Papers with Code · CC BY-SA 4.0

Camera shot boundary detection

Video Segmentation › Camera shot boundary detection 19 평가 기록 4 datasets

The objective of camera shot boundary detection is to find the transitions between the camera shots in a video and classify the type of camera transition. This task is introduced in SoccerNet-v2, where 3 types of transitions are considered (abrupt, logo, smooth).

논문

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

2011.13367 2020-11-26 이 페이지의 평가 4건

mAP: 78.5

Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks

1705.03281 2017-05-09 이 페이지의 평가 3건

F score: 0.7534FPS: 86

A novel automatic shot boundary detection algorithm: robust to illumination and motion effect

2019-11-10 이 페이지의 평가 2건

F score: 0.8470FPS: 24

AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection

2304.06116 2023-04-12 이 페이지의 평가 1건

F1 score: 78.7

Fast Video Shot Transition Localization with Deep Structured Models

1808.04234 2018-08-13 이 페이지의 평가 1건

F1 score: 76.1

Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks

1705.08214 2017-05-23 이 페이지의 평가 1건

F score: 0.7492FPS: 94

TransNet V2: An effective deep network architecture for fast shot transition detection

2008.04838 2020-08-11 이 페이지의 평가 1건

F1 score: 77.9

TransNet: A deep network for fast detection of common shot transitions

1906.03363 2019-06-08 이 페이지의 평가 1건

F score: 0.7686FPS: 93