Matches in SemOpenAlex for { <https://semopenalex.org/work/W2941821239> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2941821239 endingPage "2086" @default.
- W2941821239 startingPage "2077" @default.
- W2941821239 abstract "A lot of research attentions have been paid to image emotion analysis in recent years. Meanwhile, as convolutional neural networks (CNNs) have made great successful in computer vision, many researchers start to employ CNN to discriminate image emotions. However, the training procedure of CNNs depends on sufficient labeled data. Therefore, a CNN is hard to perform well in an image domain with scant labeled information. In this paper, we propose a deep transfer learning method for image emotion analysis. The method can leverage rich emotion knowledge from a source domain to the target domain. Our method reduces both marginal and joint domain distribution discrepancies at fully-connected layers. Through this way, we can effectively extract more transferable features and advance the performance of CNNs on poor-label emotion-image domains." @default.
- W2941821239 created "2019-05-03" @default.
- W2941821239 creator A5057732142 @default.
- W2941821239 creator A5079002529 @default.
- W2941821239 date "2019-04-22" @default.
- W2941821239 modified "2023-09-26" @default.
- W2941821239 title "Deep Transfer Learning for Image Emotion Analysis: Reducing Marginal and Joint Distribution Discrepancies Together" @default.
- W2941821239 cites W1946137962 @default.
- W2941821239 cites W1981424477 @default.
- W2941821239 cites W2003856922 @default.
- W2941821239 cites W2015861736 @default.
- W2941821239 cites W2063948594 @default.
- W2941821239 cites W2074356411 @default.
- W2941821239 cites W2082398333 @default.
- W2941821239 cites W2085940040 @default.
- W2941821239 cites W2108598243 @default.
- W2941821239 cites W2112483442 @default.
- W2941821239 cites W2115403315 @default.
- W2941821239 cites W2136922672 @default.
- W2941821239 cites W2162745601 @default.
- W2941821239 cites W2194775991 @default.
- W2941821239 cites W2214409633 @default.
- W2941821239 cites W2347880541 @default.
- W2941821239 cites W2395579298 @default.
- W2941821239 cites W2398886555 @default.
- W2941821239 cites W2531468424 @default.
- W2941821239 cites W2867696556 @default.
- W2941821239 cites W2896591327 @default.
- W2941821239 cites W2904451048 @default.
- W2941821239 cites W2913218058 @default.
- W2941821239 cites W2963992782 @default.
- W2941821239 doi "https://doi.org/10.1007/s11063-019-10035-7" @default.
- W2941821239 hasPublicationYear "2019" @default.
- W2941821239 type Work @default.
- W2941821239 sameAs 2941821239 @default.
- W2941821239 citedByCount "7" @default.
- W2941821239 countsByYear W29418212392020 @default.
- W2941821239 countsByYear W29418212392021 @default.
- W2941821239 countsByYear W29418212392022 @default.
- W2941821239 crossrefType "journal-article" @default.
- W2941821239 hasAuthorship W2941821239A5057732142 @default.
- W2941821239 hasAuthorship W2941821239A5079002529 @default.
- W2941821239 hasBestOaLocation W29418212391 @default.
- W2941821239 hasConcept C108583219 @default.
- W2941821239 hasConcept C115961682 @default.
- W2941821239 hasConcept C119857082 @default.
- W2941821239 hasConcept C127413603 @default.
- W2941821239 hasConcept C134306372 @default.
- W2941821239 hasConcept C139502532 @default.
- W2941821239 hasConcept C150899416 @default.
- W2941821239 hasConcept C153083717 @default.
- W2941821239 hasConcept C153180895 @default.
- W2941821239 hasConcept C154945302 @default.
- W2941821239 hasConcept C170154142 @default.
- W2941821239 hasConcept C18555067 @default.
- W2941821239 hasConcept C33923547 @default.
- W2941821239 hasConcept C36503486 @default.
- W2941821239 hasConcept C41008148 @default.
- W2941821239 hasConcept C81363708 @default.
- W2941821239 hasConceptScore W2941821239C108583219 @default.
- W2941821239 hasConceptScore W2941821239C115961682 @default.
- W2941821239 hasConceptScore W2941821239C119857082 @default.
- W2941821239 hasConceptScore W2941821239C127413603 @default.
- W2941821239 hasConceptScore W2941821239C134306372 @default.
- W2941821239 hasConceptScore W2941821239C139502532 @default.
- W2941821239 hasConceptScore W2941821239C150899416 @default.
- W2941821239 hasConceptScore W2941821239C153083717 @default.
- W2941821239 hasConceptScore W2941821239C153180895 @default.
- W2941821239 hasConceptScore W2941821239C154945302 @default.
- W2941821239 hasConceptScore W2941821239C170154142 @default.
- W2941821239 hasConceptScore W2941821239C18555067 @default.
- W2941821239 hasConceptScore W2941821239C33923547 @default.
- W2941821239 hasConceptScore W2941821239C36503486 @default.
- W2941821239 hasConceptScore W2941821239C41008148 @default.
- W2941821239 hasConceptScore W2941821239C81363708 @default.
- W2941821239 hasIssue "3" @default.
- W2941821239 hasLocation W29418212391 @default.
- W2941821239 hasOpenAccess W2941821239 @default.
- W2941821239 hasPrimaryLocation W29418212391 @default.
- W2941821239 hasRelatedWork W2996856019 @default.
- W2941821239 hasRelatedWork W3018421652 @default.
- W2941821239 hasRelatedWork W3021430260 @default.
- W2941821239 hasRelatedWork W3091976719 @default.
- W2941821239 hasRelatedWork W3192840557 @default.
- W2941821239 hasRelatedWork W4220996320 @default.
- W2941821239 hasRelatedWork W4285149559 @default.
- W2941821239 hasRelatedWork W4312200629 @default.
- W2941821239 hasRelatedWork W4382286161 @default.
- W2941821239 hasRelatedWork W4386213806 @default.
- W2941821239 hasVolume "51" @default.
- W2941821239 isParatext "false" @default.
- W2941821239 isRetracted "false" @default.
- W2941821239 magId "2941821239" @default.
- W2941821239 workType "article" @default.