GeoStyle: Discovering Fashion Trends and Events
This addresses the need for retailers and consumers to understand and predict fashion trends and events from social media imagery, representing a domain-specific incremental advancement.
The paper tackles the problem of analyzing spatial and temporal trends in fashion attributes from street imagery, providing an automatic framework that discovers and forecasts long-term trends and identifies localized events affecting fashion, with results showing >20% more accurate trend forecasts than prior art and identification of hundreds of socially meaningful events.
Understanding fashion styles and trends is of great potential interest to retailers and consumers alike. The photos people upload to social media are a historical and public data source of how people dress across the world and at different times. While we now have tools to automatically recognize the clothing and style attributes of what people are wearing in these photographs, we lack the ability to analyze spatial and temporal trends in these attributes or make predictions about the future. In this paper, we address this need by providing an automatic framework that analyzes large corpora of street imagery to (a) discover and forecast long-term trends of various fashion attributes as well as automatically discovered styles, and (b) identify spatio-temporally localized events that affect what people wear. We show that our framework makes long term trend forecasts that are >20% more accurate than the prior art, and identifies hundreds of socially meaningful events that impact fashion across the globe.