Showing papers by "Yap-Peng Tan published in 2014"

Discriminative Deep Metric Learning for Face Verification in the Wild

Abstract: This paper presents a new discriminative deep metric learning (DDML) method for face verification in the wild. Different from existing metric learning-based face verification methods which aim to learn a Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, simultaneously, the proposed DDML trains a deep neural network which learns a set of hierarchical nonlinear transformations to project face pairs into the same feature subspace, under which the distance of each positive face pair is less than a smaller threshold and that of each negative pair is higher than a larger threshold, respectively, so that discriminative information can be exploited in the deep network. Our method achieves very competitive face verification performance on the widely used LFW and YouTube Faces (YTF) datasets.

Large Margin Multi-metric Learning for Face and Kinship Verification in the Wild

Abstract: Metric learning has been widely used in face and kinship verification and a number of such algorithms have been proposed over the past decade. However, most existing metric learning methods only learn one Mahalanobis distance metric from a single feature representation for each face image and cannot deal with multiple feature representations directly. In many face verification applications, we have access to extract multiple features for each face image to extract more complementary information, and it is desirable to learn distance metrics from these multiple features so that more discriminative information can be exploited than those learned from individual features. To achieve this, we propose a new large margin multi-metric learning (LM\(^3\)L) method for face and kinship verification in the wild. Our method jointly learns multiple distance metrics under which the correlations of different feature representations of each sample are maximized, and the distance of each positive is less than a low threshold and that of each negative pair is greater than a high threshold, simultaneously. Experimental results show that our method can achieve competitive results compared with the state-of-the-art methods.

Co-Learned Multi-View Spectral Clustering for Face Recognition Based on Image Sets

Abstract: Different from the existing approaches that usually utilize single view information of image sets to recognize persons, multi-view information of image sets is exploited in this paper, where a novel method called Co-Learned Multi-View Spectral Clustering (CMSC) is proposed to recognize faces based on image sets. In order to make sure that a data point under different views is assigned to the same cluster, we propose an objective function that optimizes the approximations of the cluster indicator vectors for each view and meanwhile maximizes the correlations among different views. Instead of using an iterative method, we relax the constraints such that the objective function can be solved immediately. Experiments are conducted to demonstrate the efficiency and accuracy of the proposed CMSC method.

Cost optimal video transcoding in media cloud: Insights from user viewing pattern

Abstract: Video transcoding has been touted as an enabling technology to support growing media consumption over heterogenous devices. However, on-line transcoding could incur tremendous, if not prohibitive, cost in deploying or renting resources. In this research, we leverage an insight into the viewing pattern of video consumers to reduce the operating cost of video transcoding services. Specifically, it has been reported that viewers tend to terminate their session before the whole video is watched. As such, it is not cost-efficient for service providers to store or transcode all segments of the videos. Built upon this insight, we propose a partial transcoding scheme for content management in a media cloud to reduce the operating cost. Particularly, each content is split into multiple segments and stored in different files of varying playback rates. Some of the segments are stored in cache, resulting in storage cost; while some are transcoded in real-time in case of cache miss, resulting in computing cost. We aim to minimize the long-term operational cost by determining the number of segments for each playback rate to be cached or transcoded in real-time. We formulate this partial transcoding scheme as a constrained integer optimization problem. Leveraging Lagrangian relaxation and a subgradient method, we obtain the approximate solution to the integer program. Numerical results indicate that our proposed partial transcoding scheme can save more than 30% of operational cost, compared with a brute-force scheme of caching all the segments.

Complete discriminative feature learning: A new approach for heterogeneous face recognition

Abstract: In this paper, we propose a new feature learning approach called complete discriminative feature learning (CDFL) for heterogeneous face recognition. Unlike most existing heterogeneous face recognition methods where hand-crafted feature descriptors are used for face representation, the proposed CD-FL aims to learn an optimal weighted discriminative image filter to improve learning discriminative filters, so that complete discriminative information is exploited and the feature difference between different modalities is effectively reduced, simultaneously. Experimental results shows that our approach consistently outperforms the state-of-the-art methods.

Efficient Sparsity Estimation via Marginal-Lasso Coding

Abstract: This paper presents a generic optimization framework for efficient feature quantization using sparse coding which can be applied to many computer vision tasks. While there are many works working on sparse coding and dictionary learning, none of them has exploited the advantages of the marginal regression and the lasso simultaneously to provide more efficient and effective solutions. In our work, we provide such an approach with a theoretical support. Therefore, the computational complexity of the proposed method can be two orders faster than that of the lasso with sacrificing the inevitable quantization error. On the other hand, the proposed method is more robust than the conventional marginal regression based methods. We also provide an adaptive regularization parameter selection scheme and a dictionary learning method incorporated with the proposed sparsity estimation algorithm. Experimental results and detailed model analysis are presented to demonstrate the efficacy of our proposed methods.