TY - GEN
T1 - Wow you are so beautiful today
AU - Liu, Luoqi
AU - Xu, Hui
AU - Liu, Si
AU - Xing, Junliang
AU - Zhou, Xi
AU - Yan, Shuicheng
PY - 2013
Y1 - 2013
N2 - In this demo, we present Beauty e-Experts, a fully auto- matic system for hairstyle and facial makeup recommenda- Tion and synthesis. Given a user-provided frontal facial im- Age with short/bound hair and no/light makeup, the Beauty e-Experts system can not only recommend the most suit- Able hairstyle and makeup, but also show the synthesis ef- fects. Two problems are considered for the Beauty e-Experts system: what to recommend and how to wear, which de- scribe a similar process of selecting and applying 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 relationships among the beauty attributes, beauty-related attributes and image features, and then based on this model, the most suitable beauty at- Tributes for a given facial image can be eficiently inferred. For the how-to-wear problem, a facial image synthesis mod- ule is designed to seamlessly blend the recommended hairstyle and makeup into the user facial image. Extensive experi- mental evaluations and analysis on testing images well demon- strate the effectiveness of the proposed system.
AB - In this demo, we present Beauty e-Experts, a fully auto- matic system for hairstyle and facial makeup recommenda- Tion and synthesis. Given a user-provided frontal facial im- Age with short/bound hair and no/light makeup, the Beauty e-Experts system can not only recommend the most suit- Able hairstyle and makeup, but also show the synthesis ef- fects. Two problems are considered for the Beauty e-Experts system: what to recommend and how to wear, which de- scribe a similar process of selecting and applying 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 relationships among the beauty attributes, beauty-related attributes and image features, and then based on this model, the most suitable beauty at- Tributes for a given facial image can be eficiently inferred. For the how-to-wear problem, a facial image synthesis mod- ule is designed to seamlessly blend the recommended hairstyle and makeup into the user facial image. Extensive experi- mental evaluations and analysis on testing images well demon- strate the effectiveness of the proposed system.
KW - Beauty recommendation
KW - Beauty synthesis
KW - Multiple tree- structured super-graphs model
UR - https://www.scopus.com/pages/publications/84887440816
U2 - 10.1145/2502081.2502258
DO - 10.1145/2502081.2502258
M3 - 会议稿件
AN - SCOPUS:84887440816
SN - 9781450324045
T3 - MM 2013 - Proceedings of the 2013 ACM Multimedia Conference
SP - 437
EP - 438
BT - MM 2013 - Proceedings of the 2013 ACM Multimedia Conference
T2 - 21st ACM International Conference on Multimedia, MM 2013
Y2 - 21 October 2013 through 25 October 2013
ER -