Please use this identifier to cite or link to this item: https://doi.org/10.1145/2502081.2502126
DC FieldValue
dc.titleWow You are so beautiful today
dc.contributor.authorLiu, L.
dc.contributor.authorXu, H.
dc.contributor.authorXing, J.
dc.contributor.authorLiu, S.
dc.contributor.authorZhou, X.
dc.contributor.authorYan, S.
dc.date.accessioned2014-06-19T03:32:48Z
dc.date.available2014-06-19T03:32:48Z
dc.date.issued2013
dc.identifier.citationLiu, L.,Xu, H.,Xing, J.,Liu, S.,Zhou, X.,Yan, S. (2013). Wow You are so beautiful today. MM 2013 - Proceedings of the 2013 ACM Multimedia Conference : 3-12. ScholarBank@NUS Repository. <a href="https://doi.org/10.1145/2502081.2502126" target="_blank">https://doi.org/10.1145/2502081.2502126</a>
dc.identifier.isbn9781450324045
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/72217
dc.description.abstractBeauty e-Experts, a fully automatic system for hairstyle and facial makeup recommendation and synthesis, is devel- oped in this work. Given a user-provided frontal face image with short/bound hair and no/light makeup, the Beauty e-Experts system can not only recommend the most suit- Able hairdo and makeup, but also show the synthetic ef- fects. To obtain enough knowledge for beauty modeling, we build the Beauty e-Experts Database, which contains 1; 505 attractive female photos with a variety of beauty at- Tributes and beauty-related attributes annotated. Based on this Beauty e-Experts Dataset, two problems are consid- ered for the Beauty e-Experts system: what to recommend and how to wear, which describe a similar process of se- lecting hairstyle and cosmetics in our daily life. For the what-to-recommend problem, we propose a multiple tree- structured super-graphs model to explore the complex rela- Tionships among the high-level beauty attributes, mid-level beauty-related attributes and low-level image features, and then based on this model, the most compatible beauty at- Tributes for a given facial image can be efficiently inferred. For the how-to-wear problem, an effective and efficient facial image synthesis module is designed to seamlessly synthesize the recommended hairstyle and makeup into the user facial image. Extensive experimental evaluations and analysis on testing images of various conditions well demonstrate the effectiveness of the proposed system. Copyright © 2013 ACM.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1145/2502081.2502126
dc.sourceScopus
dc.subjectBeauty recommendation
dc.subjectBeauty synthesis
dc.subjectMultiple tree- structured super-graphs model
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1145/2502081.2502126
dc.description.sourcetitleMM 2013 - Proceedings of the 2013 ACM Multimedia Conference
dc.description.page3-12
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

18
checked on May 22, 2019

Page view(s)

186
checked on May 22, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.