computer-vision-1
Camera shot segmentation
3260 papers • 126 benchmarks • 313 datasets
Camera shot temporal segmentation consists in classifying each video frame according to the type of camera used to record said frame. This task is introduced with the SoccerNet-v2 dataset, where 13 camera classes are considered (main camera, behind the goal, corner camera, etc.).
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in camera-shot-segmentation-1
Trend
Dataset
Best Model
Actions
SoccerNet-v2
SoccerNet-v2
Libraries
iUse these libraries to find camera-shot-segmentation-1 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
Bernard Ghanem, T. Moeslund, A. Deliège, A. Cioppa, Silvio Giancola, M. J. Seikavandi, J. Dueholm, Kamal Nasrollahi, Marc Van Droogenbroeck•Wed Nov 25 2020
This work proposes 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, and extends current tasks in the realm of soccer to include action spotting, camera shot segmentation with boundary detection, and a novel replay grounding task.