Submitted to Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Multiscale Centerline Detection

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

EDTER: Edge Detection with Transformer (2022, neutral): “DeepEdge [3] CVPR’15 0.753 0.772 0.807 CSCNN [24] ArXiv’15 0.756 0.775 0.798 MSC [51] PAMI’15 0.756 0.776 0.787 DeepContour [48] CVPR’15 0.757 0.776 0.800 HFL [4] ICCV’15 0.767 0.788 0.795 HED [65] ICCV’15 0.788 0.808 0.840 Deep Boundary [29] ICLR’15 0.813 0.831 0.866 CEDN [67] CVPR’16 0.788 0.804…”
Pushing the Boundaries of Boundary Detection using Deep Learning (2015, background): “This problem has already been acknowledged in the literature; for instance Sironi et al. (2015) turn boundary detection into a regression problem, by explicitly manipulating the ground truth to become smoother - which however may come at the cost of localization accuracy.”
Projection onto the Manifold of Elongated Structures for Accurate Extraction (2015, methodology): “Classification-based ones [17, 47, 7, 46] have been successfully applied to the segmentation of thick linear structures while, regression-based ones [39, 40] have been shown to be particularly effective at finding centerline pixels only.”
Deep Crisp Boundaries (2017, unknown): “784 MSC [35] .”