Publications by authors named "Wang-Meng Zuo"

Article Synopsis
  • - The text discusses cervical nucleus segmentation, which is important for automatic disease diagnosis but is complicated by issues like uneven staining and overlapping nuclei.
  • - A new multi-task network based on U-Net is proposed, combining a primary task for predicting nuclei regions and an auxiliary task for predicting their boundaries to enhance feature extraction.
  • - The network includes context encoding layers and an attention learning module, resulting in better performance compared to existing methods on multiple datasets, including ISBI 2014 and MoNuSeg.
View Article and Find Full Text PDF

Raindrops adhered to a glass window or camera lens appear in various blurring degrees and resolutions due to the difference in the degrees of raindrops aggregation. The removal of raindrops from a rainy image remains a challenging task because of the density and diversity of raindrops. The abundant location and blur level information are strong prior guide to the task of raindrop removal.

View Article and Find Full Text PDF