CNNTracker: Online discriminative object tracking via deep convolutional neural network

By Yan Chen, Xiangnan Yang, Bineng Zhong, Shengnan Pan, Duansheng Chen, Huizhen Zhang. 2016

101 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Recent advances in convolutional neural networks (2015, methodology): “In [145], a CNN object tracking method is proposed to address limitations of handcrafted features and shallow classifier structures in object tracking problem.”
A survey of deep neural network architectures and their applications (2017, methodology): “In addition, deep learning approaches have been successfully employed in motion estimation especially for video tracking tasks [22].”
Learning by Tracking: Siamese CNN for Robust Target Association (2016, methodology): “CNNs have been used to model appearance and scale variations of the target [18]. Recently, several authors employ them to track via online learning, by continuously ﬁne-tuning a pre-trained CNN model [8,37,51]. 2. Learning to associate detections Our tracking framework is based on the paradigm of tr”