J&F: 62.1
Papers with Code · CC BY-SA 4.0
Unsupervised Video Object Segmentation
The unsupervised scenario assumes that the user does not interact with the algorithm to obtain the segmentation masks. Methods should provide a set of object candidates with no overlapping pixels that span through the whole video sequence. This set of objects should contain at least the objects that capture human attention when watching the whole video sequence i.e objects that are more likely to be followed by human gaze.
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
6개논문
G: 87.3J: 87.1F: 87.5
G: 87.6J: 86.8F: 88.4
G: 88.9J: 88.3F: 89.6
G: 88.5J: 88.0F: 89.0
J&F: 45.6Jaccard (Mean): 42.1Jaccard (Recall): 48.5Jaccard (Decay): 2.6
J&F: 41.7Jaccard (Mean): 38.9Jaccard (Recall): 44.3Jaccard (Decay): -2.7
J&F: 40.4Jaccard (Mean): 37.7Jaccard (Recall): 42.6Jaccard (Decay): 4.0
J&F: 22.5Jaccard (Mean): 17.7Jaccard (Recall): 16.2Jaccard (Decay): 1.6
G: 87.2J: 86.6F: 87.8
J&F: 58.0Jaccard (Mean): 54.0Jaccard (Recall): 62.9Jaccard (Decay): 3.5
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.