Robust and Discriminative Self-Taught Learning

55 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.

Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “While learning frameworks in [67, 68, 69, 70] applied structured sparsity for other similar tasks, our structured sparsity learning machine extends the sparse selection into two levels of concurrent component and layer selection, which is more suited to the hierarchical outputs from our deep factori”
Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “[31] proposed a robust self-taught learning using mixed norms and [32] utilized a fractional mixed norm for robust adaptive dictionary learning.”
Semi-supervised Robust Dictionary Learning via Efficient l-Norms Minimization (2013, background): “Recently, the advances in sparse coding have shown that linearly decomposing a signal using a few atoms of a learned dictionary instead of a predefined one usually leads to state-ofthe-art performance for a number of practical computer vision applications [7, 13, 10, 15].”
Score Function Features for Discriminative Learning: Matrix and Tensor Framework (2014, background): “Previous solutions have prescribed joint training discriminative features using labeled samples, in conjunction with unlabeled samples (Mairal et al., 2009; Maaten, 2011; Wang et al., 2013).”