TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/SoccerNet-v2: A Dataset and Benchmarks for Holistic Unders...

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

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

2020-11-26Video EditingAction SpottingReplay GroundingBoundary DetectionCamera shot boundary detectionVideo UnderstandingCamera shot segmentation
PaperPDFCodeCodeCodeCode

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 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.

Results

TaskDatasetMetricValueModel
VideoSoccerNet-v2Average-AP41.8CALF (Cioppa et al.)
VideoSoccerNet-v2Average-AP24.3NetVLAD (Giancola et al.)
VideoSoccerNet-v2Average-mAP39.9AudioVid (Vanderplaetse et al.)
VideoSoccerNet-v2Average-mAP31.4NetVLAD (Giancola et al.)
Scene ParsingSoccerNet-v2mIoU47.3CALF (Cioppa et al.)
Scene ParsingSoccerNet-v2mIoU35.8Baseline
Video Semantic SegmentationSoccerNet-v2mIoU47.3CALF (Cioppa et al.)
Video Semantic SegmentationSoccerNet-v2mIoU35.8Baseline
Scene UnderstandingSoccerNet-v2mIoU47.3CALF (Cioppa et al.)
Scene UnderstandingSoccerNet-v2mIoU35.8Baseline
Video RetrievalSoccerNet-v2Average-AP41.8CALF (Cioppa et al.)
Video RetrievalSoccerNet-v2Average-AP24.3NetVLAD (Giancola et al.)
Video SegmentationSoccerNet-v2mAP78.5Histogram (Scikit-Video)
Video SegmentationSoccerNet-v2mAP64Intensity (Scikit-Video)
Video SegmentationSoccerNet-v2mAP62.2Content (PySceneDetect)
Video SegmentationSoccerNet-v2mAP59.6CALF (Cioppa et al.)
2D Semantic SegmentationSoccerNet-v2mIoU47.3CALF (Cioppa et al.)
2D Semantic SegmentationSoccerNet-v2mIoU35.8Baseline

Related Papers

VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding2025-07-17SAMST: A Transformer framework based on SAM pseudo label filtering for remote sensing semi-supervised semantic segmentation2025-07-16UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks2025-07-15EmbRACE-3K: Embodied Reasoning and Action in Complex Environments2025-07-14Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI2025-07-14Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices2025-07-09Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation2025-07-08Omni-Video: Democratizing Unified Video Understanding and Generation2025-07-08