Factorized Latent Spaces with Structured Sparsity
By Yangqing Jia, Mathieu Salzmann, Trevor Darrell. 2010
206 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “[21] factorized the input features to shared and private components by applying structured sparsity, for the task of multi-view learning on human pose estimation, with linearity assumption.”
- Domain Separation Networks (2016, background): “Our main novelty is that, inspired by recent work [14, 24, 30] on shared-space component analysis, DSNs explicitly model both private and shared components of the domain representations.”
- A Survey on Multi-view Learning (2013, methodology): “Salzmann et al. (2010) and Jia et al. (2010) proposed to find a latent subspace in which the information is correctly factorized into shared and private parts across different views.”
- Latent Multi-Task Architecture Learning (2017, background): “entity recognition, should be supervised at lower layers when used as auxiliary tasks. Another line of work looks into separating the learned space into a private (i.e. task-specific) and shared space [31, 24, 27] to more explicitly capture the difference between task-specific and cross-task features.”
- Sluice networks: Learning what to share between loosely related tasks (2017, methodology): “Inspired by recent work on shared-space component analysis [31, 24], we add a penalty to enforce a division of labor and discourage redundancy between shared and task-specific subspaces.”
- Bayesian group factor analysis with structured sparsity (2016, methodology): “The structure on Λ in Equation (8) has been relaxed to model covariance among subsets of the observations (Jia et al., 2010; Virtanen et al., 2012; Klami et al., 2014b).”
- Adversarial Multi-task Learning for Text Classification (2017, background): “Motivated by recently work(Jia et al., 2010; Salzmann et al., 2010; Bousmalis et al., 2016) on shared-private latent space analysis, we introduce orthogonality constraints, which penalize redundant latent representations and encourages the shared and private extractors to encode different aspects…”
- Bayesian Canonical correlation analysis (2013, methodology): “Klami and Kaski (2007) introduced an infinite mixture of Bayesian CCA models, accompanied with a Gibbs sampling scheme.”
- Feature Selection Based on Structured Sparsity: A Comprehensive Study (2017, background): “Other applications of l∞,1 regularization are simultaneous sparse signal approximation [74], [75], structure learning [77], multiview learning [78], and multitask learning [79].”
- Multi-View Intact Space Learning (2015, methodology): “The proposed MISL algorithm and its kernel extension KMISL were compared with convex Multi-view Subspace Learning algorithm (MSL) [52], Factorized Latent Spaces with Structured Sparsity algorithm (FLSSS) [36], and shared Gaussian Latent Variable Model (sGPLVM) [33].”
- A Survey of Multi-View Representation Learning (2016, unknown): “consistency and complementarity of different views simultaneously, such as multi-modal topic learning [11], multi-view sparse coding [12], multi-view latent space Markov networks [15, 16], and multi-modal deep Boltzmann machines [17].”
- Learning Multiple Views with Orthogonal Denoising Autoencoders (2016, methodology): “Multi-view feature learning was first analyized from the perspective of representation learning through sparse coding in [8], but little work has employed representation learning for studying multi-view data so far, thus far only sparse coding has been used [5,22].”
- Supervised Coupled Dictionary Learning with Group Structures for Multi-modal Retrieval (2013, background): “A dictionary learning approach is proposed in (Jia, Salzmann, and Darrell 2010) to factorize the latent space across modalities into shared components (to all modalities) and private parts (to each modality).”
- Robust and Discriminative Self-Taught Learning (2013, methodology): “In this paper, motivated by (Bradley & Bagnell, 2009; Jia et al., 2010) we present a principled method to seek the optimal dictionary basis vectors .”
- Beyond spatial pyramids: Receptive field learning for pooled image features (2012, methodology): “To this end, we adopt the idea of structured sparsity [12], and train a multiple-class linear classifier y = f(x) = Wx+b via the following optimization problem:”