Visual tracking with fully convolutional networks
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractWe propose a new approach for general object tracking with fully convolutional neural network. Instead of treating convolutional neural network (CNN) as a black-box feature extractor, we conduct in-depth study on the properties of CNN features offline pre-trained on massive image data and classification task on ImageNet. The discoveries motivate the design of our tracking system. It is found that convolutional layers in different levels characterize the target from different perspectives. A top layer encodes more semantic features and serves as a category detector, while a lower layer carries more discriminative information and can better separate the target from distracters with similar appearance. Both layers are jointly used with a switch mechanism during tracking. It is also found that for a tracking target, only a subset of neurons are relevant. A feature map selection method is developed to remove noisy and irrelevant feature maps, which can reduce computation redundancy and improve tracking accuracy. Extensive evaluation on the widely used tracking benchmark [36] shows that the proposed tacker outperforms the state-of-the-art significantly.
All Author(s) ListWang L., Ouyang W., Wang X., Lu H.
Name of Conference15th IEEE International Conference on Computer Vision, ICCV 2015
Start Date of Conference11/12/2015
End Date of Conference18/12/2015
Place of ConferenceSantiago
Country/Region of ConferenceRepublic of Chile
Detailed descriptionorganized by IEEE,
Year2016
Month2
Day17
Volume Number11-18-December-2015
Pages3119 - 3127
ISBN9781467383912
ISSN1550-5499
LanguagesEnglish-United Kingdom

Last updated on 2020-18-10 at 01:49