Tiep H. Vu

TL;DR: This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.

TL;DR: This work designs a deep CNN to predict the "missing details" of wavelet coefficients of the low-resolution images to obtain the Super-Resolution (SR) results, which it shows is computationally simpler and yet produces competitive and often better results than state-of-the-art alternatives.

TL;DR: A novel method to explicitly and simultaneously learn a set of common patterns as well as class-specific features for classification with more intuitive constraints, characterized by both a shared dictionary and particular (class-specific) dictionaries.

TL;DR: It is demonstrated that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available.

TL;DR: In this paper, a discriminative feature-oriented dictionary learning (DFDL) method is proposed to learn class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample.