A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials
Attributed to:
Seebibyte: Visual Search for the Era of Big Data
funded by
EPSRC
Abstract
No abstract provided
Bibliographic Information
Digital Object Identifier: http://dx.doi.org/10.1007/978-3-319-78199-0_37
Publication URI: http://dx.doi.org/10.1007/978-3-319-78199-0_37
Type: Book Chapter
Book Title: Energy Minimization Methods in Computer Vision and Pattern Recognition (2018)
Page Reference: 564-579