Generalized Multiview Analysis: A discriminative latent space

By Abhishek Sharma, Abhishek Kumar, Hal Daumé Iii, David W. Jacobs. 2012

745 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Multimodal Learning

In Representation & Self-Supervised Learning

Citations in the corpus

Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “68 GMMFA [32] 38.”
Achieving Human Parity on Visual Question Answering (2021, background): “[66] extend CCA to a supervised version by leveraging the the semantic category labels to guide the representation learning.”
A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics (2012, methodology): “The literature contains a number of sophisticated methods for multi-view learning, including generalizations of CCA/KCCA (Rai and Daumé, 2009; Sharma et al., 2012; Yakhnenko and Honavar, 2009), metric learning (Quadrianto and Lampert, 2011) and large-margin formulations (Chen et al., 2012).”
A Survey on Multi-view Learning (2013, background): “ directed by the label information (Yu et al., 2006). However, this algorithm does not actually use the multiple views of the data; it is just a single view approach along with the label information. Sharma et al. (2012) proposed a 34 A SurveyonMulti-view Learning Generalized Multi-view Analysis (GM”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “earn the task for the target. These methods are related, on one hand, to the feature transformation based homogeneous DA methods described in Section 3.1 and, on another hand, to multi-view embedding [93, 110, 99, 111, 112, 113], where different views are embedded in a common latent space. Therefore”
Optimal Transport for Domain Adaptation (2014, methodology): “resentations in which domains match in some sense. For instance, adaptation can be performed by matching the means of the domains in the feature space [38], aligning the domains by their correlations [33] or by using pairwise constraints [51]. In most of these works, feature extraction is the key to”
A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “For the real-valued representation learning methods, we choose three popular unsupervised methods (i.e., PLS [14], BLM [15], [16] and CCA [13]), two rank based methods (i.e., LSCMR [37], and Bi-LSCMR [38]) and eight popular supervised methods (i.e., CDFE [45], GMLDA [15], GMMFA [15], CCA-3V [51],…”
Cross-Modal Retrieval With CNN Visual Features: A New Baseline (2017, methodology): “Recently, based on CCA, many extensions [5], [13], [38], [39], [42], [56] are applied to crossmodal retrieval.”
Learning Compact Binary Face Descriptor for Face Recognition (2015, neutral): “7 GMLDA [50] 23.”
Learning of Multimodal Representations With Random Walks on the Click Graph (2016, background): “, Deep CCA [6] and Generalize Multiview Analysis [16]) learn the (non)linear transformation that projects the query textual semantics and image content into the common subspace respectively, by maximizing the correlations between the two variables in the latent space.”
Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval (2016, methodology): “The scope (i.e., the top K TABLE 1 MAP Comparison of Different Methods on the Pascal VOC Dataset Methods Image query Text query Average PCA+PLS 0.2757 0.1997 0.2377 PCA+BLM 0.2667 0.2408 0.2538 PCA+CCA 0.2655 0.2215 0.2435 PCA+CDFE 0.2928 0.2211 0.2569 PCA+GMMFA 0.3090 0.2308 0.2699 GMMFA 0.2253 0.1”
Deep Supervised Cross-Modal Retrieval (2019, methodology): “This category includes unsupervised approaches [2, 5, 33], pairwise approaches [38, 39, 31] and supervised approaches [32, 28].”
RGB-Infrared Cross-Modality Person Re-identification (2017, methodology): “Metric learning methods included KISSME [15], LFDA [34] and cross-domain models CCA [35], CDFE [25], GMA [37], SCM [51] and CRAFT [3].”
Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization (2014, background): “How to leverage such multimodal data to conduct cross-view similarity search (Rasiwasia et al. 2010; Hwang and Grauman 2012; Sharma et al. 2012; Gong et al. 2014) has become a challenging but interesting research problem.”
Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation (2014, methodology): “Since some of the images are multi labeled, the images containing only one object were selected in the experiments (Sharma et al. 2012).”