2013 IEEE Conference on Computer Vision and Pattern Recognition最新文献_第3页

Learning without Human Scores for Blind Image Quality Assessment 无人工学习盲图像质量评估

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.133

Wufeng Xue, Lei Zhang, X. Mou

{"title":"Learning without Human Scores for Blind Image Quality Assessment","authors":"Wufeng Xue, Lei Zhang, X. Mou","doi":"10.1109/CVPR.2013.133","DOIUrl":"https://doi.org/10.1109/CVPR.2013.133","url":null,"abstract":"General purpose blind image quality assessment (BIQA) has been recently attracting significant attention in the fields of image processing, vision and machine learning. State-of-the-art BIQA methods usually learn to evaluate the image quality by regression from human subjective scores of the training samples. However, these methods need a large number of human scored images for training, and lack an explicit explanation of how the image quality is affected by image local features. An interesting question is then: can we learn for effective BIQA without using human scored images? This paper makes a good effort to answer this question. We partition the distorted images into overlapped patches, and use a percentile pooling strategy to estimate the local quality of each patch. Then a quality-aware clustering (QAC) method is proposed to learn a set of centroids on each quality level. These centroids are then used as a codebook to infer the quality of each patch in a given image, and subsequently a perceptual quality score of the whole image can be obtained. The proposed QAC based BIQA method is simple yet effective. It not only has comparable accuracy to those methods using human scored images in learning, but also has merits such as high linearity to human perception of image quality, real-time implementation and availability of image local quality map.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"41 4 1","pages":"995-1002"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82851025","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: 353

Structured Face Hallucination 结构化面部幻觉

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.146

Chih-Yuan Yang, Sifei Liu, Ming-Hsuan Yang

引用次数: 134

A Statistical Model for Recreational Trails in Aerial Images 航拍影像中休闲步道的统计模型

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.50

Andrew Predoehl, S. Morris, Kobus Barnard

引用次数: 4

A Max-Margin Riffled Independence Model for Image Tag Ranking 图像标签排序的最大边界riffle独立模型

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.399

Tian Lan, Greg Mori

引用次数: 17

Detecting Pulse from Head Motions in Video 视频中头部运动脉冲检测

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.440

Guha Balakrishnan, F. Durand, J. Guttag

引用次数: 508

Spectral Modeling and Relighting of Reflective-Fluorescent Scenes 反射-荧光场景的光谱建模和重照明

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.191

Antony Lam, Imari Sato

引用次数: 24

Bayesian Depth-from-Defocus with Shading Constraints 具有阴影约束的贝叶斯离焦深度

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.35

Chen Li, Shuochen Su, Yasuyuki Matsushita, Kun Zhou, Stephen Lin

引用次数: 1

Block and Group Regularized Sparse Modeling for Dictionary Learning 面向字典学习的块和组正则化稀疏建模

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.55

Yu-Tseh Chi, Mohsen Ali, Ajit Rajwade, J. Ho

引用次数: 48

Graph Matching with Anchor Nodes: A Learning Approach 锚节点图匹配:一种学习方法

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.374

Nan Hu, R. Rustamov, L. Guibas

引用次数: 30

Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines β -伯努利过程受限玻尔兹曼机的弱监督中级特征学习

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.68

Roni Mittelman, Honglak Lee, B. Kuipers, S. Savarese

{"title":"Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines","authors":"Roni Mittelman, Honglak Lee, B. Kuipers, S. Savarese","doi":"10.1109/CVPR.2013.68","DOIUrl":"https://doi.org/10.1109/CVPR.2013.68","url":null,"abstract":"The use of semantic attributes in computer vision problems has been gaining increased popularity in recent years. Attributes provide an intermediate feature representation in between low-level features and the class categories, and offer several attractive properties, among which are improved learning of novel categories based on few examples, as well as allowing for zero-shot learning. However, the major caveat is that learning semantic attributes is a laborious task, requiring a significant amount of time and human intervention to provide labels. In order to address this issue, we propose a weakly supervised approach to learn mid-level features, where the only supervision is provided by the category classes of the training examples. We develop a novel extension of the restricted Boltzmann machine (RBM) with Beta-Bernoulli process priors. Unlike the standard RBM, our model uses the class labels to promote more efficient sharing of information by different categories. This tends to improve the generalization performance. By using semantic attributes for which annotations are available, we show that we can find correspondences between the mid-level features that we learn and the labeled attributes. Therefore, the mid-level features have distinct semantic characterization which is very similar to that given by the semantic attributes, even though their labeling was not used during the training process. Our experimental results in object recognition tasks show significant performance gains, outperforming methods which rely on manually labeled semantic attributes.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"66 1","pages":"476-483"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89920705","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: 32