2012 IEEE Conference on Computer Vision and Pattern Recognition最新文献_第10页

Refractive height fields from single and multiple images 单幅和多幅图像的折射高度场

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247687

Qi Shan, Sameer Agarwal, B. Curless

引用次数: 25

Robust camera self-calibration from monocular images of Manhattan worlds 从曼哈顿世界的单目图像稳健的相机自校准

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6248008

H. Wildenauer, A. Hanbury

引用次数: 95

Improved facial expression recognition via uni-hyperplane classification 通过单超平面分类改进面部表情识别

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247973

Sien W. Chew, S. Lucey, P. Lucey, S. Sridharan, Jeff F. Conn

引用次数: 55

Robust non-rigid registration of 2D and 3D graphs 二维和三维图形的鲁棒非刚性配准

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247776

Eduard Serradell, Przemyslaw Glowacki, J. Kybic, F. Moreno-Noguer, P. Fua

引用次数: 24

Modulation transfer function of patch-based stereo systems 基于patch的立体系统的调制传递函数

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247825

Ronny Klowsky, Arjan Kuijper, M. Goesele

{"title":"Modulation transfer function of patch-based stereo systems","authors":"Ronny Klowsky, Arjan Kuijper, M. Goesele","doi":"10.1109/CVPR.2012.6247825","DOIUrl":"https://doi.org/10.1109/CVPR.2012.6247825","url":null,"abstract":"A widely used technique to recover a 3D surface from photographs is patch-based (multi-view) stereo reconstruction. Current methods are able to reproduce fine surface details, they are however limited by the sampling density and the patch size used for reconstruction. We show that there is a systematic error in the reconstruction depending on the details in the unknown surface (frequencies) and the reconstruction resolution. For this purpose we present a theoretical analysis of patch-based depth reconstruction. We prove that our model of the reconstruction process yields a linear system, allowing us to apply the transfer (or system) function concept. We derive the modulation transfer function theoretically and validate it experimentally on synthetic examples using rendered images as well as on photographs of a 3D test target. Our analysis proves that there is a significant but predictable amplitude loss in reconstructions of fine scale details. In a first experiment on real-world data we show how this can be compensated for within the limits of noise and reconstruction accuracy by an inverse transfer function in frequency space.","PeriodicalId":177454,"journal":{"name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121958994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

Cats and dogs 猫和狗

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6248092

Omkar M. Parkhi, A. Vedaldi, Andrew Zisserman, C. V. Jawahar

{"title":"Cats and dogs","authors":"Omkar M. Parkhi, A. Vedaldi, Andrew Zisserman, C. V. Jawahar","doi":"10.1109/CVPR.2012.6248092","DOIUrl":"https://doi.org/10.1109/CVPR.2012.6248092","url":null,"abstract":"We investigate the fine grained object categorization problem of determining the breed of animal from an image. To this end we introduce a new annotated dataset of pets covering 37 different breeds of cats and dogs. The visual problem is very challenging as these animals, particularly cats, are very deformable and there can be quite subtle differences between the breeds. We make a number of contributions: first, we introduce a model to classify a pet breed automatically from an image. The model combines shape, captured by a deformable part model detecting the pet face, and appearance, captured by a bag-of-words model that describes the pet fur. Fitting the model involves automatically segmenting the animal in the image. Second, we compare two classification approaches: a hierarchical one, in which a pet is first assigned to the cat or dog family and then to a breed, and a flat one, in which the breed is obtained directly. We also investigate a number of animal and image orientated spatial layouts. These models are very good: they beat all previously published results on the challenging ASIRRA test (cat vs dog discrimination). When applied to the task of discriminating the 37 different breeds of pets, the models obtain an average accuracy of about 59%, a very encouraging result considering the difficulty of the problem.","PeriodicalId":177454,"journal":{"name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","volume":"41 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121002518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1239

Seeing double without confusion: Structure-from-motion in highly ambiguous scenes 清晰地看到双重效果:高度模糊场景中的动态结构

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247834

Nianjuan Jiang, P. Tan, L. Cheong

引用次数: 58

Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach 利用网络图像进行消费者视频中的事件识别:一种多源域自适应方法

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247819

Lixin Duan, Dong Xu, Shih-Fu Chang

{"title":"Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach","authors":"Lixin Duan, Dong Xu, Shih-Fu Chang","doi":"10.1109/CVPR.2012.6247819","DOIUrl":"https://doi.org/10.1109/CVPR.2012.6247819","url":null,"abstract":"Recent work has demonstrated the effectiveness of domain adaptation methods for computer vision applications. In this work, we propose a new multiple source domain adaptation method called Domain Selection Machine (DSM) for event recognition in consumer videos by leveraging a large number of loosely labeled web images from different sources (e.g., Flickr.com and Photosig.com), in which there are no labeled consumer videos. Specifically, we first train a set of SVM classifiers (referred to as source classifiers) by using the SIFT features of web images from different source domains. We propose a new parametric target decision function to effectively integrate the static SIFT features from web images/video keyframes and the spacetime (ST) features from consumer videos. In order to select the most relevant source domains, we further introduce a new data-dependent regularizer into the objective of Support Vector Regression (SVR) using the ϵ-insensitive loss, which enforces the target classifier shares similar decision values on the unlabeled consumer videos with the selected source classifiers. Moreover, we develop an alternating optimization algorithm to iteratively solve the target decision function and a domain selection vector which indicates the most relevant source domains. Extensive experiments on three real-world datasets demonstrate the effectiveness of our proposed method DSM over the state-of-the-art by a performance gain up to 46.41%.","PeriodicalId":177454,"journal":{"name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126842081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 204

A two-stage approach to blind spatially-varying motion deblurring 一种两阶段的盲空间变化运动去模糊方法

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247660

Hui Ji, Kang Wang

引用次数: 73

Tracking the articulated motion of two strongly interacting hands 追踪两只强烈相互作用的手的关节运动

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247885

I. Oikonomidis, Nikolaos Kyriazis, Antonis A. Argyros

引用次数: 278