Robust Visual Tracking via Convolutional Networks Without Training

Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However, the offline training is time-consuming and the learned generic representation may be less discriminative for tracking specific objects. In this paper,...

Celý popis

Podrobná bibliografia

Vydané v:	IEEE transactions on image processing Ročník 25; číslo 4; s. 1779 - 1792
Hlavní autori:	Zhang, Kaihua, Liu, Qingshan, Wu, Yi, Yang, Ming-Hsuan
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 01.04.2016 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Computer architecture Convolutional Networks Deep learning Feature extraction Layout Robustness Target tracking Training Visual tracking Visualization deep learning Visual tracking convolutional networks
ISSN:	1057-7149, 1941-0042
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!