Deep Crisp Boundaries: From Boundaries to Higher-Level Tasks

Deep Crisp Boundaries: From Boundaries to Higher-level Tasks

Edge detection has made significant progress with the help of deep Convolutional Networks (ConvNet). ConvNet based edge detectors approached human level performance on standard benchmarks. We provide a systematical study of these detector outputs, and show that they failed to accurately localize edges, which can be adversarial for tasks that require crisp edge inputs. In addition, we propose a ...

Determining Motion Boundaries From Image Boundaries Using Deep Descriptor Matching

Finding Text Boundaries and Finding Topic Boundaries: Two Different Tasks?

The goal of this paper is to demonstrate that usual evaluation methods for text segmentation are not adapted for every task linked to text segmentation. To do so we differentiated the task of finding text boundaries in a corpus of concatenated texts from the task of finding transitions between topics inside the same text. We worked on a corpus of twenty two French political discourses trying to...

From boundaries to conditions over superspace

N = 1 and 2 superconformal boundary conditions are shown to be the consequence of a “boundary” on the worldsheet superspace with positive codimension in the anticommuting subspace. In addition to the well-known boundary conditions, I also find two new infinite series of N = 2 boundary states. Their free field realizations are given. A self-contained development of 2d superspace leads to new per...

Multi-Level Logic Minimization Across Latch Boundaries