Matches in SemOpenAlex for { <https://semopenalex.org/work/W2736378133> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2736378133 abstract "A Gibbs Sampler based topic model for image annotation, which takes into account the interaction between visual geometric context and related topic, is presented. Most of the existing topic models for scene annotation use segmentation-based algorithm. However, topic models using segmentation algorithm alone sometimes can produce erroneous results when used to annotate real-life scene pictures. Therefore, our algorithm makes use of peaks of image surface instead of segmentation regions. Existing approaches use SIFT algorithm and treat the peaks as round blob features. In this paper, the peaks are treated as anisotropic blob features, which models low level visual elements more precisely. In order to better utilize visual features, our model not only takes into consideration visual codeword, but also considers influence of visual properties to topic formation, such as orientation, width, length and color. The basic idea is based on the assumption that different topics will produce distinct visual appearance, and different visual appearance is helpful to distinguish topics. During the learning stage, each topic will be associated with a set of distributions of visual properties, which depicts appearance of the topic. This paper considers more geometric properties, which will reduce topic uncertainty and learn the images better. Tested with Corel5K, SAIAPR-TC12 and Espgame100k Datasets, our method performs moderately better than some state of the arts methods." @default.
- W2736378133 created "2017-07-31" @default.
- W2736378133 creator A5056949990 @default.
- W2736378133 creator A5070036406 @default.
- W2736378133 date "2017-07-21" @default.
- W2736378133 modified "2023-09-23" @default.
- W2736378133 title "Image understanding using geometric context" @default.
- W2736378133 cites W1532257412 @default.
- W2736378133 cites W2151103935 @default.
- W2736378133 doi "https://doi.org/10.1117/12.2281685" @default.
- W2736378133 hasPublicationYear "2017" @default.
- W2736378133 type Work @default.
- W2736378133 sameAs 2736378133 @default.
- W2736378133 citedByCount "0" @default.
- W2736378133 crossrefType "proceedings-article" @default.
- W2736378133 hasAuthorship W2736378133A5056949990 @default.
- W2736378133 hasAuthorship W2736378133A5070036406 @default.
- W2736378133 hasConcept C115961682 @default.
- W2736378133 hasConcept C124504099 @default.
- W2736378133 hasConcept C151730666 @default.
- W2736378133 hasConcept C153180895 @default.
- W2736378133 hasConcept C154945302 @default.
- W2736378133 hasConcept C16345878 @default.
- W2736378133 hasConcept C177264268 @default.
- W2736378133 hasConcept C199360897 @default.
- W2736378133 hasConcept C2524010 @default.
- W2736378133 hasConcept C2776321320 @default.
- W2736378133 hasConcept C2779343474 @default.
- W2736378133 hasConcept C31972630 @default.
- W2736378133 hasConcept C33923547 @default.
- W2736378133 hasConcept C36464697 @default.
- W2736378133 hasConcept C41008148 @default.
- W2736378133 hasConcept C61265191 @default.
- W2736378133 hasConcept C86803240 @default.
- W2736378133 hasConcept C89600930 @default.
- W2736378133 hasConceptScore W2736378133C115961682 @default.
- W2736378133 hasConceptScore W2736378133C124504099 @default.
- W2736378133 hasConceptScore W2736378133C151730666 @default.
- W2736378133 hasConceptScore W2736378133C153180895 @default.
- W2736378133 hasConceptScore W2736378133C154945302 @default.
- W2736378133 hasConceptScore W2736378133C16345878 @default.
- W2736378133 hasConceptScore W2736378133C177264268 @default.
- W2736378133 hasConceptScore W2736378133C199360897 @default.
- W2736378133 hasConceptScore W2736378133C2524010 @default.
- W2736378133 hasConceptScore W2736378133C2776321320 @default.
- W2736378133 hasConceptScore W2736378133C2779343474 @default.
- W2736378133 hasConceptScore W2736378133C31972630 @default.
- W2736378133 hasConceptScore W2736378133C33923547 @default.
- W2736378133 hasConceptScore W2736378133C36464697 @default.
- W2736378133 hasConceptScore W2736378133C41008148 @default.
- W2736378133 hasConceptScore W2736378133C61265191 @default.
- W2736378133 hasConceptScore W2736378133C86803240 @default.
- W2736378133 hasConceptScore W2736378133C89600930 @default.
- W2736378133 hasLocation W27363781331 @default.
- W2736378133 hasOpenAccess W2736378133 @default.
- W2736378133 hasPrimaryLocation W27363781331 @default.
- W2736378133 hasRelatedWork W1414260227 @default.
- W2736378133 hasRelatedWork W1557724123 @default.
- W2736378133 hasRelatedWork W1573254965 @default.
- W2736378133 hasRelatedWork W1596972137 @default.
- W2736378133 hasRelatedWork W1849916637 @default.
- W2736378133 hasRelatedWork W2003090023 @default.
- W2736378133 hasRelatedWork W2058423197 @default.
- W2736378133 hasRelatedWork W2107228164 @default.
- W2736378133 hasRelatedWork W2186446126 @default.
- W2736378133 hasRelatedWork W2196975585 @default.
- W2736378133 hasRelatedWork W2214651417 @default.
- W2736378133 hasRelatedWork W2527238922 @default.
- W2736378133 hasRelatedWork W2572518213 @default.
- W2736378133 hasRelatedWork W2945674360 @default.
- W2736378133 hasRelatedWork W2990995252 @default.
- W2736378133 hasRelatedWork W3025840398 @default.
- W2736378133 hasRelatedWork W3033562189 @default.
- W2736378133 hasRelatedWork W3140985361 @default.
- W2736378133 hasRelatedWork W3168495321 @default.
- W2736378133 hasRelatedWork W2185824099 @default.
- W2736378133 isParatext "false" @default.
- W2736378133 isRetracted "false" @default.
- W2736378133 magId "2736378133" @default.
- W2736378133 workType "article" @default.