Paper Info
Title
Exploiting skeletal structure in computer vision annotation with Benders decomposition.
Abstract
Many annotation problems in computer vision can be phrased as integer linear programs (ILPs). The use of standard industrial solvers does not to exploit the underlying structure of such problems eg, the skeleton in pose estimation. The leveraging of the underlying structure in conjunction with industrial solvers promises increases in both speed and accuracy. Such structure can be exploited using Benderu0027s decomposition, a technique from operations research, that solves complex ILPs or mixed integer linear programs by decomposing them into sub-problems that communicate via a master problem. The intuition is that conditioned on a small subset of the variables the solution to the remaining variables can be computed easily by taking advantage of properties of the ILP constraint matrix such as block structure. In this paper we apply Benders decomposition to a typical problem in computer vision where we have many sub-ILPs (eg, partitioning of detections, body-parts) coupled to a master ILP (eg, constructing skeletons). Dividing inference problems into a master problem and sub-problems motivates the development of a plethora of novel models, and inference approaches for the field of computer vision.
Year
Venue
Field
2017
arXiv: Computer Vision and Pattern Recognition
Integer,Division (mathematics),Computer science,Intuition,Pose,Theoretical computer science,Artificial intelligence,Benders' decomposition,Computer vision,Annotation,Pattern recognition,Inference,Algorithm,Exploit,Machine learning
DocType
Volume
Citations 
Journal
abs/1709.04411
2
PageRank 
References 
Authors
0.39
15
3
Name
Order
Citations
PageRank
Shaofei Wang145.15
Konrad Kording220.39
Julian Yarkony3769.20