2012 IEEE Conference on Computer Vision and Pattern Recognition最新文献

Unsupervised feature learning framework for no-reference image quality assessment 无参考图像质量评估的无监督特征学习框架

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247789

Peng Ye, J. Kumar, Le Kang, D. Doermann

{"title":"Unsupervised feature learning framework for no-reference image quality assessment","authors":"Peng Ye, J. Kumar, Le Kang, D. Doermann","doi":"10.1109/CVPR.2012.6247789","DOIUrl":"https://doi.org/10.1109/CVPR.2012.6247789","url":null,"abstract":"In this paper, we present an efficient general-purpose objective no-reference (NR) image quality assessment (IQA) framework based on unsupervised feature learning. The goal is to build a computational model to automatically predict human perceived image quality without a reference image and without knowing the distortion present in the image. Previous approaches for this problem typically rely on hand-crafted features which are carefully designed based on prior knowledge. In contrast, we use raw-image-patches extracted from a set of unlabeled images to learn a dictionary in an unsupervised manner. We use soft-assignment coding with max pooling to obtain effective image representations for quality estimation. The proposed algorithm is very computationally appealing, using raw image patches as local descriptors and using soft-assignment for encoding. Furthermore, unlike previous methods, our unsupervised feature learning strategy enables our method to adapt to different domains. CORNIA (Codebook Representation for No-Reference Image Assessment) is tested on LIVE database and shown to perform statistically better than the full-reference quality measure, structural similarity index (SSIM) and is shown to be comparable to state-of-the-art general purpose NR-IQA algorithms.","PeriodicalId":177454,"journal":{"name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","volume":"50 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":"115117935","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: 710

Hierarchical matching with side information for image classification 基于侧信息的图像分类层次匹配

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6248083

Qiang Chen, Zheng Song, Yang Hua, Zhongyang Huang, Shuicheng Yan

{"title":"Hierarchical matching with side information for image classification","authors":"Qiang Chen, Zheng Song, Yang Hua, Zhongyang Huang, Shuicheng Yan","doi":"10.1109/CVPR.2012.6248083","DOIUrl":"https://doi.org/10.1109/CVPR.2012.6248083","url":null,"abstract":"In this work, we introduce a hierarchical matching framework with so-called side information for image classification based on bag-of-words representation. Each image is expressed as a bag of orderless pairs, each of which includes a local feature vector encoded over a visual dictionary, and its corresponding side information from priors or contexts. The side information is used for hierarchical clustering of the encoded local features. Then a hierarchical matching kernel is derived as the weighted sum of the similarities over the encoded features pooled within clusters at different levels. Finally the new kernel is integrated with popular machine learning algorithms for classification purpose. This framework is quite general and flexible, other practical and powerful algorithms can be easily designed by using this framework as a template and utilizing particular side information for hierarchical clustering of the encoded local features. To tackle the latent spatial mismatch issues in SPM, we design in this work two exemplar algorithms based on two types of side information: object confidence map and visual saliency map, from object detection priors and within-image contexts respectively. The extensive experiments over the Caltech-UCSD Birds 200, Oxford Flowers 17 and 102, PASCAL VOC 2007, and PASCAL VOC 2010 databases show the state-of-the-art performances from these two exemplar algorithms.","PeriodicalId":177454,"journal":{"name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","volume":"27 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":"116900696","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: 97

Discriminative feature fusion for image classification 判别特征融合用于图像分类

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6248084

Basura Fernando, É. Fromont, Damien Muselet, M. Sebban

引用次数: 90

Image matching using local symmetry features 利用局部对称特征进行图像匹配

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247677

D. C. Hauagge, Noah Snavely

引用次数: 164

Intrinsic shape context descriptors for deformable shapes 可变形形状的内在形状上下文描述符

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247671

Iasonas Kokkinos, M. Bronstein, R. Litman, A. Bronstein

引用次数: 169

A learning-based framework for depth ordering 基于学习的深度排序框架

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247688

Zhaoyin Jia, Andrew C. Gallagher, Yao-Jen Chang, Tsuhan Chen

{"title":"A learning-based framework for depth ordering","authors":"Zhaoyin Jia, Andrew C. Gallagher, Yao-Jen Chang, Tsuhan Chen","doi":"10.1109/CVPR.2012.6247688","DOIUrl":"https://doi.org/10.1109/CVPR.2012.6247688","url":null,"abstract":"Depth ordering is instrumental for understanding the 3D geometry of an image. Humans are surprisingly good at depth ordering even with abstract 2D line drawings. In this paper we propose a learning-based framework for depth ordering inference. Boundary and junction characteristics are important clues for this task, and we have developed new features based on these attributes. Although each feature individually can produce reasonable depth ordering results, each still has limitations, and we can achieve better performance by combining them. In practice, local depth ordering inferences can be contradictory. Therefore, we propose a Markov Random Field model with terms that are more global than previous work, and use graph optimization to encourage a globally consistent ordering. In addition, to produce better object segmentation for the task of depth ordering, we propose to explicitly enforce closed loops and long edges for the occlusion boundary detection. We collect a new depth-order dataset for this problem, including more than a thousand human-labeled images with various daily objects and configurations. The proposed algorithm shows promising performance over conventional methods on both synthetic and real scenes.","PeriodicalId":177454,"journal":{"name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","volume":"8 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":"124860194","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: 33

A constrained latent variable model 约束潜变量模型

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247934

Aydin Varol, M. Salzmann, P. Fua, R. Urtasun

引用次数: 80

Actionable saliency detection: Independent motion detection without independent motion estimation 可操作的显著性检测:独立的运动检测，不需要独立的运动估计

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247732

Georgios Georgiadis, Alper Ayvaci, Stefano Soatto

引用次数: 11

Aligning images in the wild 在野外对齐图像

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247651

Wen-Yan Lin, Linlin Liu, Y. Matsushita, Kok-Lim Low, Siying Liu

引用次数: 38

A closed-form solution to uncalibrated photometric stereo via diffuse maxima 一个封闭形式的解决方案，以未经校准的光度立体通过漫射最大值

2012 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2012-06-16 DOI: 10.1109/CVPR.2012.6247754

P. Favaro, Thoma Papadhimitri

引用次数: 61