David Zhang

TL;DR: Wang et al. as mentioned in this paper developed a trilateral weighted sparse coding (TWSC) scheme for robust real-world image denoising by introducing three weight matrices into the data and regularization terms of the sparse coding framework to characterize the statistics of realistic noise and image priors.

TL;DR: In this paper, the authors investigated the use of nonnegative representation (NR) for pattern classification, which is largely ignored by previous work, and showed that NR can boost the representation power of homogeneous samples while limiting the represent power of heterogeneous samples, making the representation sparse and discriminative simultaneously and thus providing a more effective solution to representation based classification than SR/CR.

TL;DR: This paper develops a trilateral weighted sparse coding (TWSC) scheme for robust real-world image denoising and introduces three weight matrices into the data and regularization terms of the sparse coding framework to characterize the statistics of realistic noise and image priors.

TL;DR: This paper proposes a novel asymmetric supervised deep hashing method to preserve the semantic structure among different categories and generate the binary codes simultaneously, taking advantage of the two-stream deep structures and two types of asymmetric pairwise functions.

TL;DR: In this paper, two asymmetric deep networks are constructed to reveal the similarity between each pair of images according to their semantic labels, and another asymmetric pairwise loss is introduced to capture the similarities between the binary codes and real-value features.