Video tracking using learned hierarchical features

• Main Authors: Wang, Gang, Chan, Kap Luk, Liu, Ting, Yang, Qingxiong, Wang, Li
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
• Online Access: https://hdl.handle.net/10356/107287; http://hdl.handle.net/10220/25473; http://dx.doi.org/10.1109/TIP.2015.2403231
• Institution: Nanyang Technological University

In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer convolutional neural network. Embedding the tempor...