Search Results for author:
Found 3 papers, 1 papers with code
BARS: A Benchmark for Airport Runway Segmentation
BARS has the largest dataset with the richest categories and the only instance annotation in the field.
Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs
Object skeleton is a useful cue for object detection, complementary to the object contour, as it provides a structural representation to describe the relationship among object parts.
DeepContour: A Deep Convolutional Feature Learned by Positive-Sharing Loss for Contour Detection
Contour detection serves as the basis of a variety of computer vision tasks such as image segmentation and object recognition.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
