发布求助
文献互助 智能选刊 最新文献

2015 IEEE International Conference on Computer Vision (ICCV)最新文献

筛选
英文 中文
The HCI Stereo Metrics: Geometry-Aware Performance Analysis of Stereo Algorithms HCI立体度量:立体算法的几何感知性能分析
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.245
Katrin Honauer, L. Maier-Hein, D. Kondermann
{"title":"The HCI Stereo Metrics: Geometry-Aware Performance Analysis of Stereo Algorithms","authors":"Katrin Honauer, L. Maier-Hein, D. Kondermann","doi":"10.1109/ICCV.2015.245","DOIUrl":"https://doi.org/10.1109/ICCV.2015.245","url":null,"abstract":"Performance characterization of stereo methods is mandatory to decide which algorithm is useful for which application. Prevalent benchmarks mainly use the root mean squared error (RMS) with respect to ground truth disparity maps to quantify algorithm performance. We show that the RMS is of limited expressiveness for algorithm selection and introduce the HCI Stereo Metrics. These metrics assess stereo results by harnessing three semantic cues: depth discontinuities, planar surfaces, and fine geometric structures. For each cue, we extract the relevant set of pixels from existing ground truth. We then apply our evaluation functions to quantify characteristics such as edge fattening and surface smoothness. We demonstrate that our approach supports practitioners in selecting the most suitable algorithm for their application. Using the new Middlebury dataset, we show that rankings based on our metrics reveal specific algorithm strengths and weaknesses which are not quantified by existing metrics. We finally show how stacked bar charts and radar charts visually support multidimensional performance evaluation. An interactive stereo benchmark based on the proposed metrics and visualizations is available at: http://hci.iwr.uni-heidelberg.de/stereometrics.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"30 1","pages":"2120-2128"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81434092","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: 21
Motion Trajectory Segmentation via Minimum Cost Multicuts 基于最小成本多路分割的运动轨迹分割
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.374
M. Keuper, Bjoern Andres, T. Brox
{"title":"Motion Trajectory Segmentation via Minimum Cost Multicuts","authors":"M. Keuper, Bjoern Andres, T. Brox","doi":"10.1109/ICCV.2015.374","DOIUrl":"https://doi.org/10.1109/ICCV.2015.374","url":null,"abstract":"For the segmentation of moving objects in videos, the analysis of long-term point trajectories has been very popular recently. In this paper, we formulate the segmentation of a video sequence based on point trajectories as a minimum cost multicut problem. Unlike the commonly used spectral clustering formulation, the minimum cost multicut formulation gives natural rise to optimize not only for a cluster assignment but also for the number of clusters while allowing for varying cluster sizes. In this setup, we provide a method to create a long-term point trajectory graph with attractive and repulsive binary terms and outperform state-of-the-art methods based on spectral clustering on the FBMS-59 dataset and on the motion subtask of the VSB100 dataset.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"16 1","pages":"3271-3279"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82680178","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: 188
Where to Buy It: Matching Street Clothing Photos in Online Shops 哪里可以买到:网上商店的街头服装照片
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.382
M. Kiapour, Xufeng Han, S. Lazebnik, A. Berg, Tamara L. Berg
{"title":"Where to Buy It: Matching Street Clothing Photos in Online Shops","authors":"M. Kiapour, Xufeng Han, S. Lazebnik, A. Berg, Tamara L. Berg","doi":"10.1109/ICCV.2015.382","DOIUrl":"https://doi.org/10.1109/ICCV.2015.382","url":null,"abstract":"In this paper, we define a new task, Exact Street to Shop, where our goal is to match a real-world example of a garment item to the same item in an online shop. This is an extremely challenging task due to visual differences between street photos (pictures of people wearing clothing in everyday uncontrolled settings) and online shop photos (pictures of clothing items on people, mannequins, or in isolation, captured by professionals in more controlled settings). We collect a new dataset for this application containing 404,683 shop photos collected from 25 different online retailers and 20,357 street photos, providing a total of 39,479 clothing item matches between street and shop photos. We develop three different methods for Exact Street to Shop retrieval, including two deep learning baseline methods, and a method to learn a similarity measure between the street and shop domains. Experiments demonstrate that our learned similarity significantly outperforms our baselines that use existing deep learning based representations.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"5 1","pages":"3343-3351"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87779871","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: 428
Rolling Shutter Super-Resolution 超分辨率卷帘式快门
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.71
Abhijith Punnappurath, Vijay Rengarajan, A. Rajagopalan
{"title":"Rolling Shutter Super-Resolution","authors":"Abhijith Punnappurath, Vijay Rengarajan, A. Rajagopalan","doi":"10.1109/ICCV.2015.71","DOIUrl":"https://doi.org/10.1109/ICCV.2015.71","url":null,"abstract":"Classical multi-image super-resolution (SR) algorithms, designed for CCD cameras, assume that the motion among the images is global. But CMOS sensors that have increasingly started to replace their more expensive CCD counterparts in many applications do not respect this assumption if there is a motion of the camera relative to the scene during the exposure duration of an image because of the row-wise acquisition mechanism. In this paper, we study the hitherto unexplored topic of multi-image SR in CMOS cameras. We initially develop an SR observation model that accounts for the row-wise distortions called the \"rolling shutter\" (RS) effect observed in images captured using non-stationary CMOS cameras. We then propose a unified RS-SR framework to obtain an RS-free high-resolution image (and the row-wise motion) from distorted low-resolution images. We demonstrate the efficacy of the proposed scheme using synthetic data as well as real images captured using a hand-held CMOS camera. Quantitative and qualitative assessments reveal that our method significantly advances the state-of-the-art.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"13 1 1","pages":"558-566"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89694167","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: 13
RGB-Guided Hyperspectral Image Upsampling rgb制导高光谱图像上采样
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.43
HyeokHyen Kwon, Yu-Wing Tai
{"title":"RGB-Guided Hyperspectral Image Upsampling","authors":"HyeokHyen Kwon, Yu-Wing Tai","doi":"10.1109/ICCV.2015.43","DOIUrl":"https://doi.org/10.1109/ICCV.2015.43","url":null,"abstract":"Hyperspectral imaging usually lack of spatial resolution due to limitations of hardware design of imaging sensors. On the contrary, latest imaging sensors capture a RGB image with resolution of multiple times larger than a hyperspectral image. In this paper, we present an algorithm to enhance and upsample the resolution of hyperspectral images. Our algorithm consists of two stages: spatial upsampling stage and spectrum substitution stage. The spatial upsampling stage is guided by a high resolution RGB image of the same scene, and the spectrum substitution stage utilizes sparse coding to locally refine the upsampled hyperspectral image through dictionary substitution. Experiments show that our algorithm is highly effective and has outperformed state-of-the-art matrix factorization based approaches.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"307-315"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87079185","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: 49
Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose 打开黑箱:手部姿态估计的分层采样优化
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.380
Danhang Tang, Jonathan Taylor, Pushmeet Kohli, Cem Keskin, Tae-Kyun Kim, J. Shotton
{"title":"Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose","authors":"Danhang Tang, Jonathan Taylor, Pushmeet Kohli, Cem Keskin, Tae-Kyun Kim, J. Shotton","doi":"10.1109/ICCV.2015.380","DOIUrl":"https://doi.org/10.1109/ICCV.2015.380","url":null,"abstract":"We address the problem of hand pose estimation, formulated as an inverse problem. Typical approaches optimize an energy function over pose parameters using a 'black box' image generation procedure. This procedure knows little about either the relationships between the parameters or the form of the energy function. In this paper, we show that we can significantly improving upon black box optimization by exploiting high-level knowledge of the structure of the parameters and using a local surrogate energy function. Our new framework, hierarchical sampling optimization, consists of a sequence of predictors organized into a kinematic hierarchy. Each predictor is conditioned on its ancestors, and generates a set of samples over a subset of the pose parameters. The highly-efficient surrogate energy is used to select among samples. Having evaluated the full hierarchy, the partial pose samples are concatenated to generate a full-pose hypothesis. Several hypotheses are generated using the same procedure, and finally the original full energy function selects the best result. Experimental evaluation on three publically available datasets show that our method is particularly impressive in low-compute scenarios where it significantly outperforms all other state-of-the-art methods.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"11 1","pages":"3325-3333"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90270774","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: 144
Robust Image Segmentation Using Contour-Guided Color Palettes 使用轮廓引导调色板的鲁棒图像分割
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.189
Xiang Fu, Chien-Yi Wang, Chen Chen, Changhu Wang, C.-C. Jay Kuo
{"title":"Robust Image Segmentation Using Contour-Guided Color Palettes","authors":"Xiang Fu, Chien-Yi Wang, Chen Chen, Changhu Wang, C.-C. Jay Kuo","doi":"10.1109/ICCV.2015.189","DOIUrl":"https://doi.org/10.1109/ICCV.2015.189","url":null,"abstract":"The contour-guided color palette (CCP) is proposed for robust image segmentation. It efficiently integrates contour and color cues of an image. To find representative colors of an image, color samples along long contours between regions, similar in spirit to machine learning methodology that focus on samples near decision boundaries, are collected followed by the mean-shift (MS) algorithm in the sampled color space to achieve an image-dependent color palette. This color palette provides a preliminary segmentation in the spatial domain, which is further fine-tuned by post-processing techniques such as leakage avoidance, fake boundary removal, and small region mergence. Segmentation performances of CCP and MS are compared and analyzed. While CCP offers an acceptable standalone segmentation result, it can be further integrated into the framework of layered spectral segmentation to produce a more robust segmentation. The superior performance of CCP-based segmentation algorithm is demonstrated by experiments on the Berkeley Segmentation Dataset.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"1618-1625"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90045167","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: 25
kNN Hashing with Factorized Neighborhood Representation 具有分解邻域表示的kNN哈希
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.131
Kun Ding, Chunlei Huo, Bin Fan, Chunhong Pan
{"title":"kNN Hashing with Factorized Neighborhood Representation","authors":"Kun Ding, Chunlei Huo, Bin Fan, Chunhong Pan","doi":"10.1109/ICCV.2015.131","DOIUrl":"https://doi.org/10.1109/ICCV.2015.131","url":null,"abstract":"Hashing is very effective for many tasks in reducing the processing time and in compressing massive databases. Although lots of approaches have been developed to learn data-dependent hash functions in recent years, how to learn hash functions to yield good performance with acceptable computational and memory cost is still a challenging problem. Based on the observation that retrieval precision is highly related to the kNN classification accuracy, this paper proposes a novel kNN-based supervised hashing method, which learns hash functions by directly maximizing the kNN accuracy of the Hamming-embedded training data. To make it scalable well to large problem, we propose a factorized neighborhood representation to parsimoniously model the neighborhood relationships inherent in training data. Considering that real-world data are often linearly inseparable, we further kernelize this basic model to improve its performance. As a result, the proposed method is able to learn accurate hashing functions with tolerable computation and storage cost. Experiments on four benchmarks demonstrate that our method outperforms the state-of-the-arts.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"6 1","pages":"1098-1106"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90110912","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: 14
Contractive Rectifier Networks for Nonlinear Maximum Margin Classification 非线性最大余量分类的收缩整流网络
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.289
S. An, Munawar Hayat, S. H. Khan, Bennamoun, F. Boussaïd, Ferdous Sohel
{"title":"Contractive Rectifier Networks for Nonlinear Maximum Margin Classification","authors":"S. An, Munawar Hayat, S. H. Khan, Bennamoun, F. Boussaïd, Ferdous Sohel","doi":"10.1109/ICCV.2015.289","DOIUrl":"https://doi.org/10.1109/ICCV.2015.289","url":null,"abstract":"To find the optimal nonlinear separating boundary with maximum margin in the input data space, this paper proposes Contractive Rectifier Networks (CRNs), wherein the hidden-layer transformations are restricted to be contraction mappings. The contractive constraints ensure that the achieved separating margin in the input space is larger than or equal to the separating margin in the output layer. The training of the proposed CRNs is formulated as a linear support vector machine (SVM) in the output layer, combined with two or more contractive hidden layers. Effective algorithms have been proposed to address the optimization challenges arising from contraction constraints. Experimental results on MNIST, CIFAR-10, CIFAR-100 and MIT-67 datasets demonstrate that the proposed contractive rectifier networks consistently outperform their conventional unconstrained rectifier network counterparts.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"2011 1","pages":"2515-2523"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86346738","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: 11
Fast and Effective L0 Gradient Minimization by Region Fusion 基于区域融合的快速有效L0梯度最小化算法
2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.32
Nguyen Ho Man Rang, M. S. Brown
{"title":"Fast and Effective L0 Gradient Minimization by Region Fusion","authors":"Nguyen Ho Man Rang, M. S. Brown","doi":"10.1109/ICCV.2015.32","DOIUrl":"https://doi.org/10.1109/ICCV.2015.32","url":null,"abstract":"L0 gradient minimization can be applied to an input signal to control the number of non-zero gradients. This is useful in reducing small gradients generally associated with signal noise, while preserving important signal features. In computer vision, L0 gradient minimization has found applications in image denoising, 3D mesh denoising, and image enhancement. Minimizing the L0 norm, however, is an NP-hard problem because of its non-convex property. As a result, existing methods rely on approximation strategies to perform the minimization. In this paper, we present a new method to perform L0 gradient minimization that is fast and effective. Our method uses a descent approach based on region fusion that converges faster than other methods while providing a better approximation of the optimal L0 norm. In addition, our method can be applied to both 2D images and 3D mesh topologies. The effectiveness of our approach is demonstrated on a number of examples.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"111 1","pages":"208-216"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79182295","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: 62
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信