CHICAGO – September 12, 2018 ––STATS, the worldwide leader in sports data and intelligence, announced an expanded presence at the 2018 European Conference on Computer Vision (ECCV), with its presentation of the paper, “Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion Using Conditional Variational Autoencoders.”
ECCV is one of the highest-regarded research conferences on computer vision in the world, connecting leading experts in Munich, Germany from Sept. 8-14. STATS’ research paper focuses on predicting fine-grained motion patterns on basketball data, expanding upon “ghosting” research STATS has previously developed. The paper was authored by Panna Felsen, a Ph.D. student at the University of California, Berkeley and a former STATS intern; Sujoy Ganguly, Head of Computer Vision at STATS; and Dr. Patrick Lucey, Director of Artificial Intelligence at STATS.
“With nearly 2,500 papers submitted to ECCV, we are proud to have the opportunity to present our research to some of the best minds in our field,” said Ganguly. “STATS’ research creates computer vision applications that build models for sports predictions that are three times as accurate as previous state-of-the-art approaches. We are honored that academic conferences continually recognize STATS as the leading sports technology company in artificial intelligence and machine learning.”
Felsen will present the paper during a poster session on Wednesday, Sept. 12 from 5:15 – 6:45 p.m. CEST. For more information on the Data Science and Artificial Intelligence team, visit: statsperform.com/artificial-intelligence