Boundary Detection Using F-Measure-, Filter- and Feature- (F3) Boost

By Iasonas Kokkinos. 2010

42 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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

1. Luc Van Gool
2. Jitendra Malik
3. Trevor Darrell
4. Xiaogang Wang
5. Ming-Hsuan Yang
6. Dacheng Tao
7. Bernt Schiele
8. Andrew Zisserman

In Evaluation & Benchmarks

1. Piotr Doll'ar
2. Luc Van Gool
3. Jordi Pont-Tuset
4. C. Lawrence Zitnick
5. Iasonas Kokkinos
6. Cristian Sminchisescu
7. Pablo Arbeláez
8. Kevis-Kokitsi Maninis

Citations in the corpus

• Fast Edge Detection Using Structured Forests (2014, background): “More recent work [34], [32], [28], [1], [48], [30] explores edge detection under more challenging conditions.”
• Pushing the Boundaries of Boundary Detection using Deep Learning (2015, methodology): “We therefore adopt a Mutliple Instance Learning (MIL) approach, as in [5], and associate every ground-truth boundary position j with a set of N j positions and an associated feature ‘bag’, X j = {X j,1, .”
• Generalized Boundaries from Multiple Image Interpretations (2012, background): “gPb cues with boosting and multiple instance learning were shown to further improve performance [16].”
• Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks (2016, methodology): “Kokkinos [28] trains an orientation-sensitive boundary detector using Multiple-Instance Learning.”