J&F: 71.7J: 67.6F: 75.8FPS: 17.9
Papers with Code · CC BY-SA 4.0
Semi-Supervised Video Object Segmentation
The semi-supervised scenario assumes the user inputs a full mask of the object(s) of interest in the first frame of a video sequence. Methods have to produce the segmentation mask for that object(s) in the subsequent frames.
논문
J&F: 57.6J: 53.3F: 62.0
Jaccard (Mean): 86.7F-measure (Mean): 93.0J&F: 89.8
J&F: 66.5J: 62.3F: 70.8FPS: 25.3
J&F: 77.9
J&F: 57.2J: 53.1F: 61.3
J&F: 59.4J: 55.1F: 63.8
Jaccard (Mean): 69.1Jaccard (Recall): 79.1Jaccard (Decay): 17.5F-measure (Recall): 83.8
Jaccard (Mean): 85.2F-measure (Mean): 91.0J&F: 88.1
J&F: 48.8J: 44.6F: 52.9
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
J&F: 50.8J: 46.6F: 55.0
J&F: 50.9J: 46.8F: 54.9