Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016139543> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3016139543 abstract "We propose a computational framework for ranking images (group photos in particular) taken at the same event within a short time span. The ranking is expected to correspond with human perception of overall appeal of the images. We hypothesize and provide evidence through subjective analysis that the factors that appeal to humans are its emotional content, aesthetics and image quality. We propose a network which is an ensemble of three information channels, each predicting a score corresponding to one of three visual appeal factors. For group emotion estimation, we propose a convolutional neural network (CNN) based architecture for predicting group emotion from images. This new architecture enforces the network to put emphasis on the important regions in the images, and achieves comparable results to the state-of-the-art. Next, we develop a network for the image ranking task that combines group emotion, aesthetics and image quality scores. Owing to the unavailability of suitable databases, we created a new database of manually annotated group photos taken during various social events. We present experimental results on this database and other benchmark databases whenever available. Overall, our experiments show that the proposed framework can reliably predict the overall appeal of images with results closely corresponding to human ranking." @default.
- W3016139543 created "2020-04-17" @default.
- W3016139543 creator A5017489553 @default.
- W3016139543 creator A5021354054 @default.
- W3016139543 creator A5072672307 @default.
- W3016139543 date "2020-05-01" @default.
- W3016139543 modified "2023-10-18" @default.
- W3016139543 title "Ensemble Network For Ranking Images Based On Visual Appeal" @default.
- W3016139543 cites W1606493646 @default.
- W3016139543 cites W1982471090 @default.
- W3016139543 cites W2007773296 @default.
- W3016139543 cites W2009678853 @default.
- W3016139543 cites W2035720976 @default.
- W3016139543 cites W2051596736 @default.
- W3016139543 cites W2078807908 @default.
- W3016139543 cites W2080754665 @default.
- W3016139543 cites W2094637479 @default.
- W3016139543 cites W2217895792 @default.
- W3016139543 cites W2417288846 @default.
- W3016139543 cites W2548676029 @default.
- W3016139543 cites W3101314801 @default.
- W3016139543 cites W3101840568 @default.
- W3016139543 doi "https://doi.org/10.1109/icassp40776.2020.9054702" @default.
- W3016139543 hasPublicationYear "2020" @default.
- W3016139543 type Work @default.
- W3016139543 sameAs 3016139543 @default.
- W3016139543 citedByCount "0" @default.
- W3016139543 crossrefType "proceedings-article" @default.
- W3016139543 hasAuthorship W3016139543A5017489553 @default.
- W3016139543 hasAuthorship W3016139543A5021354054 @default.
- W3016139543 hasAuthorship W3016139543A5072672307 @default.
- W3016139543 hasBestOaLocation W30161395432 @default.
- W3016139543 hasConcept C105795698 @default.
- W3016139543 hasConcept C111472728 @default.
- W3016139543 hasConcept C115961682 @default.
- W3016139543 hasConcept C119857082 @default.
- W3016139543 hasConcept C13280743 @default.
- W3016139543 hasConcept C138885662 @default.
- W3016139543 hasConcept C153180895 @default.
- W3016139543 hasConcept C154945302 @default.
- W3016139543 hasConcept C162324750 @default.
- W3016139543 hasConcept C185798385 @default.
- W3016139543 hasConcept C187736073 @default.
- W3016139543 hasConcept C189430467 @default.
- W3016139543 hasConcept C205649164 @default.
- W3016139543 hasConcept C23123220 @default.
- W3016139543 hasConcept C2779530757 @default.
- W3016139543 hasConcept C2780451532 @default.
- W3016139543 hasConcept C2780505938 @default.
- W3016139543 hasConcept C33923547 @default.
- W3016139543 hasConcept C41008148 @default.
- W3016139543 hasConcept C81363708 @default.
- W3016139543 hasConceptScore W3016139543C105795698 @default.
- W3016139543 hasConceptScore W3016139543C111472728 @default.
- W3016139543 hasConceptScore W3016139543C115961682 @default.
- W3016139543 hasConceptScore W3016139543C119857082 @default.
- W3016139543 hasConceptScore W3016139543C13280743 @default.
- W3016139543 hasConceptScore W3016139543C138885662 @default.
- W3016139543 hasConceptScore W3016139543C153180895 @default.
- W3016139543 hasConceptScore W3016139543C154945302 @default.
- W3016139543 hasConceptScore W3016139543C162324750 @default.
- W3016139543 hasConceptScore W3016139543C185798385 @default.
- W3016139543 hasConceptScore W3016139543C187736073 @default.
- W3016139543 hasConceptScore W3016139543C189430467 @default.
- W3016139543 hasConceptScore W3016139543C205649164 @default.
- W3016139543 hasConceptScore W3016139543C23123220 @default.
- W3016139543 hasConceptScore W3016139543C2779530757 @default.
- W3016139543 hasConceptScore W3016139543C2780451532 @default.
- W3016139543 hasConceptScore W3016139543C2780505938 @default.
- W3016139543 hasConceptScore W3016139543C33923547 @default.
- W3016139543 hasConceptScore W3016139543C41008148 @default.
- W3016139543 hasConceptScore W3016139543C81363708 @default.
- W3016139543 hasLocation W30161395431 @default.
- W3016139543 hasLocation W30161395432 @default.
- W3016139543 hasOpenAccess W3016139543 @default.
- W3016139543 hasPrimaryLocation W30161395431 @default.
- W3016139543 hasRelatedWork W10175904 @default.
- W3016139543 hasRelatedWork W12336802 @default.
- W3016139543 hasRelatedWork W2267404 @default.
- W3016139543 hasRelatedWork W3262960 @default.
- W3016139543 hasRelatedWork W3820303 @default.
- W3016139543 hasRelatedWork W3904675 @default.
- W3016139543 hasRelatedWork W40399 @default.
- W3016139543 hasRelatedWork W5598288 @default.
- W3016139543 hasRelatedWork W6745161 @default.
- W3016139543 hasRelatedWork W9761094 @default.
- W3016139543 isParatext "false" @default.
- W3016139543 isRetracted "false" @default.
- W3016139543 magId "3016139543" @default.
- W3016139543 workType "article" @default.