Please use this identifier to cite or link to this item: http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/1293
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKokul, T.
dc.contributor.authorFookes, C.
dc.contributor.authorSridharan, C.
dc.contributor.authorRamanan, A.
dc.contributor.authorPinidiyaarachchi, U.A.J.
dc.date.accessioned2019-11-25T07:14:27Z
dc.date.accessioned2022-06-27T04:11:22Z-
dc.date.available2019-11-25T07:14:27Z
dc.date.available2022-06-27T04:11:22Z-
dc.date.issued2017-09-17
dc.identifier.issn2381-8549
dc.identifier.urihttp://repo.lib.jfn.ac.lk/ujrr/handle/123456789/1293-
dc.description.abstractConvolutional neural networks (CNNs) have been employedin visual tracking due to their rich levels of feature representation.While the learning capability of a CNN increaseswith its depth, unfortunately spatial information is diluted indeeper layers which hinders its important ability to localize targets. To successfully manage this trade-off, we propose anovel residual network based gating CNN architecture for objecttracking. Our deep model connects the front and bottomconvolutional features with a gate layer. This new networklearns discriminative features while reducing the spatial informationlost. This architecture is pre-trained to learn generictracking characteristics. In online tracking, an efficient domainadaptation mechanism is used to accurately learn thetarget appearance with limited samples. Extensive evaluationperformed on a publicly available benchmark dataset demonstratesour proposed tracker outperforms state-of-the-art approaches.en_US
dc.language.isoen_USen_US
dc.publisherIEEE, IEEE International Conference on Image Processing (ICIP)en_US
dc.subjectobject trackingen_US
dc.subjectdomain adaptationen_US
dc.subjectCNNen_US
dc.titleGate connected convolutional neural network for object trackingen_US
dc.typeArticleen_US
Appears in Collections:Physical Science

Files in This Item:
File Description SizeFormat 
Gate connected convolutional neural network for object tracking.pdf52.86 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.