Learning Discriminative Model Prediction for Tracking

15 Apr 2019Goutam BhatMartin DanelljanLuc Van GoolRadu Timofte

The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific appearance model online, during the inference stage... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Visual Object Tracking TrackingNet DiMP-50 Precision 68.7 # 2
Visual Object Tracking TrackingNet DiMP-50 Normalized Precision 80.1 # 1
Visual Object Tracking TrackingNet DiMP-50 Accuracy 74.0 # 1