SoccerNet-V2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos

Adrien Deliège, Anthony Cioppa, Silvio Giancola, Meisam Jamshidi Seikavandi, Jacob V. Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck

CVPRW 2021 pp. 4508-4519

doi:10.1109/CVPRW53098.2021.00508 /cvprw/2021/deliege2021cvprw-soccernetv2/

Abstract

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.

PDF CVPRW Semantic Scholar

Cite

Text

Deliège et al. "SoccerNet-V2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00508

Markdown

[Deliège et al. "SoccerNet-V2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/deliege2021cvprw-soccernetv2/) doi:10.1109/CVPRW53098.2021.00508

BibTeX

@inproceedings{deliege2021cvprw-soccernetv2,
  title     = {{SoccerNet-V2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos}},
  author    = {Deliège, Adrien and Cioppa, Anthony and Giancola, Silvio and Seikavandi, Meisam Jamshidi and Dueholm, Jacob V. and Nasrollahi, Kamal and Ghanem, Bernard and Moeslund, Thomas B. and Van Droogenbroeck, Marc},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {4508-4519},
  doi       = {10.1109/CVPRW53098.2021.00508},
  url       = {https://mlanthology.org/cvprw/2021/deliege2021cvprw-soccernetv2/}
}