Communications of the ACM
AI Tool Detects Global Fashion Trends
A new artificial intelligence tool can scan millions of publicly available photos to identify fashion trends around the world, as well as traditions and events with signature styles.
Researchers at Cornell University developed an artificial intelligence tool that scans millions of publicly available photos to effectively identify fashion trends around the world, as well as traditions and events with signature styles.
The GeoStyle tool analyzes public Instagram and Flickr photos to map trends using computer vision and neural networks.
The models help researchers understand existing trends in specific cities, and across the world as a whole.
GeoStyle's trend forecasts are up to 20% more accurate than previous methods.
The team also created a visualizer that allows users to view the popularity of a certain attribute—such as a pattern, hat, or color—by city, over time.
Said Cornell researcher Kavita Bala, "One of our follow-ups from this work is improving the technology so that if you add a little expert information, you can improve the recognition and get an even finer-grained understanding."
From Cornell Chronicle (NY)
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found