期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
卷 -, 期 -, 页码 4503-4514出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPRW53098.2021.00508
关键词
-
资金
- DeepSport project of theWalloon Region
- FRIA
- KAUST Office of Sponsored Research [OSR-CRG2017-3405]
- Milestone Research Program at Aalborg University
The study introduces SoccerNet-v2, a large-scale manual annotation corpus for the SoccerNet video dataset, and proposes open challenges to encourage research in soccer understanding and broadcast production. It extends current tasks in soccer-related fields and provides benchmark results for tasks such as action spotting, camera shot segmentation, and replay grounding.
Understanding broadcast videos is a challenging task in computer vision, as it requires generic reasoning capabilities to appreciate the content offered by the video editing. In this work, we propose SoccerNet-v2, a novel large-scale corpus of manual annotations for the SoccerNet [24] video dataset, along with open challenges to encourage more research in soccer understanding and broadcast production. Specifically, we release around 300k annotations within SoccerNet's 500 untrimmed broadcast soccer videos. We extend current tasks in the realm of soccer to include action spotting, camera shot segmentation with boundary detection, and we define a novel replay grounding task. For each task, we provide and discuss benchmark results, reproducible with our open-source adapted implementations of the most relevant works in the field. SoccerNet-v2 is presented to the broader research community to help push computer vision closer to automatic solutions for more general video understanding and production purposes.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据