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61-70 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：

MULTISCALE REPRESENTATIONS LEARNING TRANSFORMER FRAMEWORK FOR POINT CLOUd CLASSIFICATION 30

MULTISCALE REPRESENTATIONS LEARNING TRANSFORMER FRAMEWORK FO...

引用

30th IEEE International Conference on Image Processing (ICIP)

作者： Sun, Yajie Zia, Ali Zhou, Jun Griffith Univ Sch Informat & Commun Technol Brisbane Qld Australia CSIRO Agr & Food Northam WA Australia Australian Natl Univ Coll Sci Canberra ACT Australia

ISBN: (纸本)9781728198354

Extracting and aggregating multiple feature representations from various scales have become the key to point cloud classification tasks. vision Transformer (ViT) is a representative solution along this line, but it lacks the capability to model detailed multi-scale features and their interactions. In addition, learning efficient and effective representation from the point cloud is challenging due to its irregular, unordered, and sparse nature. To tackle these problems, we propose a novel multi-scale representation learning transformer framework, employing various geometric features beyond common Cartesian coordinates. Our approach enriches the description of point clouds by local geometric relationships and group them at multiple scales. This scale information is aggregated and then new patches can be extracted to minimize feature overlay. The bottleneck projection head is then adopted to enhance the information and feed all patches to the multi-head attention to capture the deep dependencies among representations across patches. Evaluation on public benchmark datasets shows the competitive performance of our framework on point cloud classification.

关键词： Point cloud classification multi-scale features geometric features multi-scale transformer 3d computer vision

来源：评论

学校读者我要写书评

暂无评论

HdMNet: A Hierarchical Matching Network with double Attention for Large-scale Outdoor LidAR Point Cloud Registration

HDMNet: A Hierarchical Matching Network with Double Attentio...

引用

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

作者： Xue, Weiyi Lu, Fan Chen, Guang Tongji Univ Shanghai Peoples R China

ISBN: (纸本)9798350318920;9798350318937

Outdoor LidAR point clouds are typically large-scale and complexly distributed. To achieve efficient and accurate registration, emphasizing the similarity among local regions and prioritizing global local-to-local matching is of utmost importance, subsequent to which accuracy can be enhanced through cost-effective fine registration. In this paper, a novel hierarchical neural network with double attention named HdMNet is proposed for large-scale outdoor LidAR point cloud registration. Specifically, A novel feature consistency enhanced double-soft matching network is introduced to achieve two-stage matching with high flexibility while enlarging the receptive field with high efficiency in a patch-to-patch manner, which significantly improves the registration performance. Moreover, in order to further utilize the sparse matching information from deeper layer, we develop a novel trainable embedding mask to incorporate the confidence scores of correspondences obtained from pose estimation of deeper layer, eliminating additional computations. The high-confidence keypoints in the sparser point cloud of the deeper layer correspond to a high-confidence spatial neighborhood region in shallower layer, which will receive more attention, while the features of non-key regions will be masked. Extensive experiments are conducted on two large-scale outdoor LidAR point cloud datasets to demonstrate the high accuracy and efficiency of the proposed HdMNet.

关键词： 3d computer vision Algorithms

来源：评论

学校读者我要写书评

暂无评论

Intrinsic Hand Avatar: Illumination-aware Hand Appearance and Shape Reconstruction from Monocular RGB Video

Intrinsic Hand Avatar: Illumination-aware Hand Appearance an...

引用

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

作者： Kalshetti, Pratik Chaudhuri, Parag Indian Inst Technol Mumbai India

ISBN: (纸本)9798350318920;9798350318937

Reconstructing a user-specific hand avatar is essential for a personalized experience in augmented and virtual reality systems. Current state-of-the-art avatar reconstruction methods use implicit representations to capture detailed geometry and appearance combined with neural rendering. However, these methods rely on a complicated multi-view setup, do not explicitly handle environment lighting leading to baked-in illumination and self-shadows, and require long hours for training. We present a method to reconstruct a hand avatar from a monocular RGB video of a user's hand in arbitrary hand poses captured under real-world environment lighting. Specifically, our method jointly optimizes shape, appearance, and lighting parameters using a realistic shading model in a differentiable rendering framework incorporating Monte Carlo path tracing. despite relying on physically-based rendering, our method can complete the reconstruction within minutes. In contrast to existing work, our method disentangles intrinsic properties of the underlying appearance and environment lighting, leading to realistic self-shadows. We compare our method with state-of-the-art hand avatar reconstruction methods and observe that it outperforms them on all commonly used metrics. We also evaluate our method on our captured dataset to emphasize its generalization capability. Finally, we demonstrate applications of our intrinsic hand avatar on novel pose synthesis and relighting. We plan to release our code to aid further research.

关键词： 3d computer vision Algorithms Algorithms Biometrics body pose face gesture

来源：评论

学校读者我要写书评

暂无评论

3d Interest Point detection via discriminative Learning

3D Interest Point Detection via Discriminative Learning

引用

13th European Conference on computer vision (ECCV)

作者： Teran, Leizer Mordohai, Philippos Drexel Univ Philadelphia PA 19104 USA Stevens Inst Technol Hoboken NJ USA

ISBN: (纸本)9783319105901;9783319105895

The task of detecting the interest points in 3d meshes has typically been handled by geometric methods. These methods, while designed according to human preference, can be ill-equipped for handling the variety and subjectivity in human responses. different tasks have different requirements for interest point detection;some tasks may necessitate high precision while other tasks may require high recall. Sometimes points with high curvature may be desirable, while in other cases high curvature may be an indication of noise. Geometric methods lack the required flexibility to adapt to such changes. As a consequence, interest point detection seems to be well suited for machine learning methods that can be trained to match the criteria applied on the annotated training data. In this paper, we formulate interest point detection as a supervised binary classification problem using a random forest as our classifier. We validate the accuracy of our method and compare our results to those of five state of the art methods on a new, standard benchmark.

关键词： 3d computer vision

来源：评论

学校读者我要写书评

暂无评论

AvatarOne: Monocular 3d Human Animation

AvatarOne: Monocular 3D Human Animation

引用

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

作者： Karthikeyan, Akash Ren, Robert Kant, Yash Gilitschenski, Igor Univ Toronto Toronto ON Canada Vector Inst AI Toronto ON Canada

ISBN: (纸本)9798350318920;9798350318937

Reconstructing realistic human avatars from monocular videos is a challenge that demands intricate modeling of 3d surface and articulation. In this paper, we introduce a comprehensive approach that synergizes three pivotal components: (1) a Signed distance Field (SdF) representation with volume rendering and grid-based ray sampling to prune empty raysets, enabling efficient 3d reconstruction;(2) faster 3d surface reconstruction through a warmup stage for human surfaces, which ensures detailed modeling of body limbs;and (3) temporally consistent subjectspecific forward canonical skinning, which helps in retaining correspondences across frames, all of which can be trained in an end-to-end fashion under 15 minutes. Leveraging warmup and grid-based ray marching, along with a faster voxel-based correspondence search, our model streamlines the computational demands of the problem. We further experiment with different sampling representations to improve ray radiance approximations and obtain a floater free surface. Through rigorous evaluation, we demonstrate that our method is on par with current techniques while offering novel insights and avenues for future research in 3d avatar modeling. This work showcases a fast and robust solution for both surface modeling and novel-view animation. Project website: https://***/projects/avatarone

关键词： 3d 3d computer vision Algorithms Algorithms Algorithms Biometrics body pose etc face Generative models for image gesture video

来源：评论

学校读者我要写书评

暂无评论

Volumetric disentanglement for 3d Scene Manipulation

Volumetric Disentanglement for 3D Scene Manipulation

引用

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

作者： Benaim, Sagie Warburg, Frederik Christensen, Peter Ebert Belongie, Serge Univ Copenhagen Copenhagen Denmark Tech Univ Denmark Lyngby Denmark

ISBN: (纸本)9798350318920;9798350318937

Recently, advances in differential volumetric rendering enabled significant breakthroughs in the photo-realistic and fine-detailed reconstruction of complex 3d scenes, which is key for many virtual reality applications. However, in the context of augmented reality, one may also wish to effect semantic manipulations or augmentations of objects within a scene. To this end, we propose a volumetric framework for (i) disentangling or separating, the volumetric representation of a given foreground object from the background, and (ii) semantically manipulating the foreground object, as well as the background. Our framework takes as input a set of 2d masks specifying the desired foreground object for training views, together with the associated 2d views and poses, and produces a foreground-background disentanglement that respects the surrounding illumination, reflections, and partial occlusions, which can be applied to both training and novel views. Our method enables the separate control of pixel color and depth as well as 3d similarity transformations of both the foreground and background objects. We subsequently demonstrate our framework's applicability on several downstream manipulation tasks, going beyond the placement and movement of foreground objects. These tasks include object camouflage, non-negative 3d object inpainting, 3d object translation, 3d object inpainting, and 3d text-based object manipulation. The project webpage is provided in https://***/volumetric-disentanglement/.

关键词： 3d computer vision Algorithms Applications Virtual / augmented reality

来源：评论

学校读者我要写书评

暂无评论

ScanEnts3d: Exploiting Phrase-to-3d-Object Correspondences for Improved Visio-Linguistic Models in 3d Scenes

ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences f...

引用

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

作者： Abdelreheem, Ahmed Olszewski, Kyle Lee, Hsin-Ying Wonka, Peter Achlioptas, Panos King Abdullah Univ Sci & Technol KAUST Thuwal Saudi Arabia Snap Inc Santa Monica CA 90405 USA

ISBN: (纸本)9798350318920;9798350318937

The two popular datasets ScanRefer [20] and ReferIt3d [5] connect natural language to real-world 3d scenes. In this paper, we curate a complementary dataset extending both the aforementioned ones. We associate all objects mentioned in a referential sentence with their underlying instances inside a 3d scene. In contrast, previous work did this only for a single object per sentence. Our Scan Entities in 3d (ScanEnts3d) dataset provides explicit correspondences between 369k objects across 84k referential sentences, covering 705 real-world scenes. We propose novel architecture modifications and losses that enable learning from this new type of data and improve the performance for both neural listening and language generation. For neural listening, we improve the SoTA in both the Nr3d and ScanRefer benchmarks by 4.3% and 5.0%, respectively. For language generation, we improve the SoTA by 13.2 CIdEr points on the Nr3d benchmark. For both of these tasks, the new type of data is only used to improve training, but no additional annotations are required at inference time. Our introduced dataset is available on the project's webpage at https://***/.

关键词： 3d computer vision Algorithms Algorithms datasets and evaluations

来源：评论

学校读者我要写书评

暂无评论

Object Re-Identification from Point Clouds

Object Re-Identification from Point Clouds

引用

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

作者： Therien, Benjamin Huang, Chengjie Chow, Adrian Czarnecki, Krzysztof Univ Waterloo Waterloo ON Canada

ISBN: (纸本)9798350318920;9798350318937

Object re-identification (ReId) from images plays a critical role in application domains of image retrieval (surveillance, retail analytics, etc.) and multi-object tracking (autonomous driving, robotics, etc.). However, systems that additionally or exclusively perceive the world from depth sensors are becoming more commonplace without any corresponding methods for object ReId. In this work, we fill the gap by providing the first large-scale study of object ReId from point clouds and establishing its performance relative to image ReId. To enable such a study, we create two large-scale ReId datasets with paired image and LidAR observations and propose a lightweight matching head that can be concatenated to any set or sequence processing backbone (e.g., PointNet or ViT), creating a family of comparable object ReId networks for both modalities. Run in Siamese style, our proposed point cloud ReId networks can make thousands of pairwise comparisons in real-time (10 Hz). Our findings demonstrate that their performance increases with higher sensor resolution and approaches that of image ReId when observations are sufficiently dense. Our strongest network trained at the largest scale achieves ReId accuracy exceeding 90% for rigid objects and 85% for deformable objects (without any explicit skeleton normalization). To our knowledge, we are the first to study object re-identification from real point cloud observations. Our code is available at https://***/bentherien/point-cloud-reid.

关键词： 3d computer vision Algorithms Algorithms Applications Robotics Video recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

UNSPAT: Uncertainty-Guided SpatioTemporal Transformer for 3d Human Pose and Shape Estimation on Videos

UNSPAT: Uncertainty-Guided SpatioTemporal Transformer for 3D...

引用

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

作者： Lee, Minsoo Lee, Hyunmin Kim, Bumsoo Kim, Seunghwan LG AI Res Seoul South Korea

ISBN: (纸本)9798350318920;9798350318937

We propose an efficient framework for 3d human pose and shape estimation from a video, named Uncertainty-Guided SpatioTemporal Transformer (UNSPAT). Unlike previous video-based methods that consider temporal relationships with global average pooled features, our approach incorporates both spatial and temporal dimensions without compromising spatial information. We address the excessive complexity of spatiotemporal attention through two modules: Spatial Alignment Module (SAM) and Space2Batch. The modules align input features and compute temporal attention at every spatial position in a batch-wise manner. Furthermore, our uncertainty-guided attention re-weighting module improves performance by diminishing the impact of artifacts. We demonstrate the effectiveness of the UNSPAT on widely used benchmark datasets and achieve state-of-the-art performance. Our method is robust to challenging scenes, such as occlusion, and cluttered backgrounds, showing its potential for real-world applications.

关键词： 3d computer vision Algorithms Algorithms Biometrics body pose face gesture

来源：评论

学校读者我要写书评

暂无评论

Ray deformation Networks for Novel View Synthesis of Refractive Objects

Ray Deformation Networks for Novel View Synthesis of Refract...

引用

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

作者： deng, Weijian Campbell, dylan Sun, Chunyi Kanitkar, Shubham Shaffer, Matthew Gould, Stephen Australian Natl Univ Canberra ACT Australia Rios Intelligent Machines Menlo Pk CA USA

ISBN: (纸本)9798350318920;9798350318937

Neural Radiance Fields (NeRF) have demonstrated exceptional capabilities in creating photorealistic novel views using volume rendering on a radiance field. However, the intrinsic assumption of straight light rays within NeRF becomes a limitation when dealing with transparent or translucent objects that exhibit refraction, and therefore have curved light paths. This hampers the ability of these approaches to accurately model the appearance of refractive objects, resulting in suboptimal novel view synthesis and geometry estimates. To address this issue, we propose an innovative solution using deformable networks to learn a tailored deformation field for refractive objects. Our approach predicts position and direction offsets, allowing NeRF to model the curved light paths caused by refraction and therefore the complex and highly view-dependent appearances of refractive objects. We also introduce a regularization strategy that encourages piece-wise linear light paths, since most physical systems can be approximated with a piece-wise constant index of refraction. By seamlessly integrating our deformation networks into the NeRF framework, our method significantly improves rendering refractive objects from novel views.

关键词： 3d computer vision Algorithms Algorithms Computational photography image and video synthesis

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 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：