Efficient Video Object Segmentation via Network Modulation

CVPR 2018 Linjie YangYanran WangXuehan XiongJianchao YangAggelos K. Katsaggelos

Video object segmentation targets at segmenting a specific object throughout a video sequence, given only an annotated first frame. Recent deep learning based approaches find it effective by fine-tuning a general-purpose segmentation model on the annotated frame using hundreds of iterations of gradient descent... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Visual Object Tracking DAVIS 2016 OSMN Jaccard (Mean) 74.0 # 12
Jaccard (Recall) 87.6 # 11
Jaccard (Decay) 9.0 # 10
F-measure (Mean) 72.9 # 12
F-measure (Recall) 84.0 # 11
F-measure (Decay) 10.6 # 13
Visual Object Tracking DAVIS-2017 OSMN Jaccard (Mean) 52.5 # 8
Jaccard (Recall) 60.9 # 5
Jaccard (Decay) 21.5 # 3
F-measure (Mean) 57.1 # 7
F-measure (Recall) 66.1 # 5
F-measure (Decay) 24.3 # 3
Visual Object Tracking YouTube-VOS OSMN Jaccard (Seen) 60.0 # 3
O (Average of Measures) 51.2 # 4
F-Measure (Seen) 60.1 # 3
F-Measure (Unseen) 44.0 # 4
One-Shot Visual Object Segmentation YouTube-VOS OSMN F-Measure (Seen) 60.1 # 3
F-Measure (Unseen) 44.0 # 3
Jaccard (Seen) 60.0 # 2
Jaccard (Unseen) 40.6 # 3
Video Object Segmentation YouTube-VOS OSMN F-Measure (Seen) 60.1 # 4
F-Measure (Unseen) 44.0 # 4
Overall 51.2 # 4
Speed (FPS) 7.14 # 2
Jaccard (Seen) 60.0 # 3
Jaccard (Unseen) 40.6 # 4