检索结果-内蒙古大学图书馆

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Bendale, Abhijit Boult, Terrance Univ Colorado Colorado Springs CO 80907 USA

ISBN: (纸本)9781479943098

Increasing access to large, non-stationary face datasets and corresponding demands to process, analyze and learn from this data. this has lead to a new class of online/incremental face recognition problems. While it is advantageous to build large scale learning systems when resources permit, a counter problem of learning with limited resources in presence of streaming data arises. We present a budgeted incremental support vector learning method suitable for online learning applications. Our system can process one sample at a time and is suitable when dealing with large streams of data. We discuss multiple budget maintenance strategies and investigate the problem of incremental unlearning. We propose a novel posterior probability estimation model based on Extreme Value theory (EVT) and show its suitability for budgeted online learning applications (calibration with limited data). We perform thorough analysis of various probability calibration techniques with the help of methods inspired from meteorology. We test our methods on Labeled Faces in the Wild dataset and show suitability of the proposed approach for face verification/recognition

关键词： SVM face recognition incremental learning probability calibration

来源：评论

学校读者我要写书评

暂无评论

Grassmann Averages for Scalable Robust PCA 27

Grassmann Averages for Scalable Robust PCA

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Hauberg, Soren Feragen, Aasa Black, Michael J. DTU Compute Lyngby Denmark DIKU Copenhagen Denmark MPIs Tubingen Tubingen Germany MPI Intelligent Syst Tubingen Germany MPI Intelligent Syst Perceiving Syst Dept Tubingen Germany Univ Copenhagen DIKU DK-1168 Copenhagen Denmark MPI Intelligent Syst Machine Learning & Computat Biol Grp Tubingen Germany MPI Dev Biol Tubingen Germany

ISBN: (纸本)9781479951178

As the collection of large datasets becomes increasingly automated, the occurrence of outliers will increase - "big data" implies "big outliers". While principal component analysis (PCA) is often used to reduce the size of data, and scalable solutions exist, it is well-known that outliers can arbitrarily corrupt the results. Unfortunately, state-of-the-art approaches for robust PCA do not scale beyond small-to-medium sized datasets. To address this, we introduce the Grassmann Average (GA), which expresses dimensionality reduction as an average of the subspaces spanned by the data. Because averages can be efficiently computed, we immediately gain scalability. GA is inherently more robust than PCA, but we show that they coincide for Gaussian data. We exploit that averages can be made robust to formulate the Robust Grassmann Average (RGA) as a form of robust PCA. Robustness can be with respect to vectors (subspaces) or elements of vectors;we focus on the latter and use a trimmed average. the resulting Trimmed Grassmann Average (TGA) is particularly appropriate for computer vision because it is robust to pixel outliers. the algorithm has low computational complexity and minimal memory requirements, making it scalable to "big noisy data." We demonstrate TGA for background modeling, video restoration, and shadow removal. We show scalability by performing robust PCA on the entire Star Wars IV movie.

关键词： Grassmann manifold PCA Robust PCA computer vision directional statistics machine learning subspace estimation

来源：评论

学校读者我要写书评

暂无评论

Recognizing RGB Images by Learning from RGB-D Data 27

Recognizing RGB Images by Learning from RGB-D Data

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Chen, Lin Li, Wen Xu, Dong Agcy Sci Technol & Res Inst Infocomm Res Singapore Singapore Nanyang Technol Univ Sch Comp Engn Singapore Singapore

ISBN: (纸本)9781479951178

In this work, we propose a new framework for recognizing RGB images captured by the conventional cameras by leveraging a set of labeled RGB-D data, in which the depth features can be additionally extracted from the depth images. We formulate this task as a new unsupervised domain adaptation (UDA) problem, in which we aim to take advantage of the additional depth features in the source domain and also cope with the data distribution mismatch between the source and target domains. To effectively utilize the additional depth features, we seek two optimal projection matrices to map the samples from both domains into a common space by preserving as much as possible the correlations between the visual features and depth features. To effectively employ the training samples from the source domain for learning the target classifier, we reduce the data distribution mismatch by minimizing the Maximum Mean Discrepancy (MMD) criterion, which compares the data distributions for each type of feature in the common space. Based on the above two motivations, we propose a new SVM based objective function to simultaneously learn the two projection matrices and the optimal target classifier in order to well separate the source samples from different classes when using each type of feature in the common space. An efficient alternating optimization algorithm is developed to solve our new objective function. Comprehensive experiments for object recognition and gender recognition demonstrate the effectiveness of our proposed approach for recognizing RGB images by learning from RGB-D data.

关键词： RGB-D domain adaptation gender recognition object recognition transfer learning object recognition Transfer (Psychology) data distribution red-green-blue colour model images Objective function Learning

来源：评论

学校读者我要写书评

暂无评论

Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models 27

Seeing 3D chairs: exemplar part-based 2D-3D alignment using ...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Aubry, Mathieu Maturana, Daniel Efros, Alexei A. Russell, Bryan C. Sivic, Josef INRIA Paris France Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Calif Berkeley Berkeley CA USA Intel Labs Cambridge England

ISBN: (纸本)9781479951178

this paper poses object category detection in images as a type of 2D-to-3D alignment problem, utilizing the large quantities of 3D CAD models that have been made publicly available online. Using the "chair" class as a running example, we propose an exemplar-based 3D category representation, which can explicitly model chairs of different styles as well as the large variation in viewpoint. We develop an approach to establish part-based correspondences between 3D CAD models and real photographs. this is achieved by (i) representing each 3D model using a set of view-dependent mid-level visual elements learned from synthesized views in a discriminative fashion, (ii) carefully calibrating the individual element detectors on a common dataset of negative images, and (iii) matching visual elements to the test image allowing for small mutual deformations but preserving the viewpoint and style constraints. We demonstrate the ability of our system to align 3D models with 2D objects in the challenging PASCAL VOC images, which depict a wide variety of chairs in complex scenes.

关键词： 3D CAD models alignment category representation mid-level visual elements recognition seat Alignment three Dimensions recognition (Psychology) three-dimensional displays computer-Aided Design DFFB gene images Comment test sample Dataset

来源：评论

学校读者我要写书评

暂无评论

Fast and Robust Perspective Rectification of Document Images on a Smartphone

Fast and Robust Perspective Rectification of Document Images...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Williem Simon, Christian Cho, Sungdae Park, In Kyu Inha Univ Dept Informat & Commun Engn Inchon 402751 South Korea Samsung Elect Co Ltd Div Mobile Commun Suwon 443742 South Korea

ISBN: (纸本)9781479943098

this paper presents a perspective rectification framework for mobile device that is fast and robust to recovering the fronto-parallel view of perspectively distorted document images. the conventional approaches is too heavy to be implemented on a mobile device. In addition, they fails to reject the false case of the perspective rectification. To ameliorate such problems, the proposed framework is designed to pursue a fast and robust algorithm to detect horizontal and vertical vanishing points efficiently and robustly. then, perspective rectification is performed using both horizontal and vertical vanishing points. In addition, the proposed framework has an adaptive scheme to detect the false case of the perspective rectification and skip the procedure without using the vertical vanishing point. Note that, the proposed framework is designed for consumer application so that bad results are rejected before they are shown for users. We demonstrate the performance of the proposed framework on various challenging examples to confirm that the proposed system is fast and robust in rectifying the perspectively distorted images.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Action and Interaction recognition in First-person videos

Action and Interaction Recognition in First-person videos

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Narayan, Sanath Kankanhalli, Mohan S. Ramakrishnan, Kalpathi R. IISc Dept Elect Engg Bangalore Karnataka India NUS Sch Comp Singapore Singapore

ISBN: (纸本)9781479943098

In this work, we evaluate the performance of the popular dense trajectories approach on first-person action recognition datasets. A person moving around with a wearable camera will actively interact with humans and objects and also passively observe others interacting. Hence, in order to represent real-world scenarios, the dataset must contain actions from first-person perspective as well as thirdperson perspective. For this purpose, we introduce a new dataset which contains actions from both the perspectives captured using a head-mounted camera. We employ a motion pyramidal structure for grouping the dense trajectory features. the relative strengths of motion along the trajectories are used to compute different bag-of-words descriptors and concatenated to form a single descriptor for the action. the motion pyramidal approach performs better than the baseline improved trajectory descriptors. the method achieves 96.7% on the JPL interaction dataset and 61.8% on our NUS interaction dataset. the same is used to detect actions in long video sequences and achieves average precision of 0.79 on JPL interaction dataset.

关键词： First-person video Interaction recognition

来源：评论

学校读者我要写书评

暂无评论

recognition of Complex Events: Exploiting Temporal Dynamics between Underlying Concepts 27

Recognition of Complex Events: Exploiting Temporal Dynamics ...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Bhattacharya, Subhabrata Kalaych, Mahdi M. Sukthankar, Rahul Shah, Mubarak Columbia Univ New York NY 10027 USA Univ Cent Florida Orlando FL 32816 USA Google Res Mountain View CA USA

ISBN: (纸本)9781479951178

While approaches based on bags of features excel at low-level action classification, they are ill-suited for recognizing complex events in video, where concept-based temporal representations currently dominate. this paper proposes a novel representation that captures the temporal dynamics of windowed mid-level concept detectors in order to improve complex event recognition. We first express each video as an ordered vector time series, where each time step consists of the vector formed from the concatenated confidences of the pre-trained concept detectors. We hypothesize that the dynamics of time series for different instances from the same event class, as captured by simple linear dynamical system (LDS) models, are likely to be similar even if the instances differ in terms of low-level visual features. We propose a two-part representation composed of fusing: (1) a singular value decomposition of block Hankel matrices (SSID-S) and (2) a harmonic signature (H-S) computed from the corresponding eigen-dynamics matrix. the proposed method offers several benefits over alternate approaches: our approach is straightforward to implement, directly employs existing concept detectors and can be plugged into linear classification frameworks. Results on standard datasets such as NIST's TRECVID Multimedia Event Detection task demonstrate the improved accuracy of the proposed method.

关键词： Complex Event recognition Hankel Matrices Harmonic signatures Linear Dynamical Systems Subspace state identification TRECVID MED Temporal Representation Hankel matrices DYNAMICAL SYSTEMS recognition (Psychology) Videotapes detector Time series dynamics

来源：评论

学校读者我要写书评

暂无评论

A Global Hypothesis Verification Framework for 3D Object recognition in Clutter

引用

ieee TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2016年第7期38卷 1383-1396页

作者： Aldoma, Aitor Tombari, Federico Di Stefano, Luigi Vincze, Markus Vienna Univ Technol Grp ACIN Vision4Robot A-1060 Vienna Austria Univ Bologna CVLAB Grp DISI Bologna Italy

Pipelines to recognize 3D objects despite clutter and occlusions usually end up with a final verification stage whereby recognition hypotheses are validated or dismissed based on how well they explain sensor measurements. Unlike previous work, we propose a Global Hypothesis Verification (GHV) approach which regards all hypotheses jointly so as to account for mutual interactions. GHV provides a principled framework to tackle the complexity of our visual world by leveraging on a plurality of recognition paradigms and cues. Accordingly, we present a 3D object recognition pipeline deploying both global and local 3D features as well as shape and color. thereby, and facilitated by the robustness of the verification process, diverse object hypotheses can be gathered and weak hypotheses need not be suppressed too early to trade sensitivity for specificity. Experiments demonstrate the effectiveness of our proposal, which significantly improves over the state-of-art and attains ideal performance (no false negatives, no false positives) on three out of the six most relevant and challenging benchmark datasets.

关键词： 3D object recognition hypothesis verification correspondence grouping scene understanding

来源：评论

学校读者我要写书评

暂无评论

Towards autonomous navigation of miniature UAV

Towards autonomous navigation of miniature UAV

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Brockers, Roland Humenberger, Martin Weiss, Stephan Matthies, Larry Jet Prop Lab Pasadena CA 91109 USA Austrian Inst Technol Vienna Austria

ISBN: (纸本)9781479943098

Micro air vehicles such as miniature rotorcrafts require high-precision and fast localization updates for their control, but cannot carry large payloads. therefore, only small and light-weight sensors and processing units can be deployed on such platforms, favoring vision-based solutions that use light weight cameras and run on small embedded computing platforms. In this paper, we propose a navigation framework to provide a small quadrotor UAV with accurate state estimation for high speed control including 6DoF pose and sensor self-calibration. Our method allows very fast deployment without prior calibration procedures literally rendering the vehicle a throw-and-go platform. Additionally, we demonstrate hazard-avoiding autonomous landing to showcase a high-level navigation capability that relies on the low-level pose estimation results and is executed on the same embedded platform. We explain our hardware-specific implementation on a 12g processing unit and show real-world end-to-end results.

关键词： Micro Air Vehicle autonomous landing autonomous navigation embedded computing vision based state estimation

来源：评论

学校读者我要写书评

暂无评论

Experiments on an RGB-D Wearable vision System for Egocentric Activity recognition

Experiments on an RGB-D Wearable Vision System for Egocentri...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Moghimi, Mohammad Azagra, Pablo Montesano, Luis Murillo, Ana C. Belongie, Serge Univ Calif San Diego La Jolla CA 92093 USA Univ Zaragoza DIIS I3A Zaragoza Spain Cornell Tech New York NY USA

ISBN: (纸本)9781479943098

this work describes and explores novel steps towards activity recognition from an egocentric point of view. Activity recognition is a broadly studied topic in computer vision, but the unique characteristics of wearable vision systems present new challenges and opportunities. We evaluate a challenging new publicly available dataset that includes trajectories of different users across two indoor environments performing a set of more than 20 different activities. the visual features studied include compact and global image descriptors, including GIST and a novel skin segmentation based histogram signature, and state-of-the art image representations for recognition, including Bag of SIFT words and Convolutional Neural Network (CNN) based features. Our experiments show that simple and compact features provide reasonable accuracy to obtain basic activity information (in our case, manipulation vs. non-manipulation). However, for finer grained categories CNN-based features provide the most promising results. Future steps include integration of depth information with these features and temporal consistency into the pipeline.

关键词： computer vision

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：