Learning Video Object Segmentation from Static Images

CVPR 2017 Anna KhorevaFederico PerazziRodrigo BenensonBernt SchieleAlexander Sorkine-Hornung

Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation. Our model proceeds on a per-frame basis, guided by the output of the previous frame towards the object of interest in the next frame... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Visual Object Tracking DAVIS 2016 MSK Jaccard (Mean) 79.7 # 8
Jaccard (Recall) 93.1 # 6
Jaccard (Decay) 8.9 # 9
F-measure (Mean) 75.4 # 11
F-measure (Recall) 87.1 # 8
F-measure (Decay) 9.0 # 10
Visual Object Tracking DAVIS 2016 MSK_b Jaccard (Mean) 69.6 # 15

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Video Object Segmentation YouTube MaskTrack mIoU 0.726 # 7