2015 IEEE International Conference on Computer Vision (ICCV)最新文献_第2页

A Collaborative Filtering Approach to Real-Time Hand Pose Estimation 一种实时手部姿态估计的协同滤波方法

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.269

Chiho Choi, Ayan Sinha, J. H. Choi, Sujin Jang, K. Ramani

引用次数: 57

Efficient Video Segmentation Using Parametric Graph Partitioning 基于参数图分割的高效视频分割

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.361

Chen-Ping Yu, Hieu M. Le, G. Zelinsky, D. Samaras

{"title":"Efficient Video Segmentation Using Parametric Graph Partitioning","authors":"Chen-Ping Yu, Hieu M. Le, G. Zelinsky, D. Samaras","doi":"10.1109/ICCV.2015.361","DOIUrl":"https://doi.org/10.1109/ICCV.2015.361","url":null,"abstract":"Video segmentation is the task of grouping similar pixels in the spatio-temporal domain, and has become an important preprocessing step for subsequent video analysis. Most video segmentation and supervoxel methods output a hierarchy of segmentations, but while this provides useful multiscale information, it also adds difficulty in selecting the appropriate level for a task. In this work, we propose an efficient and robust video segmentation framework based on parametric graph partitioning (PGP), a fast, almost parameter free graph partitioning method that identifies and removes between-cluster edges to form node clusters. Apart from its computational efficiency, PGP performs clustering of the spatio-temporal volume without requiring a pre-specified cluster number or bandwidth parameters, thus making video segmentation more practical to use in applications. The PGP framework also allows processing sub-volumes, which further improves performance, contrary to other streaming video segmentation methods where sub-volume processing reduces performance. We evaluate the PGP method using the SegTrack v2 and Chen Xiph.org datasets, and show that it outperforms related state-of-the-art algorithms in 3D segmentation metrics and running time.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"77 1","pages":"3155-3163"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79036626","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: 30

Adaptive Hashing for Fast Similarity Search 快速相似性搜索的自适应哈希算法

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.125

Fatih Çakir, S. Sclaroff

引用次数: 75

Illumination Robust Color Naming via Label Propagation 基于标签传播的光照鲁棒颜色命名

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.78

Yuanliu Liu, Zejian Yuan, Badong Chen, Jianru Xue, Nanning Zheng

引用次数: 13

A Spatio-Temporal Appearance Representation for Video-Based Pedestrian Re-Identification 基于视频的行人再识别的时空外观表征

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.434

Kang Liu, Bingpeng Ma, Wei Zhang, Rui Huang

{"title":"A Spatio-Temporal Appearance Representation for Video-Based Pedestrian Re-Identification","authors":"Kang Liu, Bingpeng Ma, Wei Zhang, Rui Huang","doi":"10.1109/ICCV.2015.434","DOIUrl":"https://doi.org/10.1109/ICCV.2015.434","url":null,"abstract":"Pedestrian re-identification is a difficult problem due to the large variations in a person's appearance caused by different poses and viewpoints, illumination changes, and occlusions. Spatial alignment is commonly used to address these issues by treating the appearance of different body parts independently. However, a body part can also appear differently during different phases of an action. In this paper we consider the temporal alignment problem, in addition to the spatial one, and propose a new approach that takes the video of a walking person as input and builds a spatio-temporal appearance representation for pedestrian re-identification. Particularly, given a video sequence we exploit the periodicity exhibited by a walking person to generate a spatio-temporal body-action model, which consists of a series of body-action units corresponding to certain action primitives of certain body parts. Fisher vectors are learned and extracted from individual body-action units and concatenated into the final representation of the walking person. Unlike previous spatio-temporal features that only take into account local dynamic appearance information, our representation aligns the spatio-temporal appearance of a pedestrian globally. Extensive experiments on public datasets show the effectiveness of our approach compared with the state of the art.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"115 1","pages":"3810-3818"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80840059","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: 239

Enhancing Road Maps by Parsing Aerial Images Around the World 通过解析世界各地的航空图像来增强道路地图

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.197

G. Máttyus, Shenlong Wang, S. Fidler, R. Urtasun

引用次数: 115

Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts 基于弱监督图的图像部分学习群体语义分割

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.160

Niloufar Pourian, S. Karthikeyan, B. S. Manjunath

{"title":"Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts","authors":"Niloufar Pourian, S. Karthikeyan, B. S. Manjunath","doi":"10.1109/ICCV.2015.160","DOIUrl":"https://doi.org/10.1109/ICCV.2015.160","url":null,"abstract":"We present a weakly-supervised approach to semantic segmentation. The goal is to assign pixel-level labels given only partial information, for example, image-level labels. This is an important problem in many application scenarios where it is difficult to get accurate segmentation or not feasible to obtain detailed annotations. The proposed approach starts with an initial coarse segmentation, followed by a spectral clustering approach that groups related image parts into communities. A community-driven graph is then constructed that captures spatial and feature relationships between communities while a label graph captures correlations between image labels. Finally, mapping the image level labels to appropriate communities is formulated as a convex optimization problem. The proposed approach does not require location information for image level labels and can be trained using partially labeled datasets. Compared to the state-of-the-art weakly supervised approaches, we achieve a significant performance improvement of 9% on MSRC-21 dataset and 11% on LabelMe dataset, while being more than 300 times faster.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"36 1","pages":"1359-1367"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82042904","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: 37

A Multiscale Variable-Grouping Framework for MRF Energy Minimization MRF能量最小化的多尺度变量分组框架

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.210

Omer Meir, M. Galun, Stav Yagev, R. Basri, I. Yavneh

引用次数: 1

Per-Sample Kernel Adaptation for Visual Recognition and Grouping 基于样本核自适应的视觉识别与分组

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.148

Borislav Antic, B. Ommer

{"title":"Per-Sample Kernel Adaptation for Visual Recognition and Grouping","authors":"Borislav Antic, B. Ommer","doi":"10.1109/ICCV.2015.148","DOIUrl":"https://doi.org/10.1109/ICCV.2015.148","url":null,"abstract":"Object, action, or scene representations that are corrupted by noise significantly impair the performance of visual recognition. Typically, partial occlusion, clutter, or excessive articulation affects only a subset of all feature dimensions and, most importantly, different dimensions are corrupted in different samples. Nevertheless, the common approach to this problem in feature selection and kernel methods is to down-weight or eliminate entire training samples or the same dimensions of all samples. Thus, valuable signal is lost, resulting in suboptimal classification. Our goal is, therefore, to adjust the contribution of individual feature dimensions when comparing any two samples and computing their similarity. Consequently, per-sample selection of informative dimensions is directly integrated into kernel computation. The interrelated problems of learning the parameters of a kernel classifier and determining the informative components of each sample are then addressed in a joint objective function. The approach can be integrated into the learning stage of any kernel-based visual recognition problem and it does not affect the computational performance in the retrieval phase. Experiments on diverse challenges of action recognition in videos and indoor scene classification show the general applicability of the approach and its ability to improve learning of visual representations.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"6 1","pages":"1251-1259"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73308285","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: 4

Detection and Segmentation of 2D Curved Reflection Symmetric Structures 二维弯曲反射对称结构的检测与分割

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.192

C. L. Teo, C. Fermüller, Y. Aloimonos

{"title":"Detection and Segmentation of 2D Curved Reflection Symmetric Structures","authors":"C. L. Teo, C. Fermüller, Y. Aloimonos","doi":"10.1109/ICCV.2015.192","DOIUrl":"https://doi.org/10.1109/ICCV.2015.192","url":null,"abstract":"Symmetry, as one of the key components of Gestalt theory, provides an important mid-level cue that serves as input to higher visual processes such as segmentation. In this work, we propose a complete approach that links the detection of curved reflection symmetries to produce symmetry-constrained segments of structures/regions in real images with clutter. For curved reflection symmetry detection, we leverage on patch-based symmetric features to train a Structured Random Forest classifier that detects multiscaled curved symmetries in 2D images. Next, using these curved symmetries, we modulate a novel symmetry-constrained foreground-background segmentation by their symmetry scores so that we enforce global symmetrical consistency in the final segmentation. This is achieved by imposing a pairwise symmetry prior that encourages symmetric pixels to have the same labels over a MRF-based representation of the input image edges, and the final segmentation is obtained via graph-cuts. Experimental results over four publicly available datasets containing annotated symmetric structures: 1) SYMMAX-300 [38], 2) BSD-Parts, 3) Weizmann Horse (both from [18]) and 4) NY-roads [35] demonstrate the approach's applicability to different environments with state-of-the-art performance.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"40 1","pages":"1644-1652"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79887328","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: 34