Fast and Accurate Online Video Object Segmentation via Tracking Parts

CVPR 2018 Jingchun ChengYi-Hsuan TsaiWei-Chih HungShengjin WangMing-Hsuan Yang

基于视频的目标检测算法研究..

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semi-Supervised Video Object Segmentation DAVIS 2016 FAVOS Jaccard (Mean) 82.4 # 14
Jaccard (Recall) 96.5 # 8
Jaccard (Decay) 4.5 # 25
F-measure (Mean) 79.5 # 18
F-measure (Recall) 89.4 # 14
F-measure (Decay) 5.5 # 8
J&F 80.95 # 17
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) FAVOS J&F 43.6 # 17
Jaccard (Mean) 42.9 # 18
Jaccard (Recall) 48.1 # 17
Jaccard (Decay) 18.1 # 3
F-measure (Mean) 44.2 # 20
F-measure (Recall) 51.1 # 17
F-measure (Decay) 19.8 # 6
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) FAVOS Jaccard (Mean) 54.6 # 19
Jaccard (Recall) 61.1 # 18
Jaccard (Decay) 14.1 # 5
F-measure (Mean) 61.8 # 19
F-measure (Recall) 72.3 # 16
F-measure (Decay) 18.0 # 6
J&F 58.2 # 20

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet