2016 IEEE Winter Conference on Applications of Computer Vision (WACV)最新文献

Deep learning the dynamic appearance and shape of facial action units 深度学习面部动作单元的动态外观和形状

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-05-26 DOI: 10.1109/WACV.2016.7477625

S. Jaiswal, M. Valstar

引用次数: 153

Region graph based method for multi-object detection and tracking using depth cameras 基于区域图的深度相机多目标检测与跟踪方法

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-11 DOI: 10.1109/WACV.2016.7477568

Sachin Mehta, B. Prabhakaran

引用次数: 6

Pose tracking by efficiently exploiting global features 有效利用全局特征的姿态跟踪

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477563

Ratnesh Kumar, Dhruv Batra

{"title":"Pose tracking by efficiently exploiting global features","authors":"Ratnesh Kumar, Dhruv Batra","doi":"10.1109/WACV.2016.7477563","DOIUrl":"https://doi.org/10.1109/WACV.2016.7477563","url":null,"abstract":"Typical pose tracking algorithms first obtain a set of plausible pose hypotheses in all image frames of a video and subsequently stitch compatible detections across time to form a pose-track. This approach to tracking is commonly termed tracking-by-detections, and has been very successful in other areas such as multiple object tracking, video segmentation using object proposals. Often models in this category can only incorporate local spatio-temporal evidence due to exponentially increased cost when using global information. Local spatio-temporal evidence can be ambiguous, thus leading to an inferior objective modeling. To deal with ambiguities in local information it is necessary to incorporate global information over multiple frames into a model. Based on the recent advances in generating multiple solutions from a probabilistic model, we first generate multiple plausible pose-track hypotheses, and subsequently employ a mixture of local and global features to express the quality of these solutions with high fidelity. We perform extensive experiments and competitive results across varied datasets demonstrate the robustness of our approach.","PeriodicalId":124363,"journal":{"name":"2016 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123065027","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: 1

Variational multi-phase segmentation using high-dimensional local features 基于高维局部特征的变分多相分割

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477729

N. Mevenkamp, B. Berkels

引用次数: 18

Hide and seek: Uncovering facial occlusion with variable-threshold robust PCA 捉迷藏:用变阈值鲁棒PCA发现面部遮挡

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477579

W. Leow, Guodong Li, J. Lai, T. Sim, Vaishali Sharma

引用次数: 3

Accurate and efficient pulse measurement from facial videos on smartphones 通过智能手机上的面部视频进行准确高效的脉搏测量

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477669

Chong Huang, Xin Yang, K. Cheng

引用次数: 7

Monocular obstacle avoidance for blind people using probabilistic focus of expansion estimation 基于概率焦点扩展估计的盲人单眼避障

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477608

Sebastian Stabinger, A. Rodríguez-Sánchez, J. Piater

引用次数: 2

Joint object recognition and pose estimation using a nonlinear view-invariant latent generative model 基于非线性视觉不变潜在生成模型的联合目标识别和姿态估计

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477655

A. Bakry, Tarek El-Gaaly, Mohamed Elhoseiny, A. Elgammal

引用次数: 7

Is alice chasing or being chased?: Determining subject and object of activities in videos 爱丽丝在追还是被追?:确定视频活动的主体和客体

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477710

Teng Zhang, Liangchen Liu, A. Wiliem, B. Lovell

{"title":"Is alice chasing or being chased?: Determining subject and object of activities in videos","authors":"Teng Zhang, Liangchen Liu, A. Wiliem, B. Lovell","doi":"10.1109/WACV.2016.7477710","DOIUrl":"https://doi.org/10.1109/WACV.2016.7477710","url":null,"abstract":"Recent progress in video description has shown promising results by combining object/action recognition and natural language processing techniques. However, even the most simplest form of the generated sentence, the SVO triplet (Subject/Verb/Object), can be misleading for its lack of role relationship analysis. When the system detects keywords \"person\", \"baby\" and \"feed\", we do not want the system to generate \"a person feeding a baby\" when the actual screen is a scene where the baby is trying to share the food. In this paper, we explore role relationships between objects/persons and their usage in generating a more meaningful video description. More specifically, we confine ourselves on the following problem: identifying subject and object roles in two-person activities. We argue that the subject and object roles have consistent properties across different activities. To that end, we cast this problem as a domain adaptation problem. A novel Youtube SVO dataset is proposed for evaluating methods developed for this problem. The performance of the proposed method is compared against several baseline methods.","PeriodicalId":124363,"journal":{"name":"2016 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121395469","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: 6

Multiscale fully convolutional network with application to industrial inspection 多尺度全卷积网络在工业检测中的应用

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2016-03-07 DOI: 10.1109/WACV.2016.7477595

Xiao Bian, Ser-Nam Lim, Ning Zhou

{"title":"Multiscale fully convolutional network with application to industrial inspection","authors":"Xiao Bian, Ser-Nam Lim, Ning Zhou","doi":"10.1109/WACV.2016.7477595","DOIUrl":"https://doi.org/10.1109/WACV.2016.7477595","url":null,"abstract":"In recent years, deep learning, particularly Convolutional Neural Network (CNN), has shown great efficacy for solving various vision tasks. In image segmentation, it has been demonstrated that a CNN can greatly outperform other approaches. However, special attention has to be paid towards setting various parameters in the CNN that affects the scale of the feature map generated at the last convolutional layer, where scale here refers to the ratio of the number of pixels in the original input image that correspond to each pixel in the feature map. Quite often, the optimal settings are tied to the specific problem on hand and can be fairly challenging to determine. To overcome such an issue, this paper proposes a multiscale Fully Convolutional Network (FCN) that combines networks trained at various scales, thereby allowing for conducting segmentation more generically. Moreover, such a multiscale architecture allows for incremental fine-tuning as more training images become available later on and new networks can be trained and added to the combined network. Such flexibility has great utility in applications such as industrial inspection, where training images may not be readily available initially, but yet requires a high level of accuracy. This paper will validate our findings by reporting the results that we have obtained by applying multiscale FCN to the inspection of aircraft engine part.","PeriodicalId":124363,"journal":{"name":"2016 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128106236","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: 54