NCSI: A Knowledge-Based Recommender System Using A Single Portrait Image

Status	Completed
Mentor Name	Hao Ji
Mentor's XSEDE Affiliation	Education Allocation
Mentor Has Been in XSEDE Community	4-5 years
Project Title	A Knowledge-Based Recommender System Using A Single Portrait Image
Summary	Recommender systems provide an essential means of recommending items to users that meet their needs or preferences, which have proven to be beneficial in e-commerce society. However, an important but often overlooked information in recommender systems is a customer's portrait images. Recent progress in Computer Vision techniques and Deep Learning research has drastically improved the ability of a computer to sense and analyze data from a single 2D image. In this project, we will study a new knowledge-based recommender system using a single portrait image. In particular, we plan to use deep facial 2D/3D attributes to build a knowledge graph, and explore visualization results to examine physical correctness and visual plausibility of the generated recommendations.
Job Description	The student will study deep learning approaches to obtaining informative features from a single portrait image, build knowledge graph based on deep features and metadata, and investigate visualization and/or animation to examine the visual plausibility of recommendations.
Computational Resources	XSEDE Bridges GPUs
Contribution to Community
Position Type	Apprentice
Training Plan	I will teach the students with the necessary knowledge and skills in Deep Learning and also on how to use XSEDE for training. During this project, I will work closely with the students and plan to have weekly meetings with them to guide their research progress.
Student Prerequisites/Conditions/Qualifications	Must have an undergraduate at California State Polytechnic University, Pomona
Duration	Semester
Start Date	08/22/2019
End Date	12/08/2019