Matches in SemOpenAlex for { <https://semopenalex.org/work/W2128460414> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W2128460414 abstract "Suppose a set of images contains frequent occurrences of objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological (mutual containment) properties of multiscale regions defining objects in the category; (2) learning a region-based structural model of the category in terms of these properties from a set of training images; and (3) segmentation and recognition of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to find the maximally matching subtrees across the set, the existence of which is itself viewed as evidence that a category is indeed present. The matched subtrees are fused into a canonical tree, which represents the learned model of the category. Recognition of objects in a new image and image segmentation delineating all object parts are achieved simultaneously by finding matches of the model with subtrees of the new image. Experimental comparison with state-of-the-art methods shows that the proposed approach has similar recognition and superior localization performance while it uses fewer training examples." @default.
- W2128460414 created "2016-06-24" @default.
- W2128460414 creator A5027742996 @default.
- W2128460414 creator A5055952568 @default.
- W2128460414 date "2006-07-10" @default.
- W2128460414 modified "2023-09-26" @default.
- W2128460414 title "Extracting Subimages of an Unknown Category from a Set of Images" @default.
- W2128460414 cites W2012330712 @default.
- W2128460414 cites W2042498858 @default.
- W2128460414 cites W2105488551 @default.
- W2128460414 cites W2105714141 @default.
- W2128460414 cites W2115835964 @default.
- W2128460414 cites W2118782734 @default.
- W2128460414 cites W2125662744 @default.
- W2128460414 cites W2154422044 @default.
- W2128460414 cites W2157231504 @default.
- W2128460414 cites W2162820221 @default.
- W2128460414 cites W2164371126 @default.
- W2128460414 doi "https://doi.org/10.1109/cvpr.2006.116" @default.
- W2128460414 hasPublicationYear "2006" @default.
- W2128460414 type Work @default.
- W2128460414 sameAs 2128460414 @default.
- W2128460414 citedByCount "65" @default.
- W2128460414 countsByYear W21284604142012 @default.
- W2128460414 countsByYear W21284604142013 @default.
- W2128460414 countsByYear W21284604142014 @default.
- W2128460414 countsByYear W21284604142015 @default.
- W2128460414 countsByYear W21284604142021 @default.
- W2128460414 crossrefType "proceedings-article" @default.
- W2128460414 hasAuthorship W2128460414A5027742996 @default.
- W2128460414 hasAuthorship W2128460414A5055952568 @default.
- W2128460414 hasConcept C153180895 @default.
- W2128460414 hasConcept C154945302 @default.
- W2128460414 hasConcept C177264268 @default.
- W2128460414 hasConcept C199360897 @default.
- W2128460414 hasConcept C31972630 @default.
- W2128460414 hasConcept C41008148 @default.
- W2128460414 hasConceptScore W2128460414C153180895 @default.
- W2128460414 hasConceptScore W2128460414C154945302 @default.
- W2128460414 hasConceptScore W2128460414C177264268 @default.
- W2128460414 hasConceptScore W2128460414C199360897 @default.
- W2128460414 hasConceptScore W2128460414C31972630 @default.
- W2128460414 hasConceptScore W2128460414C41008148 @default.
- W2128460414 hasLocation W21284604141 @default.
- W2128460414 hasOpenAccess W2128460414 @default.
- W2128460414 hasPrimaryLocation W21284604141 @default.
- W2128460414 hasRelatedWork W1891287906 @default.
- W2128460414 hasRelatedWork W1969923398 @default.
- W2128460414 hasRelatedWork W2036807459 @default.
- W2128460414 hasRelatedWork W2058170566 @default.
- W2128460414 hasRelatedWork W2170022336 @default.
- W2128460414 hasRelatedWork W2229312674 @default.
- W2128460414 hasRelatedWork W258625772 @default.
- W2128460414 hasRelatedWork W2755342338 @default.
- W2128460414 hasRelatedWork W2772917594 @default.
- W2128460414 hasRelatedWork W3116076068 @default.
- W2128460414 isParatext "false" @default.
- W2128460414 isRetracted "false" @default.
- W2128460414 magId "2128460414" @default.
- W2128460414 workType "article" @default.