F1@10%: 85.1Edit: 81.9Acc: 85.9F1@25%: 85.4
Papers with Code · CC BY-SA 4.0
Action Segmentation
Action Segmentation is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.
<span class="description-source">Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation </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.
데이터셋
15개논문
F1@10%: 92.7Edit: 87.5Acc: 91.4F1@25%: 91.6
F1@10%: 89.2Edit: 83.8Acc: 88.1F1@25%: 87.8
F1@10%: 87.6Edit: 81.7Acc: 86.9F1@25%: 86.5
F1@10%: 90.1Edit: 85.0Acc: 88.9F1@25%: 89.2
F1@10%: 89.2Edit: 82.9Acc: 87.4F1@25%: 87.5
F1@10%: 89.3Edit: 84.2Acc: 89.5F1@25%: 88.4
F1@10%: 89.4Edit: 83.2Acc: 87.7F1@25%: 87.7
F1@10%: 87.8Edit: 82.0Acc: 87.2F1@25%: 86.3
F1@10%: 91.5Edit: 89.1Acc: 88.6F1@25%: 90.2
F1@10%: 89.1Edit: 84.4Acc: 89.8F1@25%: 88.0
F1@10%: 89.1Edit: 83.9Acc: 87.4F1@25%: 87.6
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.