Image Style Classification and Its Application on User Engagement

In this project, we will apply machine learning to perform image style classification. We will build a system that uses image style classification to increase user engagement in an eCommerce platform setting. We will study the effects of user preferences for particular image styles on their engagement with the platform.
Image style classification is the task of categorizing an image based on attributes such as composition style (e.g., minimal, geometric, etc.), atmosphere (hazy, sunny), or colour (pastel, bright). Several machine learning techniques that perform automatic image style classification have been proposed recently. We will create a new large-scale dataset of images and critically evaluate the different techniques.
We hypothesize that individual users have a consistent preference for particular image styles, and that this fact can be used to increase user engagement using an automatic image style classification system. A rigorous user study will be conducted to test this hypothesis.

Faculty Supervisor:

Matt Medland

Student:

Thi Hai Van Do

Partner:

ContextLogic Technologies Inc

Discipline:

Computer science

Sector:

Information and communications technologies

University:

Program: