Robust Multiple Instance Learning Fast Compressive Tracking
Year: 2016
Type: article
Abstract: Fast compressive tracking algorithm performs more effective and robust than some other state-of-art tracking algorithm, it crop samples from the current frame, all these samples have the same weighted in learning procedure, in order to integrates the sample importance into the learning procedure, motived by the weighted multiple instance learning algorithm, we present a novel enhanced fast compressive tracking, which integrates the samples importance into learning procedure. Experimental results on various benchmark video sequences demonstrate the superior performance of our algorithm.
Authors: Li Hong Wang, Rui Wu, Jin Gao
Institution: Lanzhou Technology and Business College
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W2595550564