Robust visual tracking based on deep sparse learning
X WANG, Z HOU, W YU, Z JIN - 北京航空航天大学学报, 2017 - bhxb.buaa.edu.cn
In visual tracking, the efficient and robust feature representation plays an important role in
tracking performance in complicated environment. Therefore, a deep sparse neural network
model which can extract more intrinsic and abstract features was proposed. Meanwhile, the
complex and time-consuming pre-training process was avoided by using this model. During
online tracking, the method of data augmentation was employed in the single positive
sample to balance the quantities of positive and negative samples, which can improve the …
tracking performance in complicated environment. Therefore, a deep sparse neural network
model which can extract more intrinsic and abstract features was proposed. Meanwhile, the
complex and time-consuming pre-training process was avoided by using this model. During
online tracking, the method of data augmentation was employed in the single positive
sample to balance the quantities of positive and negative samples, which can improve the …
[CITATION][C] Soil near-infrared spectroscopy prediction model based on deep sparse learning
JR Wang, TJ Chen, YB Wang, LS Wang, CJ Xie… - Chinese Journal of …, 2017
Showing the best results for this search. See all results