Harmony potentials fusing global and local scale for semantic image segmentation

DOI10.1007/S11263-011-0449-8zbMATH Open1235.68246OpenAlexW2013777358MaRDI QIDQ409147FDOQ409147

Joan Serrat, Andrew D. Bagdanov, Xavier Boix, Josep M. Gonfaus, Joost Van De Weijer

Publication date: 12 April 2012

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

Full work available at URL: https://doi.org/10.1007/s11263-011-0449-8

zbMATH Keywords

hierarchical conditional random fieldssemantic object segmentation

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Cites Work

• Title not available (Why is that?)
• Graphical Models, Exponential Families, and Variational Inference
• Learning low-level vision
• Fast approximate energy minimization with label costs
• Recovering occlusion boundaries from an image
• Harmony potentials fusing global and local scale for semantic image segmentation
• Title not available (Why is that?)
• Learning Color Names for Real-World Applications
• Fields of experts
• Putting objects in perspective

Cited In (4)

• Harmony potentials fusing global and local scale for semantic image segmentation
• Rooted spanning superpixels
• Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
• Probabilistic joint image segmentation and labeling by figure-ground composition

Uses Software

• MAXFLOW
• BSDS
• SIFT
• PASCAL VOC

   Recommendations

• Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference 👍 👎
• Inference methods for CRFs with co-occurrence statistics 👍 👎
• Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials 👍 👎
• Probabilistic joint image segmentation and labeling by figure-ground composition 👍 👎
• Global-local optimizations by hierarchical cuts and climbing energies 👍 👎

This page was built for publication: Harmony potentials fusing global and local scale for semantic image segmentation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q409147)