2011 International Conference on Computer Vision最新文献_第8页

The medial feature detector: Stable regions from image boundaries 中间特征检测器:来自图像边界的稳定区域

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126436

Yannis Avrithis, Konstantinos Rapantzikos

引用次数: 25

Graph mode-based contextual kernels for robust SVM tracking 基于图模型的上下文核鲁棒支持向量机跟踪

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126364

Xi Li, A. Dick, Hanzi Wang, Chunhua Shen, A. Hengel

{"title":"Graph mode-based contextual kernels for robust SVM tracking","authors":"Xi Li, A. Dick, Hanzi Wang, Chunhua Shen, A. Hengel","doi":"10.1109/ICCV.2011.6126364","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126364","url":null,"abstract":"Visual tracking has been typically solved as a binary classification problem. Most existing trackers only consider the pairwise interactions between samples, and thereby ignore the higher-order contextual interactions, which may lead to the sensitivity to complicated factors such as noises, outliers, background clutters and so on. In this paper, we propose a visual tracker based on support vector machines (SVMs), for which a novel graph mode-based contextual kernel is designed to effectively capture the higher-order contextual information from samples. To do so, we first create a visual graph whose similarity matrix is determined by a baseline visual kernel. Second, a set of high-order contexts are discovered in the visual graph. The problem of discovering these high-order contexts is solved by seeking modes of the visual graph. Each graph mode corresponds to a vertex community termed as a high-order context. Third, we construct a contextual kernel that effectively captures the interaction information between the high-order contexts. Finally, this contextual kernel is embedded into SVMs for robust tracking. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"26 1","pages":"1156-1163"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89128675","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: 42

Multiclass transfer learning from unconstrained priors 基于无约束先验的多类迁移学习

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126454

Jie Luo, T. Tommasi, B. Caputo

{"title":"Multiclass transfer learning from unconstrained priors","authors":"Jie Luo, T. Tommasi, B. Caputo","doi":"10.1109/ICCV.2011.6126454","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126454","url":null,"abstract":"The vast majority of transfer learning methods proposed in the visual recognition domain over the last years addresses the problem of object category detection, assuming a strong control over the priors from which transfer is done. This is a strict condition, as it concretely limits the use of this type of approach in several settings: for instance, it does not allow in general to use off-the-shelf models as priors. Moreover, the lack of a multiclass formulation for most of the existing transfer learning algorithms prevents using them for object categorization problems, where their use might be beneficial, especially when the number of categories grows and it becomes harder to get enough annotated data for training standard learning methods. This paper presents a multiclass transfer learning algorithm that allows to take advantage of priors built over different features and with different learning methods than the one used for learning the new task. We use the priors as experts, and transfer their outputs to the new incoming samples as additional information. We cast the learning problem within the Multi Kernel Learning framework. The resulting formulation solves efficiently a joint optimization problem that determines from where and how much to transfer, with a principled multiclass formulation. Extensive experiments illustrate the value of this approach.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"1 1","pages":"1863-1870"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89473765","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: 111

Dense one-shot 3D reconstruction by detecting continuous regions with parallel line projection 利用平行线投影检测连续区域的密集单镜头三维重建

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126460

R. Sagawa, Hiroshi Kawasaki, S. Kiyota, Furukawa Ryo

{"title":"Dense one-shot 3D reconstruction by detecting continuous regions with parallel line projection","authors":"R. Sagawa, Hiroshi Kawasaki, S. Kiyota, Furukawa Ryo","doi":"10.1109/ICCV.2011.6126460","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126460","url":null,"abstract":"3D scanning of moving objects has many applications, for example, marker-less motion capture, analysis on fluid dynamics, object explosion and so on. One of the approach to acquire accurate shape is a projector-camera system, especially the methods that reconstructs a shape by using a single image with static pattern is suitable for capturing fast moving object. In this paper, we propose a method that uses a grid pattern consisting of sets of parallel lines. The pattern is spatially encoded by a periodic color pattern. While informations are sparse in the camera image, the proposed method extracts the dense (pixel-wise) phase informations from the sparse pattern. As the result, continuous regions in the camera images can be extracted by analyzing the phase. Since there remain one DOF for each region, we propose the linear solution to eliminate the DOF by using geometric informations of the devices, i.e. epipolar constraint. In addition, solution space is finite because projected pattern consists of parallel lines with same intervals, the linear equation can be efficiently solved by integer least square method. In this paper, the formulations for both single and multiple projectors are presented. We evaluated the accuracy of correspondences and showed the comparison with respect to the number of projectors by simulation. Finally, the dense 3D reconstruction of moving objects are presented in the experiments.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"76 1","pages":"1911-1918"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89678538","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: 52

Discovering object instances from scenes of Daily Living 从日常生活场景中发现对象实例

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126314

Hongwen Kang, M. Hebert, T. Kanade

引用次数: 61

Are spatial and global constraints really necessary for segmentation? 空间和全局约束对于分割真的是必要的吗?

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126219

Aurélien Lucchi, Yunpeng Li, X. Boix, Kevin Smith, P. Fua

{"title":"Are spatial and global constraints really necessary for segmentation?","authors":"Aurélien Lucchi, Yunpeng Li, X. Boix, Kevin Smith, P. Fua","doi":"10.1109/ICCV.2011.6126219","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126219","url":null,"abstract":"Many state-of-the-art segmentation algorithms rely on Markov or Conditional Random Field models designed to enforce spatial and global consistency constraints. This is often accomplished by introducing additional latent variables to the model, which can greatly increase its complexity. As a result, estimating the model parameters or computing the best maximum a posteriori (MAP) assignment becomes a computationally expensive task. In a series of experiments on the PASCAL and the MSRC datasets, we were unable to find evidence of a significant performance increase attributed to the introduction of such constraints. On the contrary, we found that similar levels of performance can be achieved using a much simpler design that essentially ignores these constraints. This more simple approach makes use of the same local and global features to leverage evidence from the image, but instead directly biases the preferences of individual pixels. While our investigation does not prove that spatial and consistency constraints are not useful in principle, it points to the conclusion that they should be validated in a larger context.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"47 1","pages":"9-16"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89839707","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: 72

Building a better probabilistic model of images by factorization 用因子分解法建立更好的图像概率模型

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126473

B. J. Culpepper, Jascha Narain Sohl-Dickstein, B. Olshausen

引用次数: 14

Image based detection of geometric changes in urban environments 基于图像的城市环境几何变化检测

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126515

Aparna Taneja, Luca Ballan, M. Pollefeys

引用次数: 89

Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance 小鸟:使用体积原语和姿势标准化外观进行从属分类

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126238

Ryan Farrell, Om Oza, Ning Zhang, Vlad I. Morariu, Trevor Darrell, L. Davis

{"title":"Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance","authors":"Ryan Farrell, Om Oza, Ning Zhang, Vlad I. Morariu, Trevor Darrell, L. Davis","doi":"10.1109/ICCV.2011.6126238","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126238","url":null,"abstract":"Subordinate-level categorization typically rests on establishing salient distinctions between part-level characteristics of objects, in contrast to basic-level categorization, where the presence or absence of parts is determinative. We develop an approach for subordinate categorization in vision, focusing on an avian domain due to the fine-grained structure of the category taxonomy for this domain. We explore a pose-normalized appearance model based on a volumetric poselet scheme. The variation in shape and appearance properties of these parts across a taxonomy provides the cues needed for subordinate categorization. Training pose detectors requires a relatively large amount of training data per category when done from scratch; using a subordinate-level approach, we exploit a pose classifier trained at the basic-level, and extract part appearance and shape information to build subordinate-level models. Our model associates the underlying image pattern parameters used for detection with corresponding volumetric part location, scale and orientation parameters. These parameters implicitly define a mapping from the image pixels into a pose-normalized appearance space, removing view and pose dependencies, facilitating fine-grained categorization from relatively few training examples.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"21 1","pages":"161-168"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78492824","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: 217

Distributed cosegmentation via submodular optimization on anisotropic diffusion 基于各向异性扩散的次模优化分布共分割

2011 International Conference on Computer Vision Pub Date : 2011-11-06 DOI: 10.1109/ICCV.2011.6126239

Gunhee Kim, E. Xing, Li Fei-Fei, T. Kanade

{"title":"Distributed cosegmentation via submodular optimization on anisotropic diffusion","authors":"Gunhee Kim, E. Xing, Li Fei-Fei, T. Kanade","doi":"10.1109/ICCV.2011.6126239","DOIUrl":"https://doi.org/10.1109/ICCV.2011.6126239","url":null,"abstract":"The saliency of regions or objects in an image can be significantly boosted if they recur in multiple images. Leveraging this idea, cosegmentation jointly segments common regions from multiple images. In this paper, we propose CoSand, a distributed cosegmentation approach for a highly variable large-scale image collection. The segmentation task is modeled by temperature maximization on anisotropic heat diffusion, of which the temperature maximization with finite K heat sources corresponds to a K-way segmentation that maximizes the segmentation confidence of every pixel in an image. We show that our method takes advantage of a strong theoretic property in that the temperature under linear anisotropic diffusion is a submodular function; therefore, a greedy algorithm guarantees at least a constant factor approximation to the optimal solution for temperature maximization. Our theoretic result is successfully applied to scalable cosegmentation as well as diversity ranking and single-image segmentation. We evaluate CoSand on MSRC and ImageNet datasets, and show its competence both in competitive performance over previous work, and in much superior scalability.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":"16 1","pages":"169-176"},"PeriodicalIF":0.0,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81399288","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: 311