F1-score: 61.4Spearman's Rho: 0.106Kendall's Tau: 0.08
Papers with Code · CC BY-SA 4.0
Unsupervised Video Summarization
Unsupervised video summarization approaches overcome the need for ground-truth data (whose production requires time-demanding and laborious manual annotation procedures), based on learning mechanisms that require only an adequately large collection of original videos for their training. Specifically, the training is based on heuristic rules, like the sparsity, the representativeness, and the diversity of the utilized input features/characteristics.
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
데이터셋
2개논문
F1-score: 58.8Spearman's Rho: 0.034Kendall's Tau: 0.025training time (s): 1797
F1-score: 62Parameters (M): 5.25
F1-score: 58.4training time (s): 3895Parameters (M): 23.31
F1-score: 60.6training time (s): 9380Parameters (M): 26.75
F1-score: 54.48
F1-score: 57.6
F1-score: 57.6Spearman's Rho: 0.026Kendall's Tau: 0.020training time (s): 58.8
F1-score: 58.3training time (s): 5423Parameters (M): 24.31
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.