Bypassing synthesis: PLS for face recognition with pose, low-resolution and sketch

By Abhishek Sharma, David W. Jacobs. Computer Vision and Pattern Recognition, 2011

396 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a3d7613971e52165f1693a972c11c54bb0bc085b

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

Citations in the corpus

Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation (2014, methodology): “Compared Methods: To evaluate the performance of the proposed algorithm, several famous algorithms in the cross-media retrieval field were compared in the experiments, including the popular methods CCA [15, 29] and PLS [30, 31], and the state-of-the-art methods SCM [29], the Microsoft algorithm…”
A Comprehensive Survey on Pose-Invariant Face Recognition (2015, methodology): “It is clear that PLS tries to correlate the samples of the same subject as well as capture the variations present in the original data, which helps to enhance the ability to differentiate the training samples of different subjects in the shared subspace Sharma and Jacobs (2011). Therefore, better pe”
Learning Compact Binary Face Descriptor for Face Recognition (2015, neutral): “7 PLS [49] 17.”
Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis (2012, methodology): “Various cross-style image synthesis problems, such as image analogies [11], texture synthesis [8, 16], and multimodal face recognition [26, 13, 22], have been proposed and studied.”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “data modalities (textual, visual, audio), such as in the case of parallel texts in different languages [236, 79], photos of the same person taken across different poses, illuminations and expressions [261, 195, 196, 170]. In classical multi-view learning it is assumed that during training there are ”
Visual Domain Adaptation: A survey of recent advances (2015, background): “Tu ■ In multisource domain adaptation, (.) f is learned from more than one domain in S accompanying each of the first two cases.”
Scalable Deep Multimodal Learning for Cross-Modal Retrieval (2019, methodology): “One typical kind of methods attempts to project the multimodal data into a latent common subspace by maximizing the correlation between different modalities, such as Canonical Correlation Analysis (CCA) [7], Partial Least Squares (PLS) [34], and Multi-set CCA (MCCA) [22, 33].”
Generalized Domain-Adaptive Dictionaries (2013, neutral): “7 PLS [22] 39.”
Multi-Layer domain adaptation method for rolling bearing fault diagnosis (2019, background): “In the recent years, domain adaptation methods have been successfully developed and applied in many practical tasks such as sentiment analysis [28], object recognition in different situations [29, 30], facial recognition [31], speech recognition [32], video recognition [33] etc.”
Learning Coupled Feature Spaces for Cross-Modal Matching (2013, methodology): “Previous methods mainly focus on the first problem, such as CCA or PLS.”
Learning Consistent Feature Representation for Cross-Modal Multimedia Retrieval (2015, methodology): “Beyond CCA, PLS [31], [32] is another classical method.”
Generalized Multiview Analysis: A discriminative latent space (2012, methodology): “This leads to a closed form solution and better preserves the between class variation as argued in [18]”
Frontal to profile face verification in the wild (2016, methodology): “These methods mostly use Canonical Correlation Analysis (CCA) [14] or Partial Least Square (PLS) [29].”
Efficient Pose-Based Action Recognition (2014, background): “The weights w can be learned by partial least squares (PLS) [24], which has been recently adopted in computer vision for different applications including pose estimation and regression [25], image classification [26], pedestrian detection [27], and multiview learning [28].”
Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding (2015, methodology): “In this subsection, we use theWiki Text-Image data set to illustrate the effectiveness of EMR-SLRA algorithm in comparing with its competitors including the traditional multiview methods CCA, PLS and BLM. Table 1 shows the number of training and test samples of each category in the Wiki Text-Image d”
A Comprehensive Survey on Cross-modal Retrieval (2016, positive): “Sharma and Jacobs [88] use PLS to linearly map images with different modalities to a common linear subspace in which they are highly correlated.”