Star Shape Prior for Graph-Cut Image Segmentation

By Olga Veksler. 2008

346 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Extreme Clicking for Efficient Object Annotation (2017, methodology): “To reduce annotation time many interactive segmentation techniques have been proposed, which require the user to input either a bounding box around the object [42, 51, 71], or scribbles [3, 16, 24, 26, 27, 42, 50, 64, 65, 72], or clicks [31, 69].”
DeeperLab: Single-Shot Image Parser (2019, methodology): “4d, we adopt the star graph [99], where the mass center is bi-directionally connected to the other four box corners.”
Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision (2014, methodology): “Unlike [13, 30], we automatically obtain the stars via K-means on the set of foreground seeds F .”
Geodesic star convexity for interactive image segmentation (2010, methodology): “Note that we still obtain globally optimal solutions while breaking free from Veksler's limitations. p q c Figure 2 .”
TouchCut: Fast image and video segmentation using single-touch interaction (2014, background): “6 on both a qualitative and quantitative basis, concluding in Sec.”
Automatic salient object segmentation based on context and shape prior (2011, background): “And Veksler [25] presented the star prior with the assumption that the center of an object is known.”
A survey of graph theoretical approaches to image segmentation (2013, background): “7 shows segmentation examples by Das et al. [79] and Veksler’s methods [80], respectively.”
Regional Interactive Image Segmentation Networks (2017, neutral): “To further improve the performance, shape priors such as [9, 25, 7, 12] have been considered in the literature.”
Learning Models for Object Recognition from Natural Language Descriptions (2009, methodology): “We use the ‘star shape’ graph-cut approach proposed by Veksler [21].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, methodology): “To reduce annotation time many interactive segmentation techniques have been proposed, which require the user to input either a bounding box around the object [42, 51, 71], or scribbles [3, 16, 24, 26, 27, 42, 50, 64, 65, 72], or clicks [31, 69].”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, background): “The popularity of semantic parsing since early 2000s is deeply rooted in the success of some speciﬁc computer vision tasks such as face/object detection and tracking, camera pose estimation, multiple view 3D reconstruction and fast conditional random ﬁeld solvers.”
Multiple Granularity Descriptors for Fine-Grained Categorization (2015, background): “Its principle is to fully utilize star-convexity as shape cues[33].”