2 papers
cs.CV2019
End-to-End Learning Deep CRF models for Multi-Object Tracking
Jun Xiang, Ma Chao, Guohan Xu +1
Existing deep multi-object tracking (MOT) approaches first learn a deep representation to describe target objects and then associate detection results by optimizing a linear assign…
cs.CV2018
Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly
Jun Xiang, Guoshuai Zhang, Jianhua Hou +2
Designing a robust affinity model is the key issue in multiple target tracking (MTT). This paper proposes a novel affinity model by learning feature representation and distance met…