + graphic...

机构

2 篇 princeton univ p...
2 篇 univ padua padua
2 篇 nanjing univ sci...
2 篇 tech univ munich...
2 篇 nankai univ cs t...
2 篇 microsoft redmon...
2 篇 stanford univ st...
1 篇 acrv brisbane ql...
1 篇 hkust peoples r ...
1 篇 statekey lab cad...
1 篇 facebook ai res ...
1 篇 uber adv technol...
1 篇 katholieke univ ...
1 篇 univ ljubljana f...
1 篇 siemens ag munic...
1 篇 univ pittsburgh ...
1 篇 facebook ai res ...
1 篇 dji peoples r ch...
1 篇 youtu lab people...
1 篇 nyu ny 10003 usa

作者

2 篇 fan deng-ping
2 篇 huang jingwei
2 篇 cheng ming-ming
1 篇 liu xiaoming
1 篇 li xuan-yi
1 篇 miraldo pedro
1 篇 zhao jia-xing
1 篇 gao shenghua
1 篇 matas jiri
1 篇 luo weixin
1 篇 wang limin
1 篇 qi zhongang
1 篇 laddha ankit
1 篇 williams francis
1 篇 van gool luc
1 篇 savarese silvio
1 篇 tombari federico
1 篇 song shuran
1 篇 liu yue
1 篇 wu gangshan

语言

33 篇 英文

检索条件"主题词=RGBD sensors and analytics"

共 33 条记录，以下是1-10 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：

Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation 32

Normalized Object Coordinate Space for Category-Level 6D Obj...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wang, He Sridhar, Srinath Huang, Jingwei Valentin, Julien Song, Shuran Guibas, Leonidas J. Stanford Univ Stanford CA 94305 USA Google Inc Mountain View CA USA Princeton Univ Princeton NJ 08544 USA Facebook AI Res Sunnyvale CA USA

ISBN: (纸本)9781728132938

The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image. Contrary to "instance-level'' 6D pose estimation tasks, our problem assumes that no exact object CAD models are available during either training or testing time. To handle different and unseen object instances in a given category, we introduce a Normalized Object Coordinate Space (NOCS)-a shared canonical representation for all possible object instances within a category. Our region-based neural network is then trained to directly infer the correspondence from observed pixels to this shared object representation (NOCS) along with other object information such as class label and instance mask. These predictions can be combined with the depth map to jointly estimate the metric 6D pose and dimensions of multiple objects in a cluttered scene. To train our network, we present a new context-aware technique to generate large amounts of fully annotated mixed reality data. To further improve our model and evaluate its performance on real data, we also provide a fully annotated real-world dataset with large environment and instance variation. Extensive experiments demonstrate that the proposed method is able to robustly estimate the pose and size of unseen object instances in real environments while also achieving state-of-the-art performance on standard 6D pose estimation benchmarks.

关键词： 3D from Single Image Datasets and Evaluation Deep Learning rgbd sensors and analytics Scene Analysis and Understanding Vision Ap

来源：评论

学校读者我要写书评

暂无评论

Cross Domain Model Compression by Structurally Weight Sharing 32

Cross Domain Model Compression by Structurally Weight Sharin...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Gao, Shangqian Deng, Cheng Huang, Heng Univ Pittsburgh Elect & Comp Engn Dept Pittsburgh PA 15260 USA Xidian Univ Sch Elect Engn Xian Shaanxi Peoples R China JD Digits Beijing Peoples R China

ISBN: (纸本)9781728132938

Regular model compression methods focus on RGB input. While cross domain tasks demand more DNN models, each domain often needs its own model. Consequently, for such tasks, the storage cost, memory footprint and computation cost increase dramatically compared to single RGB input. Moreover, the distinct appearance and special structure in cross domain tasks make it difficult to directly apply regular compression methods on it. In this paper, thus, we propose a new robust cross domain model compression method. Specifically, the proposed method compress cross domain models by structurally weight sharing, which is achieved by regularizing the models with graph embedding at training time. Due to the channel wise weights sharing, the proposed method can reduce computation cost without specially designed algorithm. In the experiments, the proposed method achieves state-of-the-art results on two diverse tasks: action recognition and RGB-D scene recognition.

关键词： Action Recognition Deep Learning Others rgbd sensors and analytics

来源：评论

学校读者我要写书评

暂无评论

Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training 32

Improving the Performance of Unimodal Dynamic Hand-Gesture R...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Abavisani, Mahdi Joze, Hamid Reza Vaezi Patel, Vishal M. Rutgers State Univ New Brunswick NJ 08901 USA Microsoft Redmond WA USA Johns Hopkins Univ Baltimore MD 21218 USA

ISBN: (纸本)9781728132938

We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal information, which is commonplace in many state-of-the-art methods, we propose a different framework in which we embed the knowledge of multiple modalities in individual networks so that each unimodal network can achieve an improved performance. In particular, we dedicate separate networks per available modality and enforce them to collaborate and learn to develop networks with common semantics and better representations. We introduce a "spatiotemporal semantic alignment" loss (SSA) to align the content of the features from different networks. In addition, we regularize this loss with our proposed "focal regularization parameter" to avoid negative knowledge transfer. Experimental results show that our framework improves the test time recognition accuracy of unimodal networks, and provides the state-of-the-art performance on various dynamic hand gesture recognition datasets.

关键词： Action Recognition And Body Pose Face Gesture rgbd sensors and analytics

来源：评论

学校读者我要写书评

暂无评论

Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders 32

Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape C...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhou, Yuxiang Deng, Jiankang Kotsia, Irene Zafeiriou, Stefanos Imperial Coll London London England Univ Middlesex London England FaceSoft London England

ISBN: (纸本)9781728132938

3D Morphable Models (3DMMs) are statistical models that represent facial texture and shape variations using a set of linear bases and more particular Principal Component Analysis (PCA). 3DMMs were used as statistical priors for reconstructing 3D faces from images by solving non-linear least square optimization problems. Recently, 3DMMs were used as generative models for training non-linear mappings (i.e., regressors) from image to the parameters of the models via Deep Convolutional Neural Networks (DCNNs). Nevertheless, all of the above methods use either fully connected layers or 2D convolutions on parametric unwrapped UV spaces leading to large networks with many parameters. In this paper, we present the first, to the best of our knowledge, non-linear 3DMMs by learning joint texture and shape auto-encoders using direct mesh convolutions. We demonstrate how these auto-encoders can be used to train very light-weight models that perform Coloured Mesh Decoding (CMD) in-the-wild at a speed of over 2500 FPS.

关键词： 3D from Single Image And Body Pose Deep Learning Face Gesture Representation Learning rgbd sensors and analytics Segmentat

来源：评论

学校读者我要写书评

暂无评论

Translate-to-Recognize Networks for RGB-D Scene Recognition 32

Translate-to-Recognize Networks for RGB-D Scene Recognition

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Du, Dapeng Wang, Limin Wang, Huiling Zhao, Kai Wu, Gangshan Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

ISBN: (纸本)9781728132938

Cross-modal transfer is helpful to enhance modality-specific discriminative power for scene recognition. To this end, this paper presents a unified framework to integrate the tasks of cross-modal translation and modality-specific recognition, termed as Translate-to-Recognize Network (TRecgNet). Specifically, both translation and recognition tasks share the same encoder network, which allows to explicitly regularize the training of recognition task with the help of translation, and thus improve its final generalization ability. For translation task, we place a decoder module on top of the encoder network and it is optimized with a new layer-wise semantic loss, while for recognition task, we use a linear classifier based on the feature embedding from encoder and its training is guided by the standard cross-entropy loss. In addition, our TRecgNet allows to exploit large numbers of unlabeled RGB-D data to train the translation task and thus improve the representation power of encoder network. Empirically, we verify that this new semi-supervised setting is able to further enhance the performance of recognition network. We perform experiments on two RGB-D scene recognition benchmarks: NYU Depth v2 and SUN RGB-D, demonstrating that TRecgNet achieves superior performance to the existing state-of-the-art methods, especially for recognition solely based on a single modality.

关键词： Categorization Recognition: Detection Representation Learning Retrieval rgbd sensors and analytics Scene Analysis and Under

来源：评论

学校读者我要写书评

暂无评论

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion 32

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fu...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wang, Chen Xu, Danfei Zhu, Yuke Martin-Martin, Roberto Lu, Cewu Li Fei-Fei Savarese, Silvio Stanford Univ Dept Comp Sci Stanford CA 94305 USA Shanghai Jiao Tong Univ Dept Comp Sci Shanghai Peoples R China

ISBN: (纸本)9781728132938

A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image and depth separately or use costly post-processing steps, limiting their performances in highly cluttered scenes and real-time applications. In this work, we present DenseFusion, a generic framework for estimating 6D pose of a set of known objects from rgbd images. DenseFusion is a heterogeneous architecture that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated. Furthermore, we integrate an end-to-end iterative pose refinement procedure that further improves the pose estimation while achieving near real-time inference. Our experiments show that our method outperforms state-of-the-art approaches in two datasets, YCB-Video and LineMOD. We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose. Our code and video are available at https://***/view/densefusion/.

关键词： 3D from Multiview and sensors Categorization Deep Learning Recognition: Detection Retrieval rgbd sensors and analytics Robot

来源：评论

学校读者我要写书评

暂无评论

Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach 32

Veritatem Dies Aperit - Temporally Consistent Depth Predicti...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Atapour-Abarghouei, Amir Breckon, Toby P. Univ Durham Dept Comp Sci Durham England Univ Durham Dept Engn Durham England

ISBN: (纸本)9781728132938

Robust geometric and semantic scene understanding is ever more important in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based approach capable of jointly performing geometric and semantic scene understanding, namely depth prediction (monocular depth estimation and depth completion) and semantic scene segmentation. Within a single temporally constrained recurrent network, our approach uniquely takes advantage of a complex series of skip connections, adversarial training and the temporal constraint of sequential frame recurrence to produce consistent depth and semantic class labels simultaneously. Extensive experimental evaluation demonstrates the efficacy of our approach compared to other contemporary state-of-the-art techniques.

关键词： 3D from Single Image Deep Learning Grouping and Shape rgbd sensors and analytics Segmentation

来源：评论

学校读者我要写书评

暂无评论

Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping 32

Temporal Transformer Networks: Joint Learning of Invariant a...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lohit, Suhas Wang, Qiao Turaga, Pavan Arizona State Univ Geometr Media Lab Tempe AZ 85287 USA SRI Int 333 Ravenswood Ave Menlo Pk CA 94025 USA

ISBN: (纸本)9781728132938

Many time-series classification problems involve developing metrics that are invariant to temporal misalignment. In human activity analysis, temporal misalignment arises due to various reasons including differing initial phase, sensor sampling rates, and elastic time-warps due to subject-specific biomechanics. Past work in this area has only looked at reducing intra-class variability by elastic temporal alignment. In this paper, we propose a hybrid model-based and data-driven approach to learn warping functions that not just reduce intra-class variability, but also increase inter-class separation. We call this a temporal transformer network (TTN). TTN is an interpretable differentiable module, which can be easily integrated at the front end of a classification network. The module is capable of reducing intra-class variance by generating input-dependent warping functions which lead to rate-robust representations. At the same time, it increases inter-class variance by learning warping functions that are more discriminative. We show improvements over strong baselines in 3D action recognition on challenging datasets using the proposed framework. The improvements are especially pronounced when training sets are smaller.

关键词： Action Recognition Representation Learning rgbd sensors and analytics Statistical Learning

来源：评论

学校读者我要写书评

暂无评论

FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization 32

FilterReg: Robust and Efficient Probabilistic Point-Set Regi...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Gao, Wei Tedrake, Russ MIT Cambridge MA 02139 USA

ISBN: (纸本)9781728132938

Probabilistic point-set registration methods have been gaining more attention for their robustness to noise, out-liers and occlusions. However, these methods tend to be much slower than the popular iterative closest point (ICP) algorithms, which severely limits their usability. In this paper, we contribute a novel probabilistic registration method that achieves state-of-the-art robustness as well as substantially faster computational performance than modern ICP implementations. This is achieved using a rigorous yet computationally-efficient probabilistic formulation. Point-set registration is cast as a maximum likelihood estimation and solved using the EM algorithm. We show that with a simple augmentation, the E step can be formulated as a filtering problem, allowing us to leverage advances in efficient Gaussian filtering methods. We also propose a customized permutohedral filter [1] for improved efficiency while retaining sufficient accuracy for our task. Additionally, we present a simple and efficient twist parameterization that generalizes our method to the registration of articulated and deformable objects. For articulated objects, the complexity of our method is almost independent of the Degrees Of Freedom (DOFs). The results demonstrate the proposed method consistently outperforms many competitive baselines on a variety of registration tasks.

关键词： Low-level Vision Motion and Tracking Optimization Methods rgbd sensors and analytics Robotics + Driving

来源：评论

学校读者我要写书评

暂无评论

Learning to Explore Intrinsic Saliency for Stereoscopic Video 32

Learning to Explore Intrinsic Saliency for Stereoscopic Vide...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhang, Qiudan Wang, Xu Wang, Shiqi Li, Shikai Kwong, Sam Jiang, Jianmin Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen Guangdong Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

ISBN: (纸本)9781728132938

The human visual system excels at biasing the stereo-scopic visual signals by the attention mechanisms. Traditional methods relying on the low-level features and depth relevant information for stereoscopic video saliency prediction have fundamental limitations. For example, it is cumbersome to model the interactions between multiple visual cues including spatial, temporal, and depth information as a result of the sophistication. In this paper, we argue that the high-level features are crucial and resort to the deep learning framework to learn the saliency map of stereoscopic videos. Driven by spatio-temporal coherence from consecutive frames, the model first imitates the mechanism of saliency by taking advantage of the 3D convolutional neural network. Subsequently, the saliency originated from the intrinsic depth is derived based on the correlations between left and right views in a data-driven manner. Finally, a Convolutional Long Short-Term Memory (Conv-LSTM) based fusion network is developed to model the instantaneous interactions between spatio-temporal and depth attributes, such that the ultimate stereoscopic saliency maps over time are produced. Moreover, we establish a new large-scale stereoscopic video saliency dataset (SVS) including 175 stereoscopic video sequences and their fixation density annotations, aiming to comprehensively study the intrinsic attributes for stereoscopic video saliency detection. Extensive experiments show that our proposed model can achieve superior performance compared to the state-of-the-art methods on the newly built dataset for stereoscopic videos.

关键词： 3D from Multiview and sensors Datasets and Evaluation Deep Learning rgbd sensors and analytics Video analytics

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4页 << < 1 2 3 4 > >>

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：