FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2037163072> ?p ?o ?g. }

• W2037163072 endingPage "4243" @default.
• W2037163072 startingPage "4232" @default.
• W2037163072 abstract "We introduce the hierarchical Markov aspect model (HMAM), a computationally efficient graphical model for densely labeling large remote sensing images with their underlying terrain classes. HMAM resolves local ambiguities efficiently by combining the benefits of quadtree representations and aspect models—the former incorporate multiscale visual features and hierarchical smoothing to provide improved local label consistency, while the latter sharpen the labelings by focusing them on the classes that are most relevant for the broader local image context. The full HMAM model takes a grid of local hierarchical Markov quadtrees over image patches and augments it by incorporating a probabilistic latent semantic analysis aspect model over a larger local image tile at each level of the quadtree forest. Bag-of-word visual features are extracted for each level and patch, and given these, the parent–child transition probabilities from the quadtree and the label probabilities from the tile-level aspect models, an efficient forwards–backwards inference pass allows local posteriors for the class labels to be obtained for each patch. Variational expectation-maximization is then used to train the complete model from either pixel-level or tile-keyword-level labelings. Experiments on a complete TerraSAR-X synthetic aperture radar terrain map with pixel-level ground truth show that HMAM is both accurate and efficient, providing significantly better results than comparable single-scale aspect models with only a modest increase in training and test complexity. Keyword-level training greatly reduces the cost of providing training data with little loss of accuracy relative to pixel-level training." @default.
• W2037163072 created "2016-06-24" @default.
• W2037163072 creator A5062363302 @default.
• W2037163072 creator A5069540177 @default.
• W2037163072 creator A5073032922 @default.
• W2037163072 creator A5078838951 @default.
• W2037163072 date "2012-09-01" @default.
• W2037163072 modified "2023-10-17" @default.
• W2037163072 title "SAR-Based Terrain Classification Using Weakly Supervised Hierarchical Markov Aspect Models" @default.
• W2037163072 cites W1972281563 @default.
• W2037163072 cites W1973657137 @default.
• W2037163072 cites W1989563777 @default.
• W2037163072 cites W1989961619 @default.
• W2037163072 cites W2023492626 @default.
• W2037163072 cites W2024527993 @default.
• W2037163072 cites W2044921373 @default.
• W2037163072 cites W2049290650 @default.
• W2037163072 cites W2049694710 @default.
• W2037163072 cites W2061220758 @default.
• W2037163072 cites W2089858150 @default.
• W2037163072 cites W2095595743 @default.
• W2037163072 cites W2100119660 @default.
• W2037163072 cites W2106490775 @default.
• W2037163072 cites W2111758425 @default.
• W2037163072 cites W2114064685 @default.
• W2037163072 cites W2114217300 @default.
• W2037163072 cites W2119807955 @default.
• W2037163072 cites W2121915926 @default.
• W2037163072 cites W2123023145 @default.
• W2037163072 cites W2131693260 @default.
• W2037163072 cites W2132012856 @default.
• W2037163072 cites W2133303294 @default.
• W2037163072 cites W2133744276 @default.
• W2037163072 cites W2134392507 @default.
• W2037163072 cites W2134731454 @default.
• W2037163072 cites W2139047322 @default.
• W2037163072 cites W2142026865 @default.
• W2037163072 cites W2142117227 @default.
• W2037163072 cites W2142500924 @default.
• W2037163072 cites W2144554203 @default.
• W2037163072 cites W2144615653 @default.
• W2037163072 cites W2149234741 @default.
• W2037163072 cites W2151952539 @default.
• W2037163072 cites W2152214791 @default.
• W2037163072 cites W2153635508 @default.
• W2037163072 cites W2162021123 @default.
• W2037163072 cites W2165754343 @default.
• W2037163072 cites W2166155205 @default.
• W2037163072 cites W4231291716 @default.
• W2037163072 cites W4233135949 @default.
• W2037163072 cites W4237791300 @default.
• W2037163072 cites W4239510810 @default.
• W2037163072 doi "https://doi.org/10.1109/tip.2012.2199127" @default.
• W2037163072 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/22614643" @default.
• W2037163072 hasPublicationYear "2012" @default.
• W2037163072 type Work @default.
• W2037163072 sameAs 2037163072 @default.
• W2037163072 citedByCount "28" @default.
• W2037163072 countsByYear W20371630722013 @default.
• W2037163072 countsByYear W20371630722014 @default.
• W2037163072 countsByYear W20371630722015 @default.
• W2037163072 countsByYear W20371630722016 @default.
• W2037163072 countsByYear W20371630722017 @default.
• W2037163072 countsByYear W20371630722018 @default.
• W2037163072 countsByYear W20371630722020 @default.
• W2037163072 countsByYear W20371630722021 @default.
• W2037163072 countsByYear W20371630722022 @default.
• W2037163072 countsByYear W20371630722023 @default.
• W2037163072 crossrefType "journal-article" @default.
• W2037163072 hasAuthorship W2037163072A5062363302 @default.
• W2037163072 hasAuthorship W2037163072A5069540177 @default.
• W2037163072 hasAuthorship W2037163072A5073032922 @default.
• W2037163072 hasAuthorship W2037163072A5078838951 @default.
• W2037163072 hasConcept C119857082 @default.
• W2037163072 hasConcept C124101348 @default.
• W2037163072 hasConcept C144986985 @default.
• W2037163072 hasConcept C151416825 @default.
• W2037163072 hasConcept C151730666 @default.
• W2037163072 hasConcept C153180895 @default.
• W2037163072 hasConcept C154945302 @default.
• W2037163072 hasConcept C160633673 @default.
• W2037163072 hasConcept C161840515 @default.
• W2037163072 hasConcept C18903297 @default.
• W2037163072 hasConcept C2776214188 @default.
• W2037163072 hasConcept C2779343474 @default.
• W2037163072 hasConcept C41008148 @default.
• W2037163072 hasConcept C86803240 @default.
• W2037163072 hasConcept C98763669 @default.
• W2037163072 hasConceptScore W2037163072C119857082 @default.
• W2037163072 hasConceptScore W2037163072C124101348 @default.
• W2037163072 hasConceptScore W2037163072C144986985 @default.
• W2037163072 hasConceptScore W2037163072C151416825 @default.
• W2037163072 hasConceptScore W2037163072C151730666 @default.
• W2037163072 hasConceptScore W2037163072C153180895 @default.
• W2037163072 hasConceptScore W2037163072C154945302 @default.
• W2037163072 hasConceptScore W2037163072C160633673 @default.
• W2037163072 hasConceptScore W2037163072C161840515 @default.
• W2037163072 hasConceptScore W2037163072C18903297 @default.

• next