Shengrong Gong

TL;DR: The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.

TL;DR: A logistic metric learning method is derived to jointly learn a distance metric and a bilinear similarity metric, which exploits both the distance and angle information from training data and outperforms the state-of-the-art approaches significantly.

TL;DR: In this paper, an unsupervised deep convolutional neural network (CANet) is proposed to cluster all the pixels into different groups according to the input's recognizable pattern of the ambiguity number of the MB interferometric phase.

TL;DR: A large margin relative distance learning (LMRDL) method which learns the metric from triplet constraints, so that the problem of imbalanced sample pairs can be bypassed.

TL;DR: In this article, a behavior recognition method based on sparse spatial-temporal characteristics is proposed, which comprises the steps as follows: step 1, convolving an input video with an original input video by using space-time Gabor to establish a scale space; step 2, using the expressions of different scales as values of different channels of a space time depth belief network.