Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288071921> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4288071921 endingPage "11" @default.
- W4288071921 startingPage "1" @default.
- W4288071921 abstract "Fashion compatibility predictions have obtained a lot of attention recently. Mining the compatibility between fashion items in an outfit is different from learning the visual similarity, since this relationship is more delicate. Decomposing the outfit compatibility into pairwise item matching is a popular way to treat the problem. However, in most existing methods, the items are matched without considering the context, i.e, the remaining items in the outfit. Recent efforts have been made to learn the underlying high order relationships among items by treating the outfit as a whole. These models could be sensitive to the properties of different datasets, and the item representations in these models are not as compact as those in the pairwise models. In this paper, we propose a context conditioning embedding approach to learn compact representations that preserve the shared information among items under the existence of contextual items. We use two different spaces, the general and the contextual spaces, to embed items, where the representation in the contextual space contains information from the context. We employ mutual information maximization for model learning, which is shown to be more appropriate for the problem. With extensive experiments, we show that our model achieves superior performance than other state-of-the-art methods." @default.
- W4288071921 created "2022-07-28" @default.
- W4288071921 creator A5009086349 @default.
- W4288071921 creator A5013213775 @default.
- W4288071921 creator A5034257982 @default.
- W4288071921 creator A5077470082 @default.
- W4288071921 creator A5089921601 @default.
- W4288071921 date "2022-01-01" @default.
- W4288071921 modified "2023-09-24" @default.
- W4288071921 title "Learning Fashion Compatibility with Context Conditioning Embedding" @default.
- W4288071921 doi "https://doi.org/10.1109/tmm.2022.3193560" @default.
- W4288071921 hasPublicationYear "2022" @default.
- W4288071921 type Work @default.
- W4288071921 citedByCount "0" @default.
- W4288071921 crossrefType "journal-article" @default.
- W4288071921 hasAuthorship W4288071921A5009086349 @default.
- W4288071921 hasAuthorship W4288071921A5013213775 @default.
- W4288071921 hasAuthorship W4288071921A5034257982 @default.
- W4288071921 hasAuthorship W4288071921A5077470082 @default.
- W4288071921 hasAuthorship W4288071921A5089921601 @default.
- W4288071921 hasConcept C119857082 @default.
- W4288071921 hasConcept C126255220 @default.
- W4288071921 hasConcept C127313418 @default.
- W4288071921 hasConcept C154945302 @default.
- W4288071921 hasConcept C17409809 @default.
- W4288071921 hasConcept C183322885 @default.
- W4288071921 hasConcept C184898388 @default.
- W4288071921 hasConcept C204321447 @default.
- W4288071921 hasConcept C23123220 @default.
- W4288071921 hasConcept C2776330181 @default.
- W4288071921 hasConcept C2778648169 @default.
- W4288071921 hasConcept C2781238097 @default.
- W4288071921 hasConcept C33923547 @default.
- W4288071921 hasConcept C41008148 @default.
- W4288071921 hasConcept C41608201 @default.
- W4288071921 hasConcept C80444323 @default.
- W4288071921 hasConceptScore W4288071921C119857082 @default.
- W4288071921 hasConceptScore W4288071921C126255220 @default.
- W4288071921 hasConceptScore W4288071921C127313418 @default.
- W4288071921 hasConceptScore W4288071921C154945302 @default.
- W4288071921 hasConceptScore W4288071921C17409809 @default.
- W4288071921 hasConceptScore W4288071921C183322885 @default.
- W4288071921 hasConceptScore W4288071921C184898388 @default.
- W4288071921 hasConceptScore W4288071921C204321447 @default.
- W4288071921 hasConceptScore W4288071921C23123220 @default.
- W4288071921 hasConceptScore W4288071921C2776330181 @default.
- W4288071921 hasConceptScore W4288071921C2778648169 @default.
- W4288071921 hasConceptScore W4288071921C2781238097 @default.
- W4288071921 hasConceptScore W4288071921C33923547 @default.
- W4288071921 hasConceptScore W4288071921C41008148 @default.
- W4288071921 hasConceptScore W4288071921C41608201 @default.
- W4288071921 hasConceptScore W4288071921C80444323 @default.
- W4288071921 hasFunder F4320321001 @default.
- W4288071921 hasLocation W42880719211 @default.
- W4288071921 hasOpenAccess W4288071921 @default.
- W4288071921 hasPrimaryLocation W42880719211 @default.
- W4288071921 hasRelatedWork W11594795 @default.
- W4288071921 hasRelatedWork W11991885 @default.
- W4288071921 hasRelatedWork W13303319 @default.
- W4288071921 hasRelatedWork W14027548 @default.
- W4288071921 hasRelatedWork W1670791 @default.
- W4288071921 hasRelatedWork W1997992 @default.
- W4288071921 hasRelatedWork W2237909 @default.
- W4288071921 hasRelatedWork W4227807 @default.
- W4288071921 hasRelatedWork W7724241 @default.
- W4288071921 hasRelatedWork W8168616 @default.
- W4288071921 isParatext "false" @default.
- W4288071921 isRetracted "false" @default.
- W4288071921 workType "article" @default.