https://github.com/Tangshitao/ClipShots
공식 코드Fast Video Shot Transition Localization with Deep Structured Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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).
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Fast Video Shot Transition Localization with Deep Structured Models
TransNet: A deep network for fast detection of common shot transitions
TransNet V2: An effective deep network architecture for fast shot transition detection
AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
TransNet: A deep network for fast detection of common shot transitions
TransNet V2: An effective deep network architecture for fast shot transition detection
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
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.