Generalized Coupled Dictionary Learning Approach with Applications to Cross – Modal Matching. Coupled dictionary learning (CDL) has recently emerged as a powerful technique with wide variety of applications ranging from image synthesis to classification tasks. In this paper, we extend the existing CDL approaches in two aspects to make them more suitable for the task of cross-modal matching. Data coming from different modalities may or may not be paired. 

 

The discriminative coupling term also makes the approach better suited for classification tasks. The discriminative coupling term also makes the approach better suited for classification tasks.

Data coming from different modalities can have very different representations.

In addition, the data can also have large intra-class variability within their modality, making cross-modal matching extremely challenging. 

Several approaches have been proposed in the literature to address this problem.