Deep Learning for Fashion Style and Online Shopping
Using artificial intelligence technology and social media data to facilitate fashion and online customer shopping has attracted a lot of attention from both academia and industry. Deep learning-based methods show huge improvement compared to traditional handcraft features in many fields such as visual classification, retrieval and generation. However, existing deep learning or other machine learning methods may not fully address the challenges in fashion style and online shopping. In this talk, I will cover three works, (i). fashion style classification, (ii). cross-domain street-to-shop clothing retrieval, and (iii). fashion style generation. I will present deep learning algorithms to learn robust and discriminative feature representation for these tasks.
Shuhui Jiang received the B.E. and M.E. degrees from Xi'an Jiaotong University, Xi'an, China, in 2011 and 2014, respectively, and a Ph.D. degree in Electrical and Computer Engineering from Northeastern University, Boston, USA, in 2018. Her research interests are Artificial Intelligence, especially machine learning, computer vision, multimedia, and big data mining. She was the recipient of the Dean's Fellowship of Northeastern University from 2014. She was the recipient of the Best Paper Award in ACM TOMM and Best Paper Candidate in ACM MM. She has served as the PC member for AAAI, ACM MM, etc., and the reviewer for international journals such as IEEE TNNLS/TIP/TMM/THMS/TBioCAS/TCYB/Access.