Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891053336> ?p ?o ?g. }
- W2891053336 abstract "In this paper, we formulate image co-segmentation as a classification problem in an unsupervised framework with the classes being the common foreground and the remaining regions in the image set. We first find a set of superpix-els across all images with high feature similarity such that the constituent superpixels in individual images are spatially compact and label them as seed for the common foreground. Those superpixels with high background probability are labeled as respective seeds for multiple background classes. Seed computation here is unsupervised and automated unlike some semi-supervised methods. Then, we compute discriminative features that separate the initially labeled classes using linear discriminant analysis. We use these features to perform spatially constrained label propagation and obtain labels for the unlabeled regions, and iterate this process till the seed regions grow to the common object. Experimental results demonstrate excellent robustness properties even while processing non-homogeneous image sets where the common object is present only in majority of the images." @default.
- W2891053336 created "2018-09-27" @default.
- W2891053336 creator A5010140343 @default.
- W2891053336 creator A5016405213 @default.
- W2891053336 creator A5060996961 @default.
- W2891053336 date "2018-10-01" @default.
- W2891053336 modified "2023-09-25" @default.
- W2891053336 title "Co-Segmentation of Non-Homogeneous Image Sets" @default.
- W2891053336 cites W1520246575 @default.
- W2891053336 cites W1635155787 @default.
- W2891053336 cites W1693210201 @default.
- W2891053336 cites W1963920598 @default.
- W2891053336 cites W1964884769 @default.
- W2891053336 cites W1968731684 @default.
- W2891053336 cites W1970899458 @default.
- W2891053336 cites W1996140089 @default.
- W2891053336 cites W2003343330 @default.
- W2891053336 cites W2008428344 @default.
- W2891053336 cites W2022432523 @default.
- W2891053336 cites W2025360228 @default.
- W2891053336 cites W2027922120 @default.
- W2891053336 cites W2044475502 @default.
- W2891053336 cites W2047670868 @default.
- W2891053336 cites W2086052791 @default.
- W2891053336 cites W2110370288 @default.
- W2891053336 cites W2118246710 @default.
- W2891053336 cites W2118802082 @default.
- W2891053336 cites W2129260071 @default.
- W2891053336 cites W2154455818 @default.
- W2891053336 cites W2157244733 @default.
- W2891053336 cites W2160847065 @default.
- W2891053336 cites W2295160225 @default.
- W2891053336 cites W2295326880 @default.
- W2891053336 cites W2296591648 @default.
- W2891053336 cites W2304841027 @default.
- W2891053336 cites W2321559277 @default.
- W2891053336 cites W2325835689 @default.
- W2891053336 cites W2415053570 @default.
- W2891053336 cites W2468480815 @default.
- W2891053336 cites W2553149432 @default.
- W2891053336 cites W2740660291 @default.
- W2891053336 cites W566255863 @default.
- W2891053336 doi "https://doi.org/10.1109/icip.2018.8451444" @default.
- W2891053336 hasPublicationYear "2018" @default.
- W2891053336 type Work @default.
- W2891053336 sameAs 2891053336 @default.
- W2891053336 citedByCount "0" @default.
- W2891053336 crossrefType "proceedings-article" @default.
- W2891053336 hasAuthorship W2891053336A5010140343 @default.
- W2891053336 hasAuthorship W2891053336A5016405213 @default.
- W2891053336 hasAuthorship W2891053336A5060996961 @default.
- W2891053336 hasConcept C104317684 @default.
- W2891053336 hasConcept C11413529 @default.
- W2891053336 hasConcept C114614502 @default.
- W2891053336 hasConcept C115961682 @default.
- W2891053336 hasConcept C124504099 @default.
- W2891053336 hasConcept C153180895 @default.
- W2891053336 hasConcept C154945302 @default.
- W2891053336 hasConcept C177264268 @default.
- W2891053336 hasConcept C185592680 @default.
- W2891053336 hasConcept C199360897 @default.
- W2891053336 hasConcept C33923547 @default.
- W2891053336 hasConcept C41008148 @default.
- W2891053336 hasConcept C45374587 @default.
- W2891053336 hasConcept C52622490 @default.
- W2891053336 hasConcept C55493867 @default.
- W2891053336 hasConcept C63479239 @default.
- W2891053336 hasConcept C66882249 @default.
- W2891053336 hasConcept C69738355 @default.
- W2891053336 hasConcept C75294576 @default.
- W2891053336 hasConcept C89600930 @default.
- W2891053336 hasConcept C97931131 @default.
- W2891053336 hasConceptScore W2891053336C104317684 @default.
- W2891053336 hasConceptScore W2891053336C11413529 @default.
- W2891053336 hasConceptScore W2891053336C114614502 @default.
- W2891053336 hasConceptScore W2891053336C115961682 @default.
- W2891053336 hasConceptScore W2891053336C124504099 @default.
- W2891053336 hasConceptScore W2891053336C153180895 @default.
- W2891053336 hasConceptScore W2891053336C154945302 @default.
- W2891053336 hasConceptScore W2891053336C177264268 @default.
- W2891053336 hasConceptScore W2891053336C185592680 @default.
- W2891053336 hasConceptScore W2891053336C199360897 @default.
- W2891053336 hasConceptScore W2891053336C33923547 @default.
- W2891053336 hasConceptScore W2891053336C41008148 @default.
- W2891053336 hasConceptScore W2891053336C45374587 @default.
- W2891053336 hasConceptScore W2891053336C52622490 @default.
- W2891053336 hasConceptScore W2891053336C55493867 @default.
- W2891053336 hasConceptScore W2891053336C63479239 @default.
- W2891053336 hasConceptScore W2891053336C66882249 @default.
- W2891053336 hasConceptScore W2891053336C69738355 @default.
- W2891053336 hasConceptScore W2891053336C75294576 @default.
- W2891053336 hasConceptScore W2891053336C89600930 @default.
- W2891053336 hasConceptScore W2891053336C97931131 @default.
- W2891053336 hasLocation W28910533361 @default.
- W2891053336 hasOpenAccess W2891053336 @default.
- W2891053336 hasPrimaryLocation W28910533361 @default.
- W2891053336 hasRelatedWork W1520303119 @default.
- W2891053336 hasRelatedWork W2067165398 @default.
- W2891053336 hasRelatedWork W2104912729 @default.
- W2891053336 hasRelatedWork W2118344708 @default.