Generalized Multiview Analysis: A discriminative latent space

Sharma, Abhishek; Kumar, Abhishek; Daumé, Hal; Jacobs, David W.

doi:10.1109/cvpr.2012.6247923

Cited by 599 publications

(395 citation statements)

References 19 publications

Supporting

Mentioning

385

Contrasting

Unclassified

Order By: Relevance

“…CCA has been used frequently in unsupervised data analysis (Sargin et al, 2006;Chaudhuri et al, 2009;Kumar and Daumé, 2011;Sharma et al, 2012). Deep Canonical Correlation Analysis (DCCA) DCCA aims to lean highly correlated deep architectures, which can be a non-linear extension of CCA .…”

Section: Mue Feature Learning Methodsmentioning

confidence: 99%

Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction

Ding¹,

Bickel²,

Pan³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

In this paper, we demonstrate how the state-of-the-art machine learning and text mining techniques can be used to build effective social media-based substance use detection systems. Since a substance use ground truth is difficult to obtain on a large scale, to maximize system performance, we explore different unsupervised feature learning methods to take advantage of a large amount of unsupervised social media data. We also demonstrate the benefit of using multi-view unsupervised feature learning to combine heterogeneous user information such as Facebook "likes" and "status updates" to enhance system performance. Based on our evaluation, our best models achieved 86% AUC for predicting tobacco use, 81% for alcohol use and 84% for illicit drug use, all of which significantly outperformed existing methods. Our investigation has also uncovered interesting relations between a user's social media behavior (e.g., word usage) and substance use.

show abstract

Section: Mue Feature Learning Methodsmentioning

confidence: 99%

Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction

Ding¹,

Bickel²,

Pan³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…In order to validate the contributions of each separate component, three approaches correlation matching (CM), semantic matching (SM) and semantic correlations matching are proposed for the correlation modeling, the abstraction method and the joint working mode of both approaches respectively. Sharma et al [36] proposed Generalized Multiview Analysis (GMA) to extract features from different views. GMA solves a joint, relaxed quadratic constrained quadratic program (QCQP) over different feature spaces to obtain a single linear/non-linear subspace, thus it affords an efficient eigenvalue based solution, and it is applicable to be extended to the cross-modality scenario.…”

Section: Related Workmentioning

confidence: 99%

Cross-Modality Submodular Dictionary Learning for Information Retrieval

Zhu

Shao

2014

Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management

View full text Add to dashboard Cite

This paper addresses the problem of joint modeling of multimedia components in different media forms. We consider the information retrieval task across both text and image documents, which includes retrieving relevant images that closely match the description in a text query and retrieving text documents that best explain the content of an image query. A greedy dictionary construction approach is introduced for learning an isomorphic feature space, to which cross-modality data can be adapted while data smoothness is guaranteed. The proposed objective function consists of two reconstruction error terms for both modalities and a Maximum Mean Discrepancy (MMD) term that measures the cross-modality discrepancy. Optimization of the reconstruction terms and the MMD term yields a compact and modalityadaptive dictionary pair. We formulate the joint combinatorial optimization problem by maximizing variance reduction over a candidate signal set while constraining the dictionary size and coefficients' sparsity. By exploiting the submodularity and the monotonicity property of the proposed objective function, the optimization problem can be solved by a highly efficient greedy algorithm, and is guaranteed to be at least a (e − 1)/e ≈ 0.632-approximation to the optimum. The proposed method achieves state-of-the-art performance on the Wikipedia dataset.

show abstract

“…Similarly, we apply 1-NN classifier to the subspace obtained by LDA [25], supervised LPP [26], D-GPLVM [20] and GPLRF [27]. We also compared VC-GPM to several stateof-the-art methods for multi-view learning, namely, the Multi-view Discriminant Analysis (mvDA) [28], and methods for Generalized Multiview Analysis (GMA) [29], namely, GM Linear Discriminant Analysis (GMLDA) and GM Locality Preserving Projections (GMLPP), which extend the LDA and LPP [30] to multiple views. Lastly, we also include the results obtained by DS-GPLVM [15], with the GP kernel parameters and the discriminative prior as in our VC-GPM.…”

Section: Datasets and Experimental Proceduresmentioning

confidence: 99%

View-Constrained Latent Variable Model for Multi-view Facial Expression Classification

Eleftheriadis

Rudovic

Pantić

2014

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. We propose a view-constrained latent variable model for multi-view facial expression classification. In this model, we first learn a discriminative manifold shared by multiple views of facial expressions, followed by the expression classification in the shared manifold. For learning, we use the expression data from multiple views, however, the inference is performed using the data from a single view. Our experiments on data of posed and spontaneously displayed facial expressions show that the proposed approach outperforms the state-of-the-art methods for multi-view facial expression classification, and several state-of-theart methods for multi-view learning.

show abstract

Generalized Multiview Analysis: A discriminative latent space

Cited by 599 publications

References 19 publications

Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction

Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction

Cross-Modality Submodular Dictionary Learning for Information Retrieval

View-Constrained Latent Variable Model for Multi-view Facial Expression Classification

Contact Info

Product

Resources

About