The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects

By John M. Winn, Jamie Shotton. 2006

320 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

Pixelwise Instance Segmentation with a Dynamically Instantiated Network (2017, methodology): “An early work on instance segmentation was by Winn and Shotton [44].”
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (2015, background): “As in [47, 20], modeling asymmetric relations requires the potential function is capable of modeling input orders, since we have: V ( y p , y q , x pq ) (cid:54) = V ( y q , y p , x qp ) .”
Class-specific Hough forests for object detection (2009, methodology): “Random forests have recently attracted a lot of attention in computer vision [6, 12, 20, 25, 27].”
Decomposing a scene into geometric and semantically consistent regions (2009, background): “The problem of multi-class image segmentation (or labeling) has been successfully addressed by a number of works [7] [22] [17] [23] [24] [5].”
Image Classification using Random Forests and Ferns (2007, background): “The advantage of randomized trees, as has been noted by previous authors [25], is that they are much faster in training and testing than traditional classifiers (such as an SVM).”
Spacetime Forests with Complementary Features for Dynamic Scene Recognition (2013, unknown): “, [4, 19, 23, 36].”
A Dynamic Conditional Random Field Model for Joint Labeling of Object and Scene Classes (2008, methodology): “Furthermore, we use different sets of weights for different parts of the detected object enforcing an object and context consistent layout [15].”
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images (2013, methodology): “Sharing a similar spirit to our work, the LayoutCRF [12, 35] defines a coarse grid of classification labels that roughly cover an object, and then exploits layout consistency terms in an MRF optimization framework to segment the objects.”
Global stereo reconstruction under second order smoothness priors (2008, unknown): “[46].”
Superpixel lattices (2008, background): “Image parsing algorithms [19, 7, 20] combine segmentation, detection and recognition to attempt to resolve these ambiguities.”
Augmenting deformable part models with irregular-shaped object patches (2012, methodology): “LayoutCRF [24] addresses the problem of detecting and segmenting partially occluded objects using CRFs.”
Relating Things and Stuff via ObjectProperty Interactions (2014, background): “For instance, many segmentation methods [13], [20], [21] have been proposed to capture stuff-stuff relationships in a random field formulation.”
Layered object detection for multi-class segmentation (2010, background): “One approach of capturing rough depth ordering is to estimate occlusion boundaries, typically done in a Markov Random Field framework [26, 8, 9].”
Efficient Human Pose Estimation from Single Depth Images (2013, background): “BPC, originally published in [14], was inspired by recent object recognition work that divides objects into parts (e.g., [15], [16], [17], [5]).”
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context (2007, methodology): “This kind of problem may be ameliorated using a parts-based modeling approach, such as Winn and Shotton (2006).”