CVPR 2011最新文献_第5页

Probabilistic event logic for interval-based event recognition 基于间隔的事件识别的概率事件逻辑

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995491

William Brendel, Alan Fern, S. Todorovic

{"title":"Probabilistic event logic for interval-based event recognition","authors":"William Brendel, Alan Fern, S. Todorovic","doi":"10.1109/CVPR.2011.5995491","DOIUrl":"https://doi.org/10.1109/CVPR.2011.5995491","url":null,"abstract":"This paper is about detecting and segmenting interrelated events which occur in challenging videos with motion blur, occlusions, dynamic backgrounds, and missing observations. We argue that holistic reasoning about time intervals of events, and their temporal constraints is critical in such domains to overcome the noise inherent to low-level video representations. For this purpose, our first contribution is the formulation of probabilistic event logic (PEL) for representing temporal constraints among events. A PEL knowledge base consists of confidence-weighted formulas from a temporal event logic, and specifies a joint distribution over the occurrence time intervals of all events. Our second contribution is a MAP inference algorithm for PEL that addresses the scalability issue of reasoning about an enormous number of time intervals and their constraints in a typical video. Specifically, our algorithm leverages the spanning-interval data structure for compactly representing and manipulating entire sets of time intervals without enumerating them. Our experiments on interpreting basketball videos show that PEL inference is able to jointly detect events and identify their time intervals, based on noisy input from primitive-event detectors.","PeriodicalId":445398,"journal":{"name":"CVPR 2011","volume":"23 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115525903","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: 113

Time and space efficient spectral clustering via column sampling 通过柱采样的时间和空间有效的光谱聚类

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995425

Mu Li, Xiao-Chen Lian, J. Kwok, Bao-Liang Lu

引用次数: 72

On deep generative models with applications to recognition 深度生成模型及其在识别中的应用

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995710

Marc'Aurelio Ranzato, J. Susskind, Volodymyr Mnih, Geoffrey E. Hinton

引用次数: 226

A unified framework for locating and recognizing human actions 定位和识别人类行为的统一框架

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995648

Yuelei Xie, Hong Chang, Zhe Li, Luhong Liang, Xilin Chen, Debin Zhao

引用次数: 38

Segment an image by looking into an image corpus 通过查看图像语料库来分割图像

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995497

Xiaobai Liu, Jiashi Feng, Shuicheng Yan, Liang Lin, Hai Jin

{"title":"Segment an image by looking into an image corpus","authors":"Xiaobai Liu, Jiashi Feng, Shuicheng Yan, Liang Lin, Hai Jin","doi":"10.1109/CVPR.2011.5995497","DOIUrl":"https://doi.org/10.1109/CVPR.2011.5995497","url":null,"abstract":"This paper investigates how to segment an image into semantic regions by harnessing an unlabeled image corpus. First, the image segmentation task is recast as a small-size patch grouping problem. Then, we discover two novel patch-pair priors, namely the first-order patch-pair density prior and the second-order patch-pair co-occurrence prior, founded on two statistical observations from the natural image corpus. The underlying rationalities are: 1) a patch-pair falling within the same object region generally has higher density than a patch-pair falling on different objects, and 2) two patch-pairs with high co-occurrence frequency are likely to bear similar semantic consistence confidences (SCCs), i.e. the confidence of the consisted two patches belonging to the same semantic concept. These two discriminative priors are further integrated into a unified objective function in order to augment the intrinsic patch-pair similarities, originally calculated using patch-level visual features, into the semantic consistence confidences. Nonnegative constraint is also imposed over the output variables and an efficient iterative procedure is provided to seek the optimal solution. The ultimate patch grouping is conducted by first building a similarity graph, which takes the atomic patches as vertices and the augmented patch-pair SCCs as edge weights, and then employing the popular Normalized Cut approach to group patches into semantic clusters. Extensive image segmentation experiments on two public databases clearly demonstrate the superiority of the proposed approach over various state-of-the-arts unsupervised image segmentation algorithms.","PeriodicalId":445398,"journal":{"name":"CVPR 2011","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116952942","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: 5

Symmetric piecewise planar object reconstruction from a single image 对称分段平面物体重建从一个单一的图像

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995405

Tianfan Xue, Jianzhuang Liu, Xiaoou Tang

引用次数: 20

Evaluating combinational color constancy methods on real-world images 评价真实世界图像的组合色彩常数方法

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995615

Bing Li, Weihua Xiong, Weiming Hu, Ou Wu

引用次数: 24

Affinity learning on a tensor product graph with applications to shape and image retrieval 张量积图的亲和学习及其在形状和图像检索中的应用

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995325

Xingwei Yang, Longin Jan Latecki

引用次数: 70

Automatic adaptation of a generic pedestrian detector to a specific traffic scene 通用行人检测器对特定交通场景的自动适应

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995698

M. Wang, Xiaogang Wang

{"title":"Automatic adaptation of a generic pedestrian detector to a specific traffic scene","authors":"M. Wang, Xiaogang Wang","doi":"10.1109/CVPR.2011.5995698","DOIUrl":"https://doi.org/10.1109/CVPR.2011.5995698","url":null,"abstract":"In recent years significant progress has been made learning generic pedestrian detectors from manually labeled large scale training sets. However, when a generic pedestrian detector is applied to a specific scene where the testing data does not match with the training data because of variations of viewpoints, resolutions, illuminations and backgrounds, its accuracy may decrease greatly. In this paper, we propose a new framework of adapting a pre-trained generic pedestrian detector to a specific traffic scene by automatically selecting both confident positive and negative examples from the target scene to re-train the detector iteratively. An important feature of the proposed framework is to utilize unsupervisedly learned models of vehicle and pedestrian paths, together with multiple other cues such as locations, sizes, appearance and motions to select new training samples. The information of scene structures increases the reliability of selected samples and is complementary to the appearance-based detector. However, it was not well explored in previous studies. In order to further improve the reliability of selected samples, outliers are removed through multiple hierarchical clustering steps. The effectiveness of different cues and clustering steps is evaluated through experiments. The proposed approach significantly improves the accuracy of the generic pedestrian detector and also outperforms the scene specific detector retrained using background subtraction. Its results are comparable with the detector trained using a large number of manually labeled frames from the target scene.","PeriodicalId":445398,"journal":{"name":"CVPR 2011","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123501983","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: 209

Contour-based joint clustering of multiple segmentations 基于轮廓的多段联合聚类

CVPR 2011 Pub Date : 2011-06-20 DOI: 10.1109/CVPR.2011.5995436

Daniel Glasner, S. Vitaladevuni, R. Basri

引用次数: 36