We proposed a novel and a Hierarchical Feature Model (HFM) for multi-target tracking. The traditional tracking algorithms
use handcrafted features that cannot track targets accurately when the target model changes due to articulation,
different illuminations and perspective distortions. Our HFM explore deep features to model the appearance of targets.
Then, we explore an unsupervised dimensionality reduction for sparse representation of the feature vectors to cope
with the time-critical nature of the tracking problem. Subsequently, a Bayesian filter is adopted as the tracker and a discrete
combinatorial optimization is considered for target association. We compare proposed HFM against 4 state-of-the-art
trackers using 4 benchmark datasets. The experimental results show that our HFM outperforms all the state-of-the-art
methods in terms of both Multi Object Tracking Accuracy (MOTA) and Multi Object Tracking Precision (MOTP).