Matches in SemOpenAlex for { <https://semopenalex.org/work/W2775528509> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2775528509 endingPage "110" @default.
- W2775528509 startingPage "98" @default.
- W2775528509 abstract "Abstract In this paper, we propose a novel semi-supervised method to predict clothing attributes with the assistance of unlabeled data like fashion shows. To this end, a two-stage framework is built, i.e., the unsupervised triplet network pre-training stage that ensures frames in the same video having coherent representations while frames from different videos having larger feature distances, and a supervised clothing attribute prediction stage to estimate the value of attributes. Specifically, we first detect the clothes of frames in the collected 18,737 female fashion shows and 21,224 male fashion shows which contain no extra labels. Then a triplet neural network is constructed via embedding the temporal appearance consistency between frames in the same video and the representation gap in different videos. Finally, we transfer the triplet model parameters to multi-task clothing attribute prediction model, and fine-tune it with clothing images holding attribute labels. Extensive experiments demonstrate the advantages of the proposed method on two clothing datasets." @default.
- W2775528509 created "2017-12-22" @default.
- W2775528509 creator A5008232261 @default.
- W2775528509 creator A5010357390 @default.
- W2775528509 creator A5028701730 @default.
- W2775528509 creator A5068837264 @default.
- W2775528509 creator A5090930764 @default.
- W2775528509 date "2018-03-01" @default.
- W2775528509 modified "2023-09-27" @default.
- W2775528509 title "Watch fashion shows to tell clothing attributes" @default.
- W2775528509 cites W1973255633 @default.
- W2775528509 cites W1992195312 @default.
- W2775528509 cites W1994769389 @default.
- W2775528509 cites W2047809566 @default.
- W2775528509 cites W2068326522 @default.
- W2775528509 cites W2088049833 @default.
- W2775528509 cites W2109255472 @default.
- W2775528509 cites W2151103935 @default.
- W2775528509 cites W3099224353 @default.
- W2775528509 cites W3101469729 @default.
- W2775528509 doi "https://doi.org/10.1016/j.neucom.2017.12.027" @default.
- W2775528509 hasPublicationYear "2018" @default.
- W2775528509 type Work @default.
- W2775528509 sameAs 2775528509 @default.
- W2775528509 citedByCount "14" @default.
- W2775528509 countsByYear W27755285092019 @default.
- W2775528509 countsByYear W27755285092020 @default.
- W2775528509 countsByYear W27755285092021 @default.
- W2775528509 countsByYear W27755285092022 @default.
- W2775528509 countsByYear W27755285092023 @default.
- W2775528509 crossrefType "journal-article" @default.
- W2775528509 hasAuthorship W2775528509A5008232261 @default.
- W2775528509 hasAuthorship W2775528509A5010357390 @default.
- W2775528509 hasAuthorship W2775528509A5028701730 @default.
- W2775528509 hasAuthorship W2775528509A5068837264 @default.
- W2775528509 hasAuthorship W2775528509A5090930764 @default.
- W2775528509 hasConcept C112698675 @default.
- W2775528509 hasConcept C144133560 @default.
- W2775528509 hasConcept C166957645 @default.
- W2775528509 hasConcept C205649164 @default.
- W2775528509 hasConcept C2779611367 @default.
- W2775528509 hasConcept C41008148 @default.
- W2775528509 hasConcept C530175646 @default.
- W2775528509 hasConceptScore W2775528509C112698675 @default.
- W2775528509 hasConceptScore W2775528509C144133560 @default.
- W2775528509 hasConceptScore W2775528509C166957645 @default.
- W2775528509 hasConceptScore W2775528509C205649164 @default.
- W2775528509 hasConceptScore W2775528509C2779611367 @default.
- W2775528509 hasConceptScore W2775528509C41008148 @default.
- W2775528509 hasConceptScore W2775528509C530175646 @default.
- W2775528509 hasLocation W27755285091 @default.
- W2775528509 hasOpenAccess W2775528509 @default.
- W2775528509 hasPrimaryLocation W27755285091 @default.
- W2775528509 hasRelatedWork W1484667021 @default.
- W2775528509 hasRelatedWork W2091397173 @default.
- W2775528509 hasRelatedWork W2107767327 @default.
- W2775528509 hasRelatedWork W2260652771 @default.
- W2775528509 hasRelatedWork W2314438141 @default.
- W2775528509 hasRelatedWork W2552519117 @default.
- W2775528509 hasRelatedWork W2570518161 @default.
- W2775528509 hasRelatedWork W2740695732 @default.
- W2775528509 hasRelatedWork W2749612761 @default.
- W2775528509 hasRelatedWork W2761712870 @default.
- W2775528509 hasVolume "282" @default.
- W2775528509 isParatext "false" @default.
- W2775528509 isRetracted "false" @default.
- W2775528509 magId "2775528509" @default.
- W2775528509 workType "article" @default.