GradNet: Gradient-Guided Network for Visual Object Tracking

ICCV 2019 Peixia LiBoyu ChenWanli OuyangDong WangXiaoyun YangHuchuan Lu

The fully-convolutional siamese network based on template matching has shown great potentials in visual tracking. During testing, the template is fixed with the initial target feature and the performance totally relies on the general matching ability of the siamese network... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Visual Object Tracking OTB-2015 GradNet Precision 0.861 # 1
Visual Object Tracking VOT2017 GradNet Expected Average Overlap (EAO) 0.247 # 4