مؤتمر
SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
| العنوان: | SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos |
|---|---|
| المؤلفون: | Deliège, Adrien, Cioppa, Anthony, Giancola, Silvio, Seikavandi, Meisam, Dueholm, Jacob, Nasrollahi, Kamal, Ghanem, Bernard, Moeslund, Thomas, Van Droogenbroeck, Marc |
| المساهمون: | Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège, Telim |
| المصدر: | IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 4508-4519 (2021-06); IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), CVsports, Nashville, TN, United States [US], du 19 juin 2021 au 25 juin 2021 |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | SoccerNet-v2, SoccerNet, Dataset, Training data, Soccer, Football, Classification, Action, Annotation, Neural network, Deep learning, Machine learning, Artificial intelligence, DeepSport, Engineering, computing & technology, Electrical & electronics engineering, Ingénierie, informatique & technologie, Ingénierie électrique & électronique |
| الوصف: | 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 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. DeepSport |
| نوع الوثيقة: | conference paper http://purl.org/coar/resource_type/c_5794 conferenceObject peer reviewed |
| اللغة: | English |
| DOI: | 10.1109/CVPRW53098.2021.00508 |
| URL الوصول: | https://orbi.uliege.be/handle/2268/253781 |
| حقوق: | open access http://purl.org/coar/access_right/c_abf2 info:eu-repo/semantics/openAccess |
| رقم الأكسشن: | edsorb.253781 |
| قاعدة البيانات: | ORBi |
| DOI: | 10.1109/CVPRW53098.2021.00508 |
|---|