Wei Sun

TL;DR: Three categories of methods are reviewed and compared, including those based on hand-engineered features, learned features and weakly supervised learning, and a number of popular datasets aiming for facilitating the development of new segmentation algorithms.

TL;DR: The experiments show that compared with the original reference fingerprints localization system, the proposed localization system explicitly reduces the localization error and can augment the fingerprints and improve the accuracy of fingerprint-based indoor localization without extra manual calibration or adding dedicated infrastructure.

TL;DR: The proposed PD2SE-Net50 consists of the ResNet50 architecture as the basic model and shuffle units as the auxiliary structures, and it achieves excellent comprehensive performances over the existing approaches.

TL;DR: The proposed Separable-Unet framework takes advantage of the separable convolutional block and U-Net architectures to enhance the pixel-level discriminative representation capability of fully Convolutional networks (FCN).

TL;DR: The comparison results on the CEC2017 test suite show that the adoption of the ring topology in exemplar generation can enhance the diversity and exploration capability of GL-PSO, while combining GLC alone with GL- PSO cannot achieve significant improvement.