J&F: 63.4J: 61.5F: 65.3
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&F: 66.0J: 64.1F: 67.9
J&F: 62.9J: 61.3F: 64.6
J&F: 68.0J: 64.8F: 71.3
J&F: 65.7J: 63.9F: 67.4
J&F: 36.4J: 34.8F: 38.1
J&F: 64.9J: 61.7F: 68.1
J&F: 69.4J: 66.2F: 72.6
J&F: 74.2J: 69.9F: 78.5
J&F: 36.6tIoU: 68.4vIoU: 34.6
J&F: 54.5
J&F: 51.3tIoU: 71.2vIoU: 42.6
J&F: 64.3J: 61.8F: 66.8
J&F: 48.7tIoU: 71.7vIoU: 41.2
J&F: 35.6tIoU: 68.4vIoU: 28.6
J&F: 60.2J: 58.9F: 61.5
J&F: 51.6J: 47.3F: 56.0
J&F: 65.4J: 63.3F: 67.5
J&F: 63.8J: 61.9F: 65.6