Matches in SemOpenAlex for { <https://semopenalex.org/work/W105646510> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W105646510 abstract "Learning a proper distance metric is crucial for many computer vision and image classification applications. Neighborhood Components Analysis (NCA) is an effective distance metric learning method which maximizes the kNN leave-out-one score on the training data by considering visual similarity between images. However, only using visual similarity to learn image distances could not satisfactorily cope with the diversity and complexity of a large number of real images with many concepts. To overcome this problem, integrating concrete semantic relations of images into the distance metric learning procedure can be a useful solution. This can more accurately model the image similarities and better reflect the perception of human in the classification system. In this paper, we propose Semantic NCA (SNCA), a novel approach which integrates semantic similarity into NCA, where neighborhood relations between images in the training dataset are measured by both visual characteristics and their concept relations. We evaluated several semantic similarity measures based on the WordNet tree. Experimental results show that the proposed approach improves the performance compared to the traditional distance metric learning methods." @default.
- W105646510 created "2016-06-24" @default.
- W105646510 creator A5002661071 @default.
- W105646510 creator A5028597017 @default.
- W105646510 creator A5079201773 @default.
- W105646510 creator A5085719285 @default.
- W105646510 date "2012-01-01" @default.
- W105646510 modified "2023-10-05" @default.
- W105646510 title "Improving Image Distance Metric Learning by Embedding Semantic Relations" @default.
- W105646510 cites W1488783102 @default.
- W105646510 cites W1566135517 @default.
- W105646510 cites W1865725639 @default.
- W105646510 cites W1970055505 @default.
- W105646510 cites W1996819635 @default.
- W105646510 cites W2062097648 @default.
- W105646510 cites W2108598243 @default.
- W105646510 cites W2122111042 @default.
- W105646510 cites W2166742463 @default.
- W105646510 cites W4235505822 @default.
- W105646510 doi "https://doi.org/10.1007/978-3-642-34778-8_39" @default.
- W105646510 hasPublicationYear "2012" @default.
- W105646510 type Work @default.
- W105646510 sameAs 105646510 @default.
- W105646510 citedByCount "3" @default.
- W105646510 countsByYear W1056465102016 @default.
- W105646510 countsByYear W1056465102017 @default.
- W105646510 countsByYear W1056465102019 @default.
- W105646510 crossrefType "book-chapter" @default.
- W105646510 hasAuthorship W105646510A5002661071 @default.
- W105646510 hasAuthorship W105646510A5028597017 @default.
- W105646510 hasAuthorship W105646510A5079201773 @default.
- W105646510 hasAuthorship W105646510A5085719285 @default.
- W105646510 hasConcept C115961682 @default.
- W105646510 hasConcept C154945302 @default.
- W105646510 hasConcept C162324750 @default.
- W105646510 hasConcept C176217482 @default.
- W105646510 hasConcept C21547014 @default.
- W105646510 hasConcept C31972630 @default.
- W105646510 hasConcept C41008148 @default.
- W105646510 hasConcept C41608201 @default.
- W105646510 hasConcept C80444323 @default.
- W105646510 hasConceptScore W105646510C115961682 @default.
- W105646510 hasConceptScore W105646510C154945302 @default.
- W105646510 hasConceptScore W105646510C162324750 @default.
- W105646510 hasConceptScore W105646510C176217482 @default.
- W105646510 hasConceptScore W105646510C21547014 @default.
- W105646510 hasConceptScore W105646510C31972630 @default.
- W105646510 hasConceptScore W105646510C41008148 @default.
- W105646510 hasConceptScore W105646510C41608201 @default.
- W105646510 hasConceptScore W105646510C80444323 @default.
- W105646510 hasLocation W1056465101 @default.
- W105646510 hasOpenAccess W105646510 @default.
- W105646510 hasPrimaryLocation W1056465101 @default.
- W105646510 hasRelatedWork W1891287906 @default.
- W105646510 hasRelatedWork W1969923398 @default.
- W105646510 hasRelatedWork W2036807459 @default.
- W105646510 hasRelatedWork W2130228941 @default.
- W105646510 hasRelatedWork W2161229648 @default.
- W105646510 hasRelatedWork W2166024367 @default.
- W105646510 hasRelatedWork W2772917594 @default.
- W105646510 hasRelatedWork W2775347418 @default.
- W105646510 hasRelatedWork W2993674027 @default.
- W105646510 hasRelatedWork W3090091644 @default.
- W105646510 isParatext "false" @default.
- W105646510 isRetracted "false" @default.
- W105646510 magId "105646510" @default.
- W105646510 workType "book-chapter" @default.