Automatic Curation of Golf Highlights using Multimodal Excitement Features

TL;DR

This paper presents a multimodal system that automatically identifies exciting moments in golf videos by analyzing player reactions, crowd noise, and commentator tone, reducing manual effort and enabling personalized highlight reels.

Contribution

It introduces a novel multimodal approach for sports highlight curation that combines multiple data sources and reduces manual annotation, demonstrated in a real-world golf tournament setting.

Findings

Successfully extracted highlights from live golf streams over four days

Achieved accurate start and end frame detection of key moments

Reduced manual annotation through correlation of modalities

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 use it to create a real-world system for the editorial aid of golf highlight reels. Our method fuses information from the players' reactions (action recognition such as high-fives and fist pumps), spectators (crowd cheering), and commentator (tone of the voice and word analysis) to determine the most interesting moments of a game. We accurately identify the start and end frames of key shot highlights with additional metadata, such as the player's name and the hole number, allowing personalized content summarization and retrieval. In addition, we introduce new techniques for learning our classifiers with reduced manual training data annotation by exploiting the correlation of different modalities. Our work has been demonstrated at a major golf tournament, successfully extracting highlights from live video streams over four consecutive days.