检索结果-内蒙古大学图书馆

29th ieee conference on computer vision and pattern recognition (cvpr)

作者： Antipov, Grigory Baccouche, Moez Berrani, Sid-Ahmed Dugelay, Jean-Luc France Telecom Orange Labs 4 Rue Clos Courtel F-35512 Cesson Sevigne France Eurecom 450 Route Chappes F-06410 Biot France

ISBN: (纸本)9781509014378

This work describes our solution in the second edition of the ChaLearn LAP competition on Apparent Age Estimation. Starting from a pretrained version of the VGG-16 convolutional neural network for face recognition, we train it on the huge IMDB-Wiki dataset for biological age estimation and then fine-tune it for apparent age estimation using the relatively small competition dataset. We show that the precise age estimation of children is the cornerstone of the competition. Therefore, we integrate a separate "children" VGG- 16 network for apparent age estimation of children between 0 and 12 years old in our final solution. The "children" network is fine-tuned from the "general" one. We employ different age encoding strategies for training "general" and "children" networks: the soft one (label distribution encoding) for the "general" network and the strict one (0/1 classification encoding) for the "children" network. Finally, we highlight the importance of the state-of-the-art face detection and face alignment for the final apparent age estimation. Our resulting solution wins the 1st place in the competition significantly outperforming the runner-up.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Sequential Face Alignment via Person-Specific Modeling in the Wild 29

Sequential Face Alignment via Person-Specific Modeling in th...

引用

29th ieee conference on computer vision and pattern recognition (cvpr)

作者： Peng, Xi Huang, Junzhou Metaxas, Dimitris N. Rutgers State Univ Piscataway NJ 08854 USA Univ Texas Arlington Arlington TX 76019 USA

ISBN: (纸本)9781509014378

Sequential face alignment, in essence, deals with non-rigid deformation that changes over time. Although numerous methods have been proposed to show impressive success on still images, many of them still suffer from limited performance when it comes to sequential alignment in wild scenarios, e.g., involving large pose/expression variations and partial occlusions. The underlying reason is that they usually perform sequential alignment by independently applying models trained offline in each frame in a tracking-by-detection manner but completely ignoring temporal constraints that become available in sequence. To address this issue, we propose to exploit incremental learning for person-specific alignment. Our approach takes advantage of part-based representation and cascade regression for robust and efficient alignment on each frame. More importantly, it incrementally updates the representation sub-space and simultaneously adapts the cascade regressors in parallel using a unified framework. Person-specific modeling is eventually achieved on the fly while the drifting issue is significantly alleviated by erroneous detection using both part and holistic descriptors. Extensive experiments on both controlled and in-the-wild datasets demonstrate the superior performance of our approach compared with the state of the arts in terms of fitting accuracy and efficiency.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Deep Learning Based Representation for Face recognition 29

A Comprehensive Analysis of Deep Learning Based Representati...

引用

29th ieee conference on computer vision and pattern recognition (cvpr)

作者： Ghazi, Mostafa Mehdipour Ekenel, Hazim Kemal Sabanci Univ Fac Engn & Nat Sci Istanbul Turkey Istanbul Tech Univ Dept Comp Engn Istanbul Turkey

ISBN: (纸本)9781509014378

Deep learning based approaches have been dominating the face recognition field due to the significant performance improvement they have provided on the challenging wild datasets. These approaches have been extensively tested on such unconstrained datasets, on the Labeled Faces in the Wild and YouTube Faces, to name a few. However, their capability to handle individual appearance variations caused by factors such as head pose, illumination, occlusion, and misalignment has not been thoroughly assessed till now. In this paper, we present a comprehensive study to evaluate the performance of deep learning based face representation under several conditions including the varying head pose angles, upper and lower face occlusion, changing illumination of different strengths, and misalignment due to erroneous facial feature localization. Two successful and publicly available deep learning models, namely VGG-Face and Lightened CNN have been utilized to extract face representations. The obtained results show that although deep learning provides a powerful representation for face recognition, it can still benefit from preprocessing, for example, for pose and illumination normalization in order to achieve better performance under various conditions. Particularly, if these variations are not included in the dataset used to train the deep learning model, the role of preprocessing becomes more crucial. Experimental results also show that deep learning based representation is robust to misalignment and can tolerate facial feature localization errors up to 10% of the interocular distance.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of Emotions and Membership in Group Videos 29

Automatic Recognition of Emotions and Membership in Group Vi...

引用

29th ieee conference on computer vision and pattern recognition (cvpr)

作者： Mou, Wenxuan Gunes, Hatice Patras, Ioannis Queen Mary Univ London London England Univ Cambridge Cambridge England

ISBN: (纸本)9781509014378

Automatic affect analysis and understanding has become a well established research area in the last two decades. However, little attention has been paid to the analysis of the affect expressed in group settings, either in the form of affect expressed by the whole group collectively or affect expressed by each individual member of the group. This paper presents a framework which, in group settings automatically classifies the affect expressed by each individual group member along both arousal and valence dimensions. We first introduce a novel Volume Quantised Local Zernike Moments Fisher Vectors (vQLZM-FV) descriptor to represent the facial behaviours of individuals in the spatio-temporal domain and then propose a method to recognize the group membership of each individual (i.e., which group the individual in question is part of) by using their face and body behavioural cues. We conduct a set of experiments on a newly collected dataset that contains fourteen recordings of four groups, each consisting of four people watching affective movie stimuli. Our experimental results show that (1) the proposed vQLZM-FV outperforms the other feature representations in affect recognition, and (2) group membership can be recognized using the non-verbal face and body features, indicating that individuals influence each other's behaviours within a group setting.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

A Combined EM and Visual Tracking Probabilistic Model for Robust Mosaicking: Application to Fetoscopy 29

A Combined EM and Visual Tracking Probabilistic Model for Ro...

引用

29th ieee conference on computer vision and pattern recognition (cvpr)

作者： Tella, Marcel Daga, Pankaj Chadebecq, Francois Thompson, Stephen Shakir, Dzhoshkun I. Dwyer, George Wimalasundera, Ruwan Deprest, Jan Stoyanov, Danail Vercauteren, Tom Ourselin, Sebastien UCL Translat Imaging Grp CMIC London WC1E 6BT England UCL Surg Robot Vis Grp CMIC London WC1E 6BT England Univ Hosp Leuven Dept Obstet & Gynaecol Leuven Belgium Univ Coll Hosp London England

ISBN: (纸本)9781509014378

Twin-to-Twin Transfusion Syndrome (TTTS) is a progressive pregnancy complication in which inter-twin vascular connections in the shared placenta result in a blood flow imbalance between the twins. The most effective therapy is to sever these connections by laser photo-coagulation. However, the limited field of view of the fetoscope hinders their identification. A potential solution is to augment the surgeon's view by creating a mosaic image of the placenta. State-of-the-art mosaicking methods use feature-based approaches, which have three main limitations: (i) they are not robust against corrupt data e.g. blurred frames, (ii) temporal information is not used, (iii) the resulting mosaic suffers from drift. We introduce a probabilistic temporal model that incorporates electromagnetic and visual tracking data to achieve a robust mosaic with reduced drift. By assuming planarity of the imaged object, the nRT decomposition can be used to parametrize the state vector. Finally, we tackle the non-linear nature of the problem in a numerically stable manner by using the Square Root Unscented Kalman Filter. We show an improvement in performance in terms of robustness as well as a reduction of the drift in comparison to state-of-the-art methods in synthetic, phantom and ex vivo datasets.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Covert Video Classification by Codebook Growing pattern 29

Covert Video Classification by Codebook Growing Pattern

引用

29th ieee conference on computer vision and pattern recognition (cvpr)

作者： Du, Liang Lang, Haitao Tian, Ying-Li Tan, Chiu C. Wu, Jie Ling, Haibin Temple Univ Philadelphia PA 19122 USA Beijing Univ Chem Technol Beijing Peoples R China City Univ New York New York NY USA

ISBN: (纸本)9781509014378

Recent advances in visual data acquisition and Internet technologies make it convenient and popular to collect and share videos. These activities, however, also raise the issue of privacy invasion. One potential privacy threat is the unauthorized capture and/or sharing of covert videos, which are recorded without the awareness of the subject(s) in the video. Automatic classification of such videos can provide an important basis toward addressing relevant privacy issues. The task is very challenging due to the large intra-class variation and between-class similarity, since there is no limit in the content of a covert video and it may share very similar content with a regular video. The challenge brings troubles when applying existing content-based video analysis methods to covert video classification. In this paper, we propose a novel descriptor, codebook growing pattern (CGP), which is derived from latent Dirichlet allocation (LDA) over optical flows. Given an input video V, we first represent it with a sequence of histograms of optical flow (HOF). After that, these HOFs are fed into LDA to dynamically generate the codebook for V. The CGP descriptor is then defined as the growing codebook sizes in the LDA procedure. CGP fits naturally for covert video representation since (1) optical flows can capture the camera motion that characterizes the covert video acquisition, and (2) CGP by itself is insensitive to video content. To evaluate the proposed approach, we collected a large covert video dataset, the first such dataset to our knowledge, and tested the proposed method on the dataset. The results show clearly the effectiveness of the proposed approach in comparison with other state-of-the-art video classification algorithms.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Geospatial correspondences for multimodal registration

Geospatial correspondences for multimodal registration

引用

2016 ieee conference on computer vision and pattern recognition, cvpr 2016

作者： Marcos, Diego Hamid, Raffay Tuia, Devis University of Zurich Switzerland DigitalGlobe Inc. United States

The growing availability of very high resolution (

ISBN: (纸本)9781467388511

The growing availability of very high resolution (

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Parametric object motion from blur

Parametric object motion from blur

引用

2016 ieee conference on computer vision and pattern recognition, cvpr 2016

作者： Gast, Jochen Sellent, Anita Roth, Stefan Department of Computer Science TU Darmstadt Germany

ISBN: (纸本)9781467388511

Motion blur can adversely affect a number of vision tasks, hence it is generally considered a nuisance. We instead treat motion blur as a useful signal that allows to compute the motion of objects from a single image. Drawing on the success of joint segmentation and parametric motion models in the context of optical flow estimation, we propose a parametric object motion model combined with a segmentation mask to exploit localized, non-uniform motion blur. Our parametric image formation model is differentiable w.r.t. the motion parameters, which enables us to generalize marginal-likelihood techniques from uniform blind deblurring to localized, non-uniform blur. A two-stage pipeline, first in derivative space and then in image space, allows to estimate both parametric object motion as well as a motion segmentation from a single image alone. Our experiments demonstrate its ability to cope with very challenging cases of object motion blur.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Pupil detection for head-mounted eye tracking in the wild: an evaluation of the state of the art

引用

MACHINE vision AND APPLICATIONS 2016年第8期27卷 1275-1288页

作者： Fuhl, Wolfgang Tonsen, Marc Bulling, Andreas Kasneci, Enkelejda Univ Tubingen Percept Engn Grp Tubingen Germany Max Planck Inst Informat Perceptual User Interfaces Grp Saarbrucken Germany

Robust and accurate detection of the pupil position is a key building block for head-mounted eye tracking and prerequisite for applications on top, such as gaze-based human-computer interaction or attention analysis. Despite a large body of work, detecting the pupil in images recorded under real-world conditions is challenging given significant variability in the eye appearance (e.g., illumination, reflections, occlusions, etc.), individual differences in eye physiology, as well as other sources of noise, such as contact lenses or make-up. In this paper we review six state-of-the-art pupil detection methods, namely ElSe (Fuhl et al. in Proceedings of the ninth biennial ACM symposium on eye tracking research&applications, ACM. New York, NY, USA, pp 123130, 2016), ExCuSe (Fuhl et al. in computer analysis of images and patterns. Springer, New York, pp 39-51, 2015), Pupil Labs (Kassner et al. in Adjunct proceedings of the 2014 ACM international joint conference on pervasive and ubiquitous computing (UbiComp), pp 1151-1160, 2014. doi: 10.1145/2638728.2641695), SET (Javadi et al. in Front Neuroeng 8, 2015), Starburst (Li et al. in computer vision and pattern recognition-workshops, 2005. ieee computer society conference on cvpr workshops. ieee, pp 79-79, 2005), and Swirski (Swirski et al. in Proceedings of the symposium on eye tracking research and applications (ETRA). ACM, pp 173-176, 2012. doi: 10.1145/2168556.2168585). We compare their performance on a large-scale data set consisting of 225,569 annotated eye images taken from four publicly available data sets. Our experimental results show that the algorithm ElSe (Fuhl et al. 2016) outperforms other pupil detection methods by a large margin, offering thus robust and accurate pupil positions on challenging everyday eye images.

关键词： Pupil detection Head-mounted eye tracking Data set computer vision Image processing

来源：评论

学校读者我要写书评

暂无评论

Structured regression gradient boosting

Structured regression gradient boosting

引用

2016 ieee conference on computer vision and pattern recognition, cvpr 2016

作者： Diego, Ferran Hamprecht, Fred A. University of Heidelberg Heidelberg69115 Germany

ISBN: (纸本)9781467388511

We propose a new way to train a structured output prediction model. More specifically, we train nonlinear data terms in a Gaussian Conditional Random Field (GCRF) by a generalized version of gradient boosting. The approach is evaluated on three challenging regression benchmarks: vessel detection, single image depth estimation and image inpainting. These experiments suggest that the proposed boosting framework matches or exceeds the state-of-the-art.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：