2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第2页

Salient object detection via bootstrap learning 基于自举学习的显著目标检测

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298798

Na Tong, Huchuan Lu, Xiang Ruan, Ming-Hsuan Yang

引用次数: 301

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition 基于子空间学习的半监督域自适应视觉识别

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298826

Ting Yao, Yingwei Pan, C. Ngo, Houqiang Li, Tao Mei

{"title":"Semi-supervised Domain Adaptation with Subspace Learning for visual recognition","authors":"Ting Yao, Yingwei Pan, C. Ngo, Houqiang Li, Tao Mei","doi":"10.1109/CVPR.2015.7298826","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7298826","url":null,"abstract":"In many real-world applications, we are often facing the problem of cross domain learning, i.e., to borrow the labeled data or transfer the already learnt knowledge from a source domain to a target domain. However, simply applying existing source data or knowledge may even hurt the performance, especially when the data distribution in the source and target domain is quite different, or there are very few labeled data available in the target domain. This paper proposes a novel domain adaptation framework, named Semi-supervised Domain Adaptation with Subspace Learning (SDASL), which jointly explores invariant low-dimensional structures across domains to correct data distribution mismatch and leverages available unlabeled target examples to exploit the underlying intrinsic information in the target domain. Specifically, SDASL conducts the learning by simultaneously minimizing the classification error, preserving the structure within and across domains, and restricting similarity defined on unlabeled target examples. Encouraging results are reported for two challenging domain transfer tasks (including image-to-image and image-to-video transfers) on several standard datasets in the context of both image object recognition and video concept detection.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116026900","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: 205

Object detection by labeling superpixels 标记超像素的目标检测

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299146

Junjie Yan, Yinan Yu, Xiangyu Zhu, Zhen Lei, S. Li

引用次数: 98

Intra-frame deblurring by leveraging inter-frame camera motion 利用帧间相机运动的帧内去模糊

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299030

Haichao Zhang, Jianchao Yang

引用次数: 32

R6P - Rolling shutter absolute pose problem R6P -卷帘门绝对姿势问题

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298842

Cenek Albl, Z. Kukelova, T. Pajdla

{"title":"R6P - Rolling shutter absolute pose problem","authors":"Cenek Albl, Z. Kukelova, T. Pajdla","doi":"10.1109/CVPR.2015.7298842","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7298842","url":null,"abstract":"We present a minimal, non-iterative solution to the absolute pose problem for images from rolling shutter cameras. Absolute pose problem is a key problem in computer vision and rolling shutter is present in a vast majority of today's digital cameras. We propose several rolling shutter camera models and verify their feasibility for a polynomial solver. A solution based on linearized camera model is chosen and verified in several experiments. We use a linear approximation to the camera orientation, which is meaningful only around the identity rotation. We show that the standard P3P algorithm is able to estimate camera orientation within 6 degrees for camera rotation velocity as high as 30deg/frame. Therefore we can use the standard P3P algorithm to estimate camera orientation and to bring the camera rotation matrix close to the identity. Using this solution, camera position, orientation, translational velocity and angular velocity can be computed using six 2D-to-3D correspondences, with orientation error under half a degree and relative position error under 2%. A significant improvement in terms of the number of inliers in RANSAC is demonstrated.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122314984","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: 27

Making better use of edges via perceptual grouping 通过感知分组更好地利用边缘

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298795

Yonggang Qi, Yi-Zhe Song, T. Xiang, Honggang Zhang, Timothy M. Hospedales, Yi Li, Jun Guo

引用次数: 86

The common self-polar triangle of concentric circles and its application to camera calibration 常见同心圆自极三角形及其在摄像机标定中的应用

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299033

H. Huang, Hui Zhang, Yiu-ming Cheung

{"title":"The common self-polar triangle of concentric circles and its application to camera calibration","authors":"H. Huang, Hui Zhang, Yiu-ming Cheung","doi":"10.1109/CVPR.2015.7299033","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7299033","url":null,"abstract":"In projective geometry, the common self-polar triangle has often been used to discuss the position relationship of two planar conics. However, there are few researches on the properties of the common self-polar triangle, especially when the two planar conics are special conics. In this paper, we explore the properties of the common self-polar triangle, when the two conics happen to be concentric circles. We show there exist infinite many common self-polar triangles of two concentric circles, and provide a method to locate the vertices of these triangles. By investigating all these triangles, we find that they encode two important properties. The first one is all triangles share one common vertex, and the opposite side of the common vertex lies on the same line, which are the circle center and the line at the infinity of the support plane. The second is all triangles are right triangles. Based on these two properties, the imaged circle center and the varnishing line of support plane can be recovered simultaneously, and many conjugate pairs on vanishing line can be obtained. These allow to induce good constraints on the image of absolute conic. We evaluate two calibration algorithms, whereby accurate results are achieved. The main contribution of this paper is that we initiate a new perspective to look into circle-based camera calibration problem. We believe that other calibration methods using different circle patterns can benefit from this perspective, especially for the patterns which involve more than two circles.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"320 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122786371","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: 39

First-person pose recognition using egocentric workspaces 使用以自我为中心的工作空间的第一人称姿势识别

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299061

Grégory Rogez, J. Supančič, Deva Ramanan

{"title":"First-person pose recognition using egocentric workspaces","authors":"Grégory Rogez, J. Supančič, Deva Ramanan","doi":"10.1109/CVPR.2015.7299061","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7299061","url":null,"abstract":"We tackle the problem of estimating the 3D pose of an individual's upper limbs (arms+hands) from a chest mounted depth-camera. Importantly, we consider pose estimation during everyday interactions with objects. Past work shows that strong pose+viewpoint priors and depth-based features are crucial for robust performance. In egocentric views, hands and arms are observable within a well defined volume in front of the camera. We call this volume an egocentric workspace. A notable property is that hand appearance correlates with workspace location. To exploit this correlation, we classify arm+hand configurations in a global egocentric coordinate frame, rather than a local scanning window. This greatly simplify the architecture and improves performance. We propose an efficient pipeline which 1) generates synthetic workspace exemplars for training using a virtual chest-mounted camera whose intrinsic parameters match our physical camera, 2) computes perspective-aware depth features on this entire volume and 3) recognizes discrete arm+hand pose classes through a sparse multi-class SVM. We achieve state-of-the-art hand pose recognition performance from egocentric RGB-D images in real-time.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122932301","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: 90

Reflection removal for in-vehicle black box videos 车载黑匣子视频的反射去除

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299051

C. Simon, I. Park

引用次数: 39

Real-time coarse-to-fine topologically preserving segmentation 实时的从粗到精的拓扑保持分割

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298913

Jian Yao, Marko Boben, S. Fidler, R. Urtasun

引用次数: 119