检索结果-内蒙古大学图书馆

International Conference on 3D Imaging, modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Shivanand Venkanna Sheshappanavar Tejas Anvekar Shivanand Kundargi Yufan Wang Chandra Kambhamettu Dept. of Computer and Information Sciences Video/Image Modeling and Synthesis (VIMS) Lab University of Delaware Newark DE USA

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Fine-grained grocery object recognition is an important computer vision problem with broad applications in automatic checkout, in-store robotic navigation, and assistive technologies for the visually impaired. Existing datasets on groceries are mainly 2D images. Models trained on these datasets are limited to learning features from the regular 2D grids. While portable 3D sensors such as Kinect were commonly available for mobile phones, sensors such as LiDAR and TrueDepth, have recently been integrated into mobile phones. Despite the availability of mobile 3D sensors, there are currently no dedicated real-world large-scale benchmark 3D datasets for grocery. In addition, existing 3D datasets lack fine-grained grocery categories and have limited training samples. Furthermore, collecting data by going around the object versus the traditional photo capture makes data collection cumbersome. Thus, we introduce a large-scale grocery dataset called 3DGrocery100. It constitutes 100 classes, with a total of 87,898 3D point clouds created from 10,755 RGB-D single-view images. We benchmark our dataset on six recent stateof-the-art 3D point cloud classification models. Additionally, we also benchmark the dataset on few-shot and continual learning point cloud classification tasks. Project Page: https://***/3DGrocery100/.

关键词： Point cloud compression Training Solid modeling Three-dimensional displays Benchmark testing Robot sensing systems Mobile handsets

来源：评论

学校读者我要写书评

暂无评论

3DSAINT Representation for 3D Point Clouds

3DSAINT Representation for 3D Point Clouds

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Chandra Kambhamettu Video/Image Modeling and Synthesis (VIMS) Lab. Computer and Information Sciences University of Delaware Newark Delaware

This paper introduces a Sphere-based representation to model a 3D scene and show its performance on various tasks, including Structure from Motion (SfM) and 3D scene classification. A significant target application of this work is Mixed Reality, where 3D data can be efficiently represented, and synthetic and real data can be mixed for an immersive experience. Over the past few decades, 3D big data has garnered increased attention in computer vision. Acquiring, representing, reconstructing, querying, classifying, and visualizing 3D models for Mixed Reality has become crucial for many applications, such as medicine, architecture, entertainment, and bioinformatics. With the ever-increasing amount of data that the 3D scanners produce, storing, processing, and transmitting the data becomes challenging. Techniques that exploit the shape information need to be developed to model, classify and visualize the data. Our work offers a novel multi-scale surface representation based on spheres, with the ultimate goal of helping scientists to see and work with 3D data in Mixed Reality more effectively and efficiently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Margins for Instance Reweighting in Adversarial Training

arXiv

引用

arXiv 2021年

作者： Wang, Qizhou Liu, Feng Han, Bo Liu, Tongliang Gong, Chen Niu, Gang Zhou, Mingyuan Sugiyama, Masashi Department of Computer Science Hong Kong Baptist University Hong Kong DeSI Lab Australian Artificial Intelligence Institute University of Technology Sydney Australia TML Lab School of Computer Science Faculty of Engineering The University of Sydney Australia PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of MoE Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China McCombs School of Business The University of Texas at Austin United States Graduate School of Frontier Sciences The University of Tokyo Japan

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However, existing methods measuring the closeness are not very reliable: they are discrete and can take only a few values, and they are path-dependent, i.e., they may change given the same start and end points with different attack paths. In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighting adversarial data. Specifically, a PM is defined as the difference between two estimated class-posterior probabilities, e.g., such a probability of the true label minus the probability of the most confusing label given some natural data. Though different PMs capture different geometric properties, all three PMs share a negative correlation with the vulnerability of data: data with larger/smaller PMs are safer/riskier and should have smaller/larger weights. Experiments demonstrated that PMs are reliable and PM-based reweighting methods outperformed state-of-the-art counterparts. Copyright © 2021, The Authors. All rights reserved.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

Probabilistic margins for instance reweighting in adversarial training 21

Probabilistic margins for instance reweighting in adversaria...

引用

Proceedings of the 35th International Conference on Neural information Processing Systems

作者： Qizhou Wang Feng Liu Bo Han Tongliang Liu Chen Gong Gang Niu Mingyuan Zhou Masashi Sugiyama Department of Computer Science Hong Kong Baptist University DeSI Lab Australian Artificial Intelligence Institute University of Technology Sydney TML Lab School of Computer Science Faculty of Engineering The University of Sydney PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of MoE and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology RIKEN Center for Advanced Intelligence Project (AIP) McCombs School of Business The University of Texas at Austin RIKEN Center for Advanced Intelligence Project (AIP) and Graduate School of Frontier Sciences The University of Tokyo

ISBN: (纸本)9781713845393

关键词：

来源：评论

学校读者我要写书评

暂无评论

REFRACTIVE STEREO RAY TRACING FOR RECONSTRUCTING UNDERWATER STRUCTURES

REFRACTIVE STEREO RAY TRACING FOR RECONSTRUCTING UNDERWATER ...

引用

IEEE International Conference on image Processing

作者： Scott Sorensen Abhishek Kolagunda Philip Saponaro Chandra Kambhamettu Video/Image Modeling and Synthesis (VIMS) Lab Computer and Information Sciences University of Delaware

ISBN: (纸本)9781479983407

Underwater objects behind a refractive surface pose problems for traditional 3D reconstruction techniques. Scenes where underwater objects are visible from the surface are commonplace, however the refraction of light causes 3D points in these scenes to project non-linearly. Refractive Stereo Ray Tracing allows for accurate reconstruction by modeling the refraction of light. Our approach uses techniques from ray tracing to compute the 3D position of points behind a refractive surface. This technique aims to reconstruct underwater structures in situations where access to the water is dangerous or cost prohibitive. Experimental results in real and synthetic scenes show this technique effectively handles refraction.

关键词： Underwater Stereo Vision Refraction Underwater refractions Stereoviews REFRACTION Light refraction Ray tracing Underwater structures Solar Terrestrial Relations Observatory

来源：评论

学校读者我要写书评

暂无评论

Dog breed classification via landmarks

Dog breed classification via landmarks

引用

作者： Wang, Xiaolong Ly, Vincent Sorensen, Scott Kambhamettu, Chandra Video/Image Modeling and Synthesis Laboratory Department of Computer and Information Sciences University of Delaware NewarkDE United States

ISBN: (纸本)9781479957514

Object recognition is an important problem with a wide range of applications. It is also a challenging problem, especially for animal categorization as the differences among breeds can be subtle. In this paper, based on statistical techniques for landmark-based shape representation, we propose to model the shape of dog breed as points on the Grassmann manifold. We consider the dog breed categorization as the classification problem on this manifold. The proposed scheme is tested on a dataset including 8,351 images of 133 different breeds. Experimental results demonstrate the advocated scheme outperforms state of the art approaches by nearly 20%. © 2014 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Knowing where I am: Exploiting multi-task learning for multi-view indoor image-based localization 25

Knowing where I am: Exploiting multi-task learning for multi...

引用

25th British Machine Vision Conference, BMVC 2014

作者： Lu, Guoyu Yan, Yan Sebe, Nicu Kambhamettu, Chandra Video/Image Modeling and Synthesis Lab University of Delaware United States Department of Information Engineering and Computer Science University of Trento Italy

Indoor localization has attracted a large amount of applications in mobile and robotics area, especially in vast and sophisticated environments. Most indoor localization methods are based on cellular base stations and WiFi signals. Such methods require users to carry additional equipment. Localization accuracy is largely based on the beacon distribution. image-based localization is mainly applied for outdoor environments to overcome the problem caused by weak GPS signals in large building areas. In this paper, we propose to localize images in indoor environments from multi-view settings. We use Structure-from-Motion to reconstruct the 3D environment of our indoor buildings to provide users a clear view of the whole building's indoor structure. Since the orientation information is also quite essential for indoor navigation, images are localized based on a multi-task learning method, which treats each view direction classification as a task. We perform image retrieval based on the trained multi-task classifiers. Thus the orientation of the image together with the location information is achieved. We assign the pose of the retrieved image to the query image calculated from SfM reconstruction with the use of bundle adjustment to refine the pose estimation. © 2014. The copyright of this document resides with its authors.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

Can faces verify blood-relations?

Can faces verify blood-relations?

引用

IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS)

作者： Gowri Somanath Chandra Kambhamettu Video/Image Modeling and Synthesis (VIMS) Laboratory Department of Computer and Information Sciences University of Delaware Newark DE USA

Humans can verify unknown parent-offspring and sibling pairs over unrelated subject pairs. A computational scheme to accomplish the task robustly, in the presence of challenges due to gender and age gap between related-pairs, finds many applications such as matching orphaned/lost children, identifying relatives from a photo collection. We propose one of the first computational schemes to verify sibling pairs along with parent-child relation. Towards the same, we present a novel ensemble metric learning scheme that combines the advantages of task-specific learning, adaptive prototype and feature selection and `late fusion'. We demonstrate the robustness of the scheme on a very large scale, real-world dataset. Specifically, we show that the gender difference among related-pairs leads to lower performance of traditional verification and metric learning algorithms. Through various experiments, we quantitatively study the robustness of the proposed scheme in the general and specific case of different gender related-pairs, achieving up to 80%, 75% accuracy for the parent-child and siblings relations respectively.

关键词： Kernel Measurement Training Testing Robustness Support vector machines Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

VADANA: A dense dataset for facial image analysis

VADANA: A dense dataset for facial image analysis

引用

International Conference on computer Vision Workshops (ICCV Workshops)

作者： Gowri Somanath MV Rohith Chandra Kambhamettu Video/Image Modeling and Synthesis Lab University of Delaware USA Video/Image Modeling and Synthesis Lab Department of Computer and Information Sciences University of Delaware USA

Analysis of face images has been the topic of in-depth research with wide spread applications. Face recognition, verification, age progression studies are some of the topics under study. In order to facilitate comparison and benchmarking of different approaches, various datasets have been released. For the specific topics of face verification with age progression, aging pattern extraction and age estimation, only two public datasets are currently available. The FGNET and MORPH datasets contain a large number of subjects, but only a few images are available for each subject. We present a new dataset, VADANA, which complements them by providing a large number of high quality digital images for each subject within and across ages (depth vs. breadth). It provides the largest number of intrapersonal pairs, essential for better training and testing. The images also offer a natural range of pose, expression and illumination variation. A parallel version with aligned faces is also created. Additionally, we provide relationships between subjects. We demonstrate the difference and difficulty of VADANA by testing with state-of-the-art algorithms. Our findings from experiments show how VADANA can aid further research on different types of verification algorithms. The variety of characteristics our data offers facilitate testing and benchmarking of other facial analysis algorithms.

关键词： Face Training Lighting Databases Algorithm design and analysis Testing Aging

来源：评论

学校读者我要写书评

暂无评论

Towards estimation of dense disparities from stereo images containing large textureless regions

Towards estimation of dense disparities from stereo images c...

引用

International Conference on Pattern Recognition

作者： M.V. Rohith Gowri Somanath Chandra Kambhamettu Cathleen Geiger Dept. of Computer and Information Sciences Video/Image Modeling and Synthesis(VIMS) Lab Department. of Geography University of Delaware USA

Stereo algorithms for structure reconstruction demand accurate disparities with low mismatch errors and false positives. Mismatch errors in large textureless regions force most accurate algorithms to be sparse, with disparities known only in textured regions. We propose a novel method which uses characteristics of the multi-valued disparity to segregate image regions into unambiguous, occluded but textured and regions with low color variation. The disparity in the unambiguous region is calculated using stable matching with local disparity filtering. The disparity is interpolated into other regions by diffusion using unstructured triangulation and method of finite elements for rapid convergence. The boundary conditions for each of the region are appropriately modified so that accurate discontinuities in the disparity are preserved. A comparison of our method with some existing methods through experiments reveal that this algorithm indeed performs significantly better in producing dense accurate disparities.

关键词： image reconstruction Stereo image processing Interpolation image matching computer errors Matched filters Filtering Geography Finite element methods Convergence

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：