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

191 篇 会议
46 篇 期刊文献
6 篇 学位论文

馆藏范围

243 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

234 篇 工学
- 205 篇 计算机科学与技术...
- 156 篇 电气工程
- 13 篇 控制科学与工程
- 12 篇 软件工程
- 9 篇 机械工程
- 5 篇 信息与通信工程
- 5 篇 土木工程
- 3 篇 测绘科学与技术
- 3 篇 农业工程
- 2 篇 仪器科学与技术
- 2 篇 材料科学与工程（可...
- 2 篇 电子科学与技术（可...
- 2 篇 交通运输工程
- 1 篇 力学（可授工学、理...
- 1 篇 建筑学
- 1 篇 环境科学与工程（可...
- 1 篇 生物医学工程（可授...
- 1 篇 网络空间安全
153 篇 医学
- 150 篇 临床医学
- 4 篇 基础医学(可授医学...
- 2 篇 公共卫生与预防医...
10 篇 理学
- 4 篇 物理学
- 3 篇 地球物理学
- 2 篇 生物学
- 1 篇 数学
- 1 篇 化学
- 1 篇 生态学
8 篇 管理学
- 5 篇 管理科学与工程(可...
- 2 篇 公共管理
4 篇 农学
- 3 篇 作物学

主题

243 篇 3d computer visi...
128 篇 algorithms
34 篇 applications
25 篇 image recognitio...
21 篇 biometrics
20 篇 gesture
20 篇 face
20 篇 body pose
18 篇 and algorithms
18 篇 machine learning...
18 篇 formulations
15 篇 generative model...
15 篇 video
15 篇 3d
14 篇 deep learning
12 篇 computational ph...
12 篇 datasets and eva...
12 篇 image and video ...
11 篇 autonomous drivi...
10 篇 robotics

机构

6 篇 australian natl ...
4 篇 swiss fed inst t...
3 篇 univ waterloo wa...
3 篇 google res mount...
3 篇 carnegie mellon ...
3 篇 tech univ munich...
2 篇 iiit hyderabad h...
2 篇 univ copenhagen ...
2 篇 univ toronto on
2 篇 seoul natl univ
2 篇 concordia univ c...
2 篇 vienna univ tech...
2 篇 univ tubingen tu...
2 篇 microsoft redmon...
2 篇 tu wien austria
2 篇 guangxi univ col...
2 篇 chinese univ hon...
2 篇 fujitsu r&d ctr ...
2 篇 max planck inst ...
2 篇 samsung res

作者

3 篇 kortylewski adam
3 篇 friedrich markus
3 篇 linnhoff-popien ...
3 篇 li hongdong
3 篇 cremers daniel
3 篇 gould stephen
3 篇 adan antonio
2 篇 czarnecki krzysz...
2 篇 dong zhen
2 篇 sun shanlin
2 篇 pizarro daniel
2 篇 okutomi masatosh...
2 篇 yang t. y.
2 篇 zhang tong
2 篇 zhang qian
2 篇 liu chen
2 篇 gonzalez-ortega ...
2 篇 di stefano luigi
2 篇 huang sheng-yu
2 篇 bartoli adrien

语言

242 篇 英文
1 篇 其他

检索条件"主题词=3D Computer Vision"

共 243 条记录，以下是81-90 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：

Continual Learning of Unsupervised Monocular depth from Videos

Continual Learning of Unsupervised Monocular Depth from Vide...

引用

IEEE/CVF Winter Conference on Applications of computer vision (WACV)

作者： Chawla, Hemang Varma, Arnav Arani, Elahe Zonooz, Bahram Eindhoven Univ Technol TU E Eindhoven Netherlands TomTom Amsterdam Netherlands Wayve London England

ISBN: (纸本)9798350318920;9798350318937

Spatial scene understanding, including monocular depth estimation, is an important problem in various applications such as robotics and autonomous driving. While improvements in unsupervised monocular depth estimation have potentially allowed models to be trained on diverse crowdsourced videos, this remains underexplored as most methods utilize the standard training protocol wherein the models are trained from scratch on all data after new data is collected. Instead, continual training of models on sequentially collected data would significantly reduce computational and memory costs. Nevertheless, naive continual training leads to catastrophic forgetting, where the model performance deteriorates on older domains as it learns on newer domains, highlighting the trade-off between model stability and plasticity. While several techniques have been proposed to address this issue in image classification, the high-dimensional and spatiotemporally correlated outputs of depth estimation make it a distinct challenge. To the best of our knowledge, no framework or method currently exists focusing on the problem of continual learning in depth estimation. Thus, we introduce a framework that captures the challenges of continual unsupervised depth estimation (CUdE), and define the necessary metrics to evaluate model performance. We propose a rehearsal-based dual-memory method MonodepthCL, which utilizes spatiotemporal consistency for continual learning in depth estimation, even when the camera intrinsics are unknown.

关键词： 3d computer vision Algorithms Applications Applications Autonomous driving Robotics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Latent diffusion Model for 3d Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging Study

Adaptive Latent Diffusion Model for 3D Medical Image to Imag...

引用

IEEE/CVF Winter Conference on Applications of computer vision (WACV)

作者： Kim, Jonghun Park, Hyunjin Sungkyunkwan Univ Dept Elect & Comp Engn Suwon South Korea

ISBN: (纸本)9798350318920;9798350318937

Multi-modal images play a crucial role in comprehensive evaluations in medical image analysis providing complementary information for identifying clinically important biomarkers. However, in clinical practice, acquiring multiple modalities can be challenging due to reasons such as scan cost, limited scan time, and safety considerations. In this paper, we propose a model based on the latent diffusion model (LdM) that leverages switchable blocks for image-to-image translation in 3d medical images without patch cropping. The 3d LdM combined with conditioning using the target modality allows generating high-quality target modality in 3d overcoming the shortcoming of the missing out-of-slice information in 2d generation methods. The switchable block, noted as multiple switchable spatially adaptive normalization (MS-SPAdE), dynamically transforms source latents to the desired style of the target latents to help with the diffusion process. The MS-SPAdE block allows us to have one single model to tackle many translation tasks of one source modality to various targets removing the need for many translation models for different scenarios. Our model exhibited successful image synthesis across different source-target modality scenarios and surpassed other models in quantitative evaluations tested on multi-modal brain magnetic resonance imaging datasets of four different modalities and an independent IXI dataset. Our model demonstrated successful image synthesis across various modalities even allowing for one-to-many modality translations. Furthermore, it outperformed other one-to-one translation models in quantitative evaluations. Our code is available at https://***/jongdory/ALdM/ [GRAPHICS] .

关键词： 3d 3d computer vision Algorithms Algorithms Applications Biomedical / healthcare / medicine etc Generative models for image video

来源：评论

学校读者我要写书评

暂无评论

SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering

SupeRVol: Super-Resolution Shape and Reflectance Estimation ...

引用

IEEE/CVF Winter Conference on Applications of computer vision (WACV)

作者： Brahimi, Mohammed Haefner, Bjoern Yenamandra, Tarun Goldluecke, Bastian Cremers, daniel Tech Univ Munich Munich Germany Univ Konstanz Constance Germany Munich Ctr Machine Learning Munich Germany

ISBN: (纸本)9798350318920;9798350318937

We propose an end-to-end inverse rendering pipeline called SupeRVol that allows us to recover 3d shape and material parameters from a set of color images in a super-resolution manner. To this end, we represent both the bidirectional reflectance distribution function's (BRdF) parameters and the signed distance function (SdF) by multi-layer perceptrons (MLPs). In order to obtain both the surface shape and its reflectance properties, we revert to a differentiable volume renderer with a physically based illumination model that allows us to decouple reflectance and lighting. This physical model takes into account the effect of the camera's point spread function thereby enabling a reconstruction of shape and material in a super-resolution quality. Experimental validation confirms that SupeRVol achieves state of the art performance in terms of inverse rendering quality. It generates reconstructions that are sharper than the individual input images, making this method ideally suited for 3d modeling from low-resolution imagery.

关键词： 3d computer vision Algorithms

来源：评论

学校读者我要写书评

暂无评论

LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks 10

LC-NAS: Latency Constrained Neural Architecture Search for P...

引用

International Conference on 3d vision (3dV)

作者： Li, Guohao Xu, Mengmeng Giancola, Silvio Thabet, Ali Ghanem, Bernard King Abdullah Univ Sci & Technol KAUST Thuwal Saudi Arabia Meta Menlo Pk CA USA

ISBN: (纸本)9781665456708

Point cloud architecture design has become a crucial problem for deep learning in 3d. Several efforts have been made to manually design architectures targeting high accuracy in point cloud tasks such as classification, segmentation, and detection. Recent progress in automatic Neural Architecture Search (NAS) minimizes the human effort in network design and optimizes architectures for high performance. However, those efforts fail to consider crucial factors such as latency during inference, which is of high importance in time-critical and hardware-bounded applications like self-driving cars, robot navigation, and mobile applications. In this paper, we introduce a new NAS framework, dubbed LC-NAS, that searches for point cloud architectures constrained to a target latency. We implement a novel latency constraint formulation for the trade-off between accuracy and latency in our architecture search. Contrary to previous works, our latency loss enables us to find the best architecture with latency near a specific target value, which is crucial when the end task is to be deployed in a limited hardware setting. Extensive experiments show that LC-NAS is able to find state-of-the-art architectures for point cloud classification in ModelNet40 with a minimal computational cost. We also show how our searched architectures achieve any desired latency with a reasonably low drop in accuracy. Finally, we show how our searched architectures easily transfer to the part segmentation task on PartNet, where we achieve state-of-the-art results with significantly lower latency.

关键词： 3d computer vision Graph Neural Networks Neural Architecture Search

来源：评论

学校读者我要写书评

暂无评论

Optimizing Geometry Compression using Quantum Annealing

Optimizing Geometry Compression using Quantum Annealing

引用

IEEE Global Telecommunications Conference (GC Wkshps)

作者： Feld, Sebastian Friedrich, Markus Linnhoff-Popien, Claudia Ludwig Maximilians Univ Munchen Inst Comp Sci Munich Germany

ISBN: (纸本)9781538649206

The compression of geometry data is an important aspect of bandwidth-efficient data transfer for distributed 3d computer vision applications. We propose a quantum-enabled lossy 3d point cloud compression pipeline based on the constructive solid geometry (CSG) model representation. Key parts of the pipeline are mapped to NP-complete problems for which an efficient Ising formulation suitable for the execution on a Quantum Annealer exists. We describe existing Ising formulations for the maximum clique search problem and the smallest exact cover problem, both of which are important building blocks of the proposed compression pipeline. Additionally, we discuss the properties of the overall pipeline regarding result optimality and described Ising formulations.

关键词： optimized quantum applications 3d computer vision geometry processing constructive solid geometry

来源：评论

学校读者我要写书评

暂无评论

depth gradient image based on silhouette -: A solution for reconstruction of scenes in 3d environments

Depth gradient image based on silhouette -: A solution for r...

引用

3rd International Conference on Informatics in Control, Automation and Robotics

作者： Merchan, Pilar Adan, Antonio Salamanca, Santiago Univ Extremadura Escuela Engn Ind Avda Elvas S-N E-06071 Badajoz Spain Univ Castilla La Mancha Escuela Super Informat Ciudad Real 13071 Spain Univ Extremadura Escuela Ingn Ind Badajoz 06071 Spain

ISBN: (纸本)9728865600

Greatest difficulties arise in 3d environments when we have to deal with a scene with dissimilar objects without pose restrictions and where contacts and occlusions are allowed. This work tackles the problem of correspondence and alignment of surfaces in such a kind of scenes. The method presented in this paper is based on a new representation model called depth Gradient Image Based on Silhouette (dGI-BS) which synthesizes object surface information (through depth) and object shape information (through contour). Recognition and pose problems are efficiently solved for all objects of the scene by using a simple matching algorithm in the dGI-BS space. As a result of this the scene can be virtually reconstructed. This work is part of a robot intelligent manipulation project. The method has been successfully tested in real experimentation environments using range sensors.

关键词： 3d computer vision reconstruction 3d object recognition range image processing

来源：评论

学校读者我要写书评

暂无评论

6d Pose Estimation from Point Cloud Using an Improved Point Pair Features Method 7

6D Pose Estimation from Point Cloud Using an Improved Point ...

引用

7th International Conference on Control, Automation and Robotics (ICCAR)

作者： Wang, Haoyu Wang, Hesheng Zhuang, Chungang Shanghai Jiao Tong Univ Sch Mech Engn Shanghai Peoples R China

ISBN: (纸本)9781665449861

The Point Pair Features (PPF) method has been shown to be effective for pose estimation under clutter and occlusion. Our improved method mainly includes: (1) an approach for solving normal orientations of closed geometries based on Odd-even Rule;(2) an efficient downsampling approach by dividing a voxel grid into equivalent angle cells;(3) a verification step based on fitting points. The method is evaluated on real datasets of clutter and shows better performance as well as efficiency for 6d pose estimation compared to original PPF method.

关键词： pose estimation point pair features point cloud normal estimation 3d computer vision

来源：评论

学校读者我要写书评

暂无评论

Self-Annotated 3d Geometric Learning for Smeared Points Removal

Self-Annotated 3D Geometric Learning for Smeared Points Remo...

引用

IEEE/CVF Winter Conference on Applications of computer vision (WACV)

作者： Wang, Miaowei Morris, daniel Univ Edinburgh Edinburgh Midlothian Scotland Michigan State Univ E Lansing MI USA

ISBN: (纸本)9798350318920;9798350318937

There has been significant progress in improving the accuracy and quality of consumer-level dense depth sensors. Nevertheless, there remains a common depth pixel artifact which we call smeared points. These are points not on any 3d surface and typically occur as interpolations between foreground and background objects. As they cause fictitious surfaces, these points have the potential to harm applications dependent on the depth maps. Statistical outlier removal methods fare poorly in removing these points as they tend also to remove actual surface points. Trained network-based point removal faces difficulty in obtaining sufficient annotated data. To address this, we propose a fully self-annotated method to train a smeared point removal classifier. Our approach relies on gathering 3d geometric evidence from multiple perspectives to automatically detect and annotate smeared points and valid points. To validate the effectiveness of our method, we present a new benchmark dataset: the Real Azure-Kinect dataset. Experimental results and ablation studies show that our method outperforms traditional filters and other self-annotated methods. Our work is publicly available at https://***/wangmiaowei/wacv2024_***.

关键词： 3d computer vision Algorithms Algorithms Applications Image recognition and understanding Remote Sensing

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations

Task-Oriented Human-Object Interactions Generation with Impl...

引用

IEEE/CVF Winter Conference on Applications of computer vision (WACV)

作者： Li, Quanzhou Wang, Jingbo Loy, Chen Change dai, Bo Nanyang Technol Univ S Lab Singapore Singapore Shanghai AI Lab Shanghai Peoples R China

ISBN: (纸本)9798350318920;9798350318937

digital human motion synthesis is a vibrant research field with applications in movies, AR/VR, and video games. Whereas methods were proposed to generate natural and realistic human motions, most only focus on modeling humans and largely ignore object movements. Generating task-oriented human-object interaction motions in simulation is challenging. For different intents of using the objects, humans conduct various motions, which requires the human first to approach the objects and then make them move consistently with the human instead of staying still. Also, to deploy in downstream applications, the synthesized motions are desired to be flexible in length, providing options to personalize the predicted motions for various purposes. To this end, we propose TOHO: Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations, which generates full human-object interaction motions to conduct specific tasks, given only the task type, the object, and a starting human status. TOHO generates human-object motions in four steps: 1) it first estimates the object's final position given the task intent;2) it then generates keyframe poses grasping the objects;3) after that, it infills the keyframes and generates continuous motions;4) finally, it applies a compact closed-form object motion estimation to generate the object motion. Our method generates continuous motions that are parameterized only by the temporal coordinate, which allows for upsampling of the sequence to arbitrary frames and adjusting the motion speeds by designing the temporal coordinate vector. This work takes a step further toward general human-scene interaction simulation.

关键词： 3d 3d computer vision Algorithms Algorithms etc Generative models for image video

来源：评论

学校读者我要写书评

暂无评论

TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval

TriCoLo: Trimodal Contrastive Loss for Text to Shape Retriev...

引用

IEEE/CVF Winter Conference on Applications of computer vision (WACV)

作者： Ruan, Yue Lee, Han-Hung Zhang, Yiming Zhang, Ke Chang, Angel X. Simon Fraser Univ Burnaby BC Canada Alberta Machine Intelligence Inst Amii Edmonton AB Canada

ISBN: (纸本)9798350318920;9798350318937

Text-to-shape retrieval is an increasingly relevant problem with the growth of 3d shape data. Recent work on contrastive losses for learning joint embeddings over multimodal data [45] has been successful at tasks such as retrieval and classification. Thus far, work on joint representation learning for 3d shapes and text has focused on improving embeddings through modeling of complex attention between representations [53], or multi-task learning [25]. We propose a trimodal learning scheme over text, multi-view images and 3d shape voxels, and show that with large batch contrastive learning we achieve good performance on text-to-shape retrieval without complex attention mechanisms or losses. Our experiments serve as a foundation for follow-up work on building trimodal embeddings for text-image-shape.

关键词： 3d computer vision Algorithms Algorithms vision + language and/or other modalities

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25页 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：