Inference methods for CRFs with co-occurrence statistics

DOI10.1007/S11263-012-0583-YMaRDI QIDQ362141zbMATH OpenOpenAlexFDO

Authors L'ubor Ladický, Chris Russell, Pushmeet Kohli, Philip H. S. Torr

Publication date 20 August 2013

Published in International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11263-012-0583-y

zbMATH Keywords

optimizationconditional random fieldsobject class segmentation

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Machine vision and scene understanding (68T45)

Recommendations

• Conditional random fields for image labeling
• Global interactions in random field models: a potential function ensuring connectedness
• An introduction to conditional random fields
• Markov models for image labeling
• Filter-based mean-field inference for random fields with higher-order terms and product label-spaces

Cites work

• scientific article; zbMATH DE number 6253875 (Why is no real title available?)
• An exact primal-dual penalty method approach to warmstarting interior-point methods for linear programming
• Approximation algorithms for classification problems with pairwise relationships, metric labeling and Markov random fields
• Fast approximate energy minimization with label costs
• Geometric motion segmentation and model selection
• MAP Estimation Via Agreement on Trees: Message-Passing and Linear Programming
• On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs

Cited in

(13)

• Active-set Methods for Submodular Minimization Problems
• Harmony potentials fusing global and local scale for semantic image segmentation
• Conditional random fields for pattern recognition applied to structured data
• Minimizing energies with hierarchical costs
• Blending learning and inference in conditional random fields
• Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials
• Global interactions in random field models: a potential function ensuring connectedness
• Fast approximate energy minimization with label costs
• Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
• Integrating geometrical context for semantic labeling of indoor scenes using RGBD images
• Midrange geometric interactions for semantic segmentation. Constraints for continuous multi-label optimization
• Optimizing the relevance-redundancy tradeoff for efficient semantic segmentation
• Generalized roof duality

This page was built for publication: Inference methods for CRFs with co-occurrence statistics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q362141)