Heterogeneous Visual Features Fusion via Sparse Multimodal Machine

87 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): “Hence we adopt the structured sparsity regularization method of [68, 70] aiming to select a number of components/layers sparsely to achieve more robust classification.”
Feature Selection Based on Structured Sparsity: A Comprehensive Study (2017, methodology): “bc] is the bias vector, and group l1-norm (G1-norm) is defined in [123] and [125].”
Multi-View Clustering and Feature Learning via Structured Sparsity (2013, methodology): “To address this, we use group ℓ1norm (G1-norm) for regularization, which is defined as ∥W∥G1 = c∑ i=1 k∑ j=1 ||wji ||2 (Wang et al., 2012b; 2013) and illustrated in Figure 1.”