The Excitement of Sports: Automatic Highlights Using Audio/Visual Cues

Michele Merler, Dhiraj Joshi, Khoi-Nguyen C. Mac, Quoc-Bao Nguyen, Stephen Hammer, John Kent, Jinjun Xiong, Minh N. Do, John R. Smith, Rogerio S. Feris; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 2520-2523

Abstract


The production of sports highlight packages summarizing a game's most exciting moments is an essential task for broadcast media. Yet, it requires labor-intensive video editing. We propose a novel approach for auto-curating sports highlights, and demonstrate it to create a first of a kind, real-world system for the editorial aid of golf and tennis highlight reels. Our method fuses information from the players' reactions (action recognition such as high-fives and fist pumps), players' expressions (aggressive, tense, smiling and neutral), spectators (crowd cheering), commentator (tone of the voice and word analysis) and game analytics to determine the most interesting moments of a game.

Related Material


[pdf]
[bibtex]
@InProceedings{Merler_2018_CVPR_Workshops,
author = {Merler, Michele and Joshi, Dhiraj and Mac, Khoi-Nguyen C. and Nguyen, Quoc-Bao and Hammer, Stephen and Kent, John and Xiong, Jinjun and Do, Minh N. and Smith, John R. and Feris, Rogerio S.},
title = {The Excitement of Sports: Automatic Highlights Using Audio/Visual Cues},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}