2013 IEEE Conference on Computer Vision and Pattern Recognition最新文献_第4页

Structure Preserving Object Tracking 保持结构的目标跟踪

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.240

Lu Zhang, L. Maaten

引用次数: 196

Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras 结构光RGB-D相机的层深度去噪和补全

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.157

Ju Shen, S. Cheung

{"title":"Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras","authors":"Ju Shen, S. Cheung","doi":"10.1109/CVPR.2013.157","DOIUrl":"https://doi.org/10.1109/CVPR.2013.157","url":null,"abstract":"The recent popularity of structured-light depth sensors has enabled many new applications from gesture-based user interface to 3D reconstructions. The quality of the depth measurements of these systems, however, is far from perfect. Some depth values can have significant errors, while others can be missing altogether. The uncertainty in depth measurements among these sensors can significantly degrade the performance of any subsequent vision processing. In this paper, we propose a novel probabilistic model to capture various types of uncertainties in the depth measurement process among structured-light systems. The key to our model is the use of depth layers to account for the differences between foreground objects and background scene, the missing depth value phenomenon, and the correlation between color and depth channels. The depth layer labeling is solved as a maximum a-posteriori estimation problem, and a Markov Random Field attuned to the uncertainty in measurements is used to spatially smooth the labeling process. Using the depth-layer labels, we propose a depth correction and completion algorithm that outperforms other techniques in the literature.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"1187-1194"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76838641","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: 139

Spatial Inference Machines 空间推理机

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.384

Roman Shapovalov, D. Vetrov, Pushmeet Kohli

引用次数: 41

Capturing Layers in Image Collections with Componential Models: From the Layered Epitome to the Componential Counting Grid 用组件模型捕获图像集合中的图层:从分层缩影到组件计数网格

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.71

A. Perina, N. Jojic

{"title":"Capturing Layers in Image Collections with Componential Models: From the Layered Epitome to the Componential Counting Grid","authors":"A. Perina, N. Jojic","doi":"10.1109/CVPR.2013.71","DOIUrl":"https://doi.org/10.1109/CVPR.2013.71","url":null,"abstract":"Recently, the Counting Grid (CG) model was developed to represent each input image as a point in a large grid of feature counts. This latent point is a corner of a window of grid points which are all uniformly combined to match the (normalized) feature counts in the image. Being a bag of word model with spatial layout in the latent space, the CG model has superior handling of field of view changes in comparison to other bag of word models, but with the price of being essentially a mixture, mapping each scene to a single window in the grid. In this paper we introduce a family of componential models, dubbed the Componential Counting Grid, whose members represent each input image by multiple latent locations, rather than just one. In this way, we make a substantially more flexible admixture model which captures layers or parts of images and maps them to separate windows in a Counting Grid. We tested the models on scene and place classification where their componential nature helped to extract objects, to capture parallax effects, thus better fitting the data and outperforming Counting Grids and Latent Dirichlet Allocation, especially on sequences taken with wearable cameras.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"72 8 1","pages":"500-507"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78055576","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: 2

Deep Learning Shape Priors for Object Segmentation 用于对象分割的深度学习形状先验

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.244

Fei Chen, Huimin Yu, Roland Hu, Xunxun Zeng

引用次数: 81

Unsupervised Joint Object Discovery and Segmentation in Internet Images 互联网图像中的无监督联合目标发现与分割

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.253

Michael Rubinstein, Armand Joulin, J. Kopf, Ce Liu

{"title":"Unsupervised Joint Object Discovery and Segmentation in Internet Images","authors":"Michael Rubinstein, Armand Joulin, J. Kopf, Ce Liu","doi":"10.1109/CVPR.2013.253","DOIUrl":"https://doi.org/10.1109/CVPR.2013.253","url":null,"abstract":"We present a new unsupervised algorithm to discover and segment out common objects from large and diverse image collections. In contrast to previous co-segmentation methods, our algorithm performs well even in the presence of significant amounts of noise images (images not containing a common object), as typical for datasets collected from Internet search. The key insight to our algorithm is that common object patterns should be salient within each image, while being sparse with respect to smooth transformations across other images. We propose to use dense correspondences between images to capture the sparsity and visual variability of the common object over the entire database, which enables us to ignore noise objects that may be salient within their own images but do not commonly occur in others. We performed extensive numerical evaluation on established co-segmentation datasets, as well as several new datasets generated using Internet search. Our approach is able to effectively segment out the common object for diverse object categories, while naturally identifying images where the common object is not present.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"69 1","pages":"1939-1946"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76064512","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: 370

Online Dominant and Anomalous Behavior Detection in Videos 视频中的在线支配和异常行为检测

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.337

M. J. Roshtkhari, M. Levine

{"title":"Online Dominant and Anomalous Behavior Detection in Videos","authors":"M. J. Roshtkhari, M. Levine","doi":"10.1109/CVPR.2013.337","DOIUrl":"https://doi.org/10.1109/CVPR.2013.337","url":null,"abstract":"We present a novel approach for video parsing and simultaneous online learning of dominant and anomalous behaviors in surveillance videos. Dominant behaviors are those occurring frequently in videos and hence, usually do not attract much attention. They can be characterized by different complexities in space and time, ranging from a scene background to human activities. In contrast, an anomalous behavior is defined as having a low likelihood of occurrence. We do not employ any models of the entities in the scene in order to detect these two kinds of behaviors. In this paper, video events are learnt at each pixel without supervision using densely constructed spatio-temporal video volumes. Furthermore, the volumes are organized into large contextual graphs. These compositions are employed to construct a hierarchical codebook model for the dominant behaviors. By decomposing spatio-temporal contextual information into unique spatial and temporal contexts, the proposed framework learns the models of the dominant spatial and temporal events. Thus, it is ultimately capable of simultaneously modeling high-level behaviors as well as low-level spatial, temporal and spatio-temporal pixel level changes.","PeriodicalId":6343,"journal":{"name":"2013 IEEE Conference on Computer Vision and Pattern Recognition","volume":"488 1","pages":"2611-2618"},"PeriodicalIF":0.0,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76108053","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: 168

Expanded Parts Model for Human Attribute and Action Recognition in Still Images 静态图像中人体属性和动作识别的扩展部件模型

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.90

Gaurav Sharma, F. Jurie, C. Schmid

引用次数: 104

A New Model and Simple Algorithms for Multi-label Mumford-Shah Problems 多标签Mumford-Shah问题的一个新模型和简单算法

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.161

Byung-Woo Hong, Zhaojin Lu, G. Sundaramoorthi

引用次数: 7

Exemplar-Based Face Parsing 基于范例的人脸解析

2013 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2013-06-23 DOI: 10.1109/CVPR.2013.447

Brandon M. Smith, Li Zhang, Jonathan Brandt, Zhe L. Lin, Jianchao Yang

引用次数: 141