Results 1 - 10
of
14
Reconstruction-based metric learning for unconstrained face verification,” Information Forensics and Security
- IEEE Transactions on
, 2015
"... Abstract — In this paper, we propose a reconstruction-based metric learning method to learn a discriminative distance metric for unconstrained face verification. Unlike conventional metric learning methods, which only consider the label information of training samples and ignore the reconstruction r ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Abstract — In this paper, we propose a reconstruction-based metric learning method to learn a discriminative distance metric for unconstrained face verification. Unlike conventional metric learning methods, which only consider the label information of training samples and ignore the reconstruction residual infor-mation in the learning procedure, we apply a reconstruction criterion to learn a discriminative distance metric. For each training example, the distance metric is learned by enforcing a margin between the interclass sparse reconstruction residual and interclass sparse reconstruction residual, so that the recon-struction residual of training samples can be effectively exploited to compute the between-class and within-class variations. To better use multiple features for distance metric learning, we propose a reconstruction-based multimetric learning method to collaboratively learn multiple distance metrics, one for each feature descriptor, to remove uncorrelated information for recog-nition. We evaluate our proposed methods on the Labelled Faces in the Wild (LFW) and YouTube face data sets and our experimental results clearly show the superiority of our methods over both previous metric learning methods and several state-of-the-art unconstrained face verification methods. Index Terms — Face recognition, unconstrained face verification, metric learning, reconstruction-based learning.
Discriminative Shared Gaussian Processes for Multiview and View-Invariant Facial Expression Recognition
"... Abstract — Images of facial expressions are often captured from various views as a result of either head movements or variable camera position. Existing methods for multiview and/or view-invariant facial expression recognition typically perform classification of the observed expression using either ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract — Images of facial expressions are often captured from various views as a result of either head movements or variable camera position. Existing methods for multiview and/or view-invariant facial expression recognition typically perform classification of the observed expression using either classifiers learned separately for each view or a single classifier learned for all views. However, these approaches ignore the fact that different views of a facial expression are just different manifestations of the same facial expression. By accounting for this redundancy, we can design more effective classifiers for the target task. To this end, we propose a discriminative shared Gaussian process latent variable model (DS-GPLVM) for multiview and view-invariant classification of facial expressions from multiple views. In this model, we first learn a discriminative manifold shared by multiple views of a facial expression. Subsequently, we perform facial expression classification in the expression manifold. Finally, classification of an observed facial expression is carried out either in the view-invariant manner (using only a single view of the expression) or in the multiview manner (using multiple views of the expression). The proposed model can also be used to perform fusion of different facial features in a principled manner. We validate the proposed DS-GPLVM on both posed and spontaneously displayed facial expressions from three publicly available datasets (MultiPIE, labeled face parts in the wild, and static facial expressions in the wild). We show that this model outperforms the state-of-the-art methods for multiview and view-invariant facial expression classification, and several state-of-the-art methods for multiview learning and feature fusion. Index Terms — View-invariant, multi-view learning, facial expression recognition, Gaussian Processes.
IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Robust Face Recognition from Multi-View Videos
"... Abstract—Multi-view face recognition has become an active research area in the last few years. In this paper, we present an approach for video-based face recognition in camera net-works. Our goal is to handle pose variations by exploiting the redundancy in multi-view video data. However, unlike trad ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Multi-view face recognition has become an active research area in the last few years. In this paper, we present an approach for video-based face recognition in camera net-works. Our goal is to handle pose variations by exploiting the redundancy in multi-view video data. However, unlike traditional approaches that explicitly estimate the pose of the face, we propose a novel feature for robust face recognition in the presence of diffuse lighting and pose variations. The proposed feature is developed using the spherical harmonic representation of the face texture-mapped onto a sphere; the texture map itself is generated by back-projecting the multi-view video data. Video plays an important role in this scenario. First, it provides an automatic and efficient way for feature extraction. Second, the data redundancy renders the recognition algorithm more robust. We measure the similarity between feature sets from different videos using the Reproducing Kernel Hilbert Space. We demonstrate that the proposed approach outperforms traditional algorithms on a multi-view video database.
Learning Compact Binary Face Descriptor for Face Recognition
"... Abstract—Binary feature descriptors such as local binary patterns (LBP) and its variations have been widely used in many face recognition systems due to their excellent robustness and strong discriminative power. However, most existing binary face descriptors are hand-crafted, which require strong p ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Binary feature descriptors such as local binary patterns (LBP) and its variations have been widely used in many face recognition systems due to their excellent robustness and strong discriminative power. However, most existing binary face descriptors are hand-crafted, which require strong prior knowledge to engineer them by hand. In this paper, we propose a compact binary face descriptor (CBFD) feature learning method for face representation and recognition. Given each face image, we first extract pixel difference vectors (PDVs) in local patches by computing the difference between each pixel and its neighboring pixels. Then, we learn a feature mapping to project these pixel difference vectors into low-dimensional binary vectors in an unsupervised manner, where 1) the variance of all binary codes in the training set is maximized, 2) the loss between the original real-valued codes and the learned binary codes is minimized, and 3) binary codes evenly distribute at each learned bin, so that the redundancy information in PDVs is removed and compact binary codes are obtained. Lastly, we cluster and pool these binary codes into a histogram feature as the final representation for each face image. Moreover, we propose a coupled CBFD (C-CBFD) method by reducing the modality gap of heterogeneous faces at the feature level to make our method applicable to heterogeneous face recognition. Extensive experimental results on five widely used face datasets show that our methods outperform state-of-the-art face descriptors. Index Terms—Face recognition, heterogeneous face matching, feature learning, binary feature, compact feature, biometrics Ç 1
Rank Consistency based Multi-View Learning: A Privacy-Preserving Approach
"... Complex media objects are often described by multi-view feature groups collected from diverse domains or information channels. Multi-view learning, which attempts to exploit the relationship am-ong multiple views to improve learning performance, has drawn extensive attention. It is noteworthy that i ..."
Abstract
- Add to MetaCart
(Show Context)
Complex media objects are often described by multi-view feature groups collected from diverse domains or information channels. Multi-view learning, which attempts to exploit the relationship am-ong multiple views to improve learning performance, has drawn extensive attention. It is noteworthy that in some real-world appli-cations, features of different views may come from different pri-vate data repositories, and thus, it is desired to exploit view re-lationship with data privacy preserved simultaneously. Existing multi-view learning approaches such as subspace methods and pre-fusion methods are not applicable in this scenario because they need to access the whole features, whereas late-fusion approaches could not exploit information from other views to improve the in-dividual view-specific learners. In this paper, we propose a novel multi-view learning framework which works in a hybrid fusion manner. Specifically, we convert predicted values of each view into an Accumulated Prediction Matrix (APM) with low-rank con-straint enforced jointly by the multiple views. The joint low-rank constraint enables the view-specific learner to exploit other views to help improve the performance, without accessing the features of other views. Thus, the proposed RANC framework provides a privacy-preserving way for multi-view learning. Furthermore, we consider variants of solutions to achieve rank consistency and present corresponding methods for the optimization. Empirical in-vestigations on real datasets show that the proposed method achiev-es state-of-the-art performance on various tasks.
IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Discriminative Shared Gaussian Processes for Multi-view and View-invariant Facial Expression Recognition
"... Abstract—Images of facial expressions are often captured from various views as a result of either head movements or variable camera position. Existing methods for multi-view and/or view-invariant facial expression recognition typically perform classification of the observed expression by using eithe ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Images of facial expressions are often captured from various views as a result of either head movements or variable camera position. Existing methods for multi-view and/or view-invariant facial expression recognition typically perform classification of the observed expression by using either classifiers learned separately for each view or a single classifier learned for all views. However, these approaches ignore the fact that different views of a facial expression are just different manifestations of the same facial expression. By accounting for this redundancy, we can design more effective classifiers for the target task. To this end, we propose a Discriminative Shared Gaussian Process Latent Variable Model (DS-GPLVM) for multi-view and view-invariant classification of facial expressions from multiple views. In this model, we first learn a discriminative manifold shared by multiple views of a facial expression. Subsequently, we perform facial expression classification in the expression manifold. Finally, classification of an observed facial expression is carried out either in the view-invariant manner (using only a single view of the expression) or in the multi-view manner (using multiple views of the expression). The proposed model can also be used to perform fusion of different facial features in a principled manner. We validate the proposed DS-GPLVM on both posed and spontaneously displayed facial expressions from three publicly available datasets (MultiPIE, LFPW, and SFEW). We show that this model outperforms the state-of-the-art methods for multi-view and view-invariant facial expression classification, and several state-of-the-art methods for multi-view learning and feature fusion. Index Terms—view-invariant, multi-view learning, facial ex-pression recognition, Gaussian Processes. I.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. 1 Learning Prototype Hyperplanes for Face Verification in the
"... Abstract—In this paper, we propose a new scheme called Prototype Hyperplane Learning (PHL) for face verification in the wild using only weakly labeled training samples (i.e., we only know whether each pair of samples are from the same class or different classes without knowing the class label of eac ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—In this paper, we propose a new scheme called Prototype Hyperplane Learning (PHL) for face verification in the wild using only weakly labeled training samples (i.e., we only know whether each pair of samples are from the same class or different classes without knowing the class label of each sample) by leveraging a large number of unlabeled samples in a generic data set. Our scheme represents each sample in the weakly labeled data set as a mid-level feature with each entry as the corresponding decision value from the classification hyperplane (referred to as the prototype hyperplane) of one Support Vector Machine (SVM) model, in which a sparse set of support vectors are selected from the unlabeled generic data set based on the learnt combination coefficients. To learn the optimal prototype hyperplanes for the extraction of mid-level features, we propose a Fisher’s Linear Discriminant-like (FLD-like) objective function by maximizing the discriminability on the weakly labeled data set with a constraint enforcing sparsity on the combination coefficients of each SVM model, which is solved by using an alternating optimization method. Then, we use the recent work called Side-Information based Linear Discriminant Analysis (SILD) for dimensionality reduction and a cosine similarity measure for final face verification. Comprehensive experiments on two data sets, Labeled Faces in the Wild (LFW) and YouTube Faces, demonstrate the effectiveness of our scheme.
Discriminative Prior Bias Learning for Pattern Classification
"... Abstract: Prior information has been effectively exploited mainly using probabilistic models. In this paper, by focus-ing on the bias embedded in the classifier, we propose a novel method to discriminatively learn the prior bias based on the extra prior information assigned to the samples other than ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract: Prior information has been effectively exploited mainly using probabilistic models. In this paper, by focus-ing on the bias embedded in the classifier, we propose a novel method to discriminatively learn the prior bias based on the extra prior information assigned to the samples other than the class category, e.g., the 2-D position where the local image feature is extracted. The proposed method is formulated in the framework of maximum margin to adaptively optimize the biases, improving the classification performance. We also present the computationally efficient optimization approach that makes the method even faster than the standard SVM of the same size. The experimental results on patch labeling in the on-board camera images demonstrate the favorable performance of the proposed method in terms of both classification accuracy and computation time. 1
Learning from Synthetic Data Using a Stacked Multichannel Autoencoder
"... Abstract—Learning from synthetic data has many important and practical applications, An example of application is photo-sketch recognition. Using synthetic data is challenging due to the differences in feature distributions between synthetic and real data, a phenomenon we term synthetic gap. In this ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Learning from synthetic data has many important and practical applications, An example of application is photo-sketch recognition. Using synthetic data is challenging due to the differences in feature distributions between synthetic and real data, a phenomenon we term synthetic gap. In this paper, we investigate and formalize a general framework – Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently. In particular, we show that our SMCAE can not only transform and use synthetic data on the challenging face-sketch recognition task, but that it can also help simulate real images, which can be used for training classifiers for recognition. Preliminary experiments validate the effectiveness of the framework. I.
Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence A Tree-Based Tabu Search Algorithm for the Manpower Allocation Problem with Time Windows and Job-Teaming Constraints
"... This paper investigates the manpower allocation problem with time windows and job-teaming constraints (MAPTWTC), a practical scheduling and routing problem that tries to synchronize workers’ schedules to complete all tasks. We first provide an integer programming model for the problem and discuss it ..."
Abstract
- Add to MetaCart
This paper investigates the manpower allocation problem with time windows and job-teaming constraints (MAPTWTC), a practical scheduling and routing problem that tries to synchronize workers’ schedules to complete all tasks. We first provide an integer programming model for the problem and discuss its properties. Next, we show that tree data structure can be used to represent the MAPTWTC solutions, and its optimal solution can be obtained from one of trees by solving a minimum cost flow model for each worker type. Consequently, we develop for the problem a novel tabu search algorithm employing search operators based on the tree data structure. Finally, we prove the effectiveness of the tabu search algorithm by computational experiments on two sets of instances. 1
