FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3110156989> ?p ?o ?g. }

• W3110156989 endingPage "635" @default.
• W3110156989 startingPage "619" @default.
• W3110156989 abstract "The 2D virtual try-on task has recently attracted a great interest from the research community, for its direct potential applications in online shopping as well as for its inherent and non-addressed scientific challenges. This task requires fitting an in-shop cloth image on the image of a person, which is highly challenging because it involves cloth warping, image compositing, and synthesizing. Casting virtual try-on into a supervised task faces a difficulty: available datasets are composed of pairs of pictures (cloth, person wearing the cloth). Thus, we have no access to ground-truth when the cloth on the person changes. State-of-the-art models solve this by masking the cloth information on the person with both a human parser and a pose estimator. Then, image synthesis modules are trained to reconstruct the person image from the masked person image and the cloth image. This procedure has several caveats: firstly, human parsers are prone to errors; secondly, it is a costly pre-processing step, which also has to be applied at inference time; finally, it makes the task harder than it is since the mask covers information that should be kept such as hands or accessories. In this paper, we propose a novel student-teacher paradigm where the teacher is trained in the standard way (reconstruction) before guiding the student to focus on the initial task (changing the cloth). The student additionally learns from an adversarial loss, which pushes it to follow the distribution of the real images. Consequently, the student exploits information that is masked to the teacher. A student trained without the adversarial loss would not use this information. Also, getting rid of both human parser and pose estimator at inference time allows obtaining a real-time virtual try-on." @default.
• W3110156989 created "2020-12-07" @default.
• W3110156989 creator A5008216150 @default.
• W3110156989 creator A5034842399 @default.
• W3110156989 creator A5053968661 @default.
• W3110156989 date "2020-01-01" @default.
• W3110156989 modified "2023-09-30" @default.
• W3110156989 title "Do Not Mask What You Do Not Need to Mask: A Parser-Free Virtual Try-On" @default.
• W3110156989 cites W1901129140 @default.
• W3110156989 cites W1978216348 @default.
• W3110156989 cites W2011131260 @default.
• W3110156989 cites W2057175746 @default.
• W3110156989 cites W2128409098 @default.
• W3110156989 cites W2133665775 @default.
• W3110156989 cites W2331128040 @default.
• W3110156989 cites W2562637781 @default.
• W3110156989 cites W2572730214 @default.
• W3110156989 cites W2598915960 @default.
• W3110156989 cites W2604233003 @default.
• W3110156989 cites W2737762407 @default.
• W3110156989 cites W2771558241 @default.
• W3110156989 cites W2883309205 @default.
• W3110156989 cites W2895668250 @default.
• W3110156989 cites W2962785568 @default.
• W3110156989 cites W2962793481 @default.
• W3110156989 cites W2963073614 @default.
• W3110156989 cites W2963876278 @default.
• W3110156989 cites W2963978393 @default.
• W3110156989 cites W2964002510 @default.
• W3110156989 cites W2964050021 @default.
• W3110156989 cites W2964094136 @default.
• W3110156989 cites W2981840821 @default.
• W3110156989 cites W2982697283 @default.
• W3110156989 cites W2984983779 @default.
• W3110156989 cites W2990737297 @default.
• W3110156989 cites W2991079364 @default.
• W3110156989 cites W3013135579 @default.
• W3110156989 doi "https://doi.org/10.1007/978-3-030-58565-5_37" @default.
• W3110156989 hasPublicationYear "2020" @default.
• W3110156989 type Work @default.
• W3110156989 sameAs 3110156989 @default.
• W3110156989 citedByCount "34" @default.
• W3110156989 countsByYear W31101569892021 @default.
• W3110156989 countsByYear W31101569892022 @default.
• W3110156989 countsByYear W31101569892023 @default.
• W3110156989 crossrefType "book-chapter" @default.
• W3110156989 hasAuthorship W3110156989A5008216150 @default.
• W3110156989 hasAuthorship W3110156989A5034842399 @default.
• W3110156989 hasAuthorship W3110156989A5053968661 @default.
• W3110156989 hasBestOaLocation W31101569892 @default.
• W3110156989 hasConcept C107457646 @default.
• W3110156989 hasConcept C115961682 @default.
• W3110156989 hasConcept C120665830 @default.
• W3110156989 hasConcept C121332964 @default.
• W3110156989 hasConcept C129315195 @default.
• W3110156989 hasConcept C154945302 @default.
• W3110156989 hasConcept C157202957 @default.
• W3110156989 hasConcept C162324750 @default.
• W3110156989 hasConcept C186644900 @default.
• W3110156989 hasConcept C187736073 @default.
• W3110156989 hasConcept C192209626 @default.
• W3110156989 hasConcept C2776674983 @default.
• W3110156989 hasConcept C2780451532 @default.
• W3110156989 hasConcept C31972630 @default.
• W3110156989 hasConcept C41008148 @default.
• W3110156989 hasConceptScore W3110156989C107457646 @default.
• W3110156989 hasConceptScore W3110156989C115961682 @default.
• W3110156989 hasConceptScore W3110156989C120665830 @default.
• W3110156989 hasConceptScore W3110156989C121332964 @default.
• W3110156989 hasConceptScore W3110156989C129315195 @default.
• W3110156989 hasConceptScore W3110156989C154945302 @default.
• W3110156989 hasConceptScore W3110156989C157202957 @default.
• W3110156989 hasConceptScore W3110156989C162324750 @default.
• W3110156989 hasConceptScore W3110156989C186644900 @default.
• W3110156989 hasConceptScore W3110156989C187736073 @default.
• W3110156989 hasConceptScore W3110156989C192209626 @default.
• W3110156989 hasConceptScore W3110156989C2776674983 @default.
• W3110156989 hasConceptScore W3110156989C2780451532 @default.
• W3110156989 hasConceptScore W3110156989C31972630 @default.
• W3110156989 hasConceptScore W3110156989C41008148 @default.
• W3110156989 hasLocation W31101569891 @default.
• W3110156989 hasLocation W31101569892 @default.
• W3110156989 hasOpenAccess W3110156989 @default.
• W3110156989 hasPrimaryLocation W31101569891 @default.
• W3110156989 hasRelatedWork W1024182683 @default.
• W3110156989 hasRelatedWork W2116300362 @default.
• W3110156989 hasRelatedWork W2123758101 @default.
• W3110156989 hasRelatedWork W2127108814 @default.
• W3110156989 hasRelatedWork W2134569597 @default.
• W3110156989 hasRelatedWork W2143630701 @default.
• W3110156989 hasRelatedWork W2370766994 @default.
• W3110156989 hasRelatedWork W2621079708 @default.
• W3110156989 hasRelatedWork W2890988828 @default.
• W3110156989 hasRelatedWork W4386043393 @default.
• W3110156989 isParatext "false" @default.
• W3110156989 isRetracted "false" @default.
• W3110156989 magId "3110156989" @default.
• W3110156989 workType "book-chapter" @default.