</> Code with Papers by Syntology

Papers › SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos

SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos

26 Nov 2020arXiv:2011.13367archive 2025-07-28

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

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

SilvioGiancola/SoccerNetv2-DevKit mentioned on GitHubpytorch report
aimagelab/rmsnet_soccer mentioned on GitHubpytorch report
soccernet/sn-grounding mentioned on GitHubpytorch report
soccernet/sn-spotting mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action SpottingBoundary DetectionCamera shot boundary detectionCamera shot segmentationReplay GroundingVideo EditingVideo Understanding

Datasets

Introduced by this paper, per the archive.

SoccerNet-v2

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Spotting SoccerNet-v2 AudioVid (Vanderplaetse et al.) Average-mAP 39.9 #9 of 10 Archive leaderboard report
Action Spotting SoccerNet-v2 NetVLAD (Giancola et al.) Average-mAP 31.4 #10 of 10 Archive leaderboard report
Camera shot boundary detection SoccerNet-v2 Histogram (Scikit-Video) mAP 78.5 #1 of 4 Archive leaderboard report
Camera shot boundary detection SoccerNet-v2 Intensity (Scikit-Video) mAP 64.0 #2 of 4 Archive leaderboard report
Camera shot boundary detection SoccerNet-v2 Content (PySceneDetect) mAP 62.2 #3 of 4 Archive leaderboard report
Camera shot boundary detection SoccerNet-v2 CALF (Cioppa et al.) mAP 59.6 #4 of 4 Archive leaderboard report
Camera shot segmentation SoccerNet-v2 CALF (Cioppa et al.) mIoU 47.3 #1 of 2 Archive leaderboard report
Camera shot segmentation SoccerNet-v2 Baseline mIoU 35.8 #2 of 2 Archive leaderboard report
Replay Grounding SoccerNet-v2 CALF (Cioppa et al.) Average-AP 41.8 #1 of 2 Archive leaderboard report
Replay Grounding SoccerNet-v2 NetVLAD (Giancola et al.) Average-AP 24.3 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections