J: 57.6F: 62.5J&F: 60R: 18.9
Papers with Code · CC BY-SA 4.0
Referring Video Object Segmentation
Referring video object segmentation aims at segmenting an object in video with language expressions. Unlike the previous video object segmentation, the task exploits a different type of supervision, language expressions, to identify and segment an object referred by the given language expressions in a video.
논문
J: 25.1F: 25.9J&F: 25.5R: 5.6
J&F: 53.2J: 50.5F: 55.9
J&F: 70.6J: 68.2F: 72.9
J: 26.2F: 29.9J&F: 28.1R: 8.8
J: 21.2F: 31.7J&F: 26.4R: 3.2
J&F: 42.7J: 39.9F: 45.5
J: 48.8F: 52.9J&F: 50.9R: 14.5
J&F: 46.4J: 43F: 49.8
J&F: 51.3J: 48.5F: 54.2
J&F: 68.5
J&F: 32
J&F: 29.3J: 27.8F: 30.8
J: 39.8F: 43.5J&F: 41.6R: 8.6
J&F: 53.7J: 50.7F: 56.7
J&F: 47.6J: 44.1F: 51.1
J&F: 49.3J: 44.7F: 53.9
J&F: 48.3J: 45.4F: 51.2
J: 43.2F: 46.8J&F: 45.0R: 12.8
J&F: 27.8J: 25.7F: 29.9
J&F: 35.5J: 33.6F: 37.3