F1-score (Canonical): 61.0
Papers with Code · CC BY-SA 4.0
Video Summarization
Video Summarization aims to generate a short synopsis that summarizes the video content by selecting its most informative and important parts. The produced summary is usually composed of a set of representative video frames (a.k.a. video key-frames), or video fragments (a.k.a. video key-fragments) that have been stitched in chronological order to form a shorter video. The former type of a video summary is known as video storyboard, and the latter type is known as video skim.
<span class="description-source">Source: Video Summarization Using Deep Neural Networks: A Survey</span> <br> <span style="color:grey; opacity: 0.6">Image credit: iJRASET</span>
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.
Dataset기록된 모델 예시MetricPaperCode
데이터셋
10개논문
F1-score (Canonical): 63.0F1-score (Augmented): 63.6
Kendall's Tau: 0.194Spearman's Rho: 0.255
F1-score (Canonical): 62.1F1-score (Augmented): 63.9
MAP (50%): 61.60
CIDEr: 8.6BLEU-4: 11.7METEOR: 19.7ROUGE: 26.8
CIDEr: 152.3BLEU-4: 7.67METEOR: 23.2ROUGE: 43
F1-score (Canonical): 61.42F1-score (Augmented): 62.37
F1-score (Canonical): 61.0F1-score (Augmented): 61.8
1 shot Micro-F1: 23.5
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.